diff --git a/1a_Breakout-v0_train.ipynb b/1a_Breakout-v0_train.ipynb new file mode 100644 index 0000000..46f026b --- /dev/null +++ b/1a_Breakout-v0_train.ipynb @@ -0,0 +1,62232 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "7d1fa20c", + "metadata": {}, + "outputs": [], + "source": [ + "import os, sys\n", + "import gc\n", + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c3d9f370", + "metadata": {}, + "outputs": [], + "source": [ + "sys.path.append('../')\n", + "import torch" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "c8c767df", + "metadata": {}, + "outputs": [], + "source": [ + "from get_algos import get_all_algos , run_experiment ,create_paths" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "c9fc3531", + "metadata": {}, + "outputs": [], + "source": [ + "import gym\n", + "from gym.wrappers import Monitor\n", + "from stable_baselines3 import PPO, A2C, DDPG, DQN, SAC, TD3\n", + "from stable_baselines3.common.vec_env import VecFrameStack\n", + "from stable_baselines3.common.evaluation import evaluate_policy\n", + "from stable_baselines3.common.env_util import make_atari_env" + ] + }, + { + "cell_type": "markdown", + "id": "e1d33e3c", + "metadata": {}, + "source": [ + "### 1. Explore breakout environment\n", + "" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "1aad3196", + "metadata": {}, + "outputs": [], + "source": [ + "env_name='Breakout-v0'\n", + "env=gym.make(env_name)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "df2cd276", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Action space: Discrete(4)\n", + "Observation space shape: Box([[[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " ...\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]], [[[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " ...\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]], (210, 160, 3), uint8)\n", + "Action space shape: ()\n", + "Observation space shape: (210, 160, 3)\n" + ] + } + ], + "source": [ + "print('Action space: ',env.action_space)\n", + "print('Observation space shape: ',env.observation_space)\n", + "print('Action space shape: ',env.action_space.shape)\n", + "print('Observation space shape: ',env.observation_space.shape)" + ] + }, + { + "cell_type": "markdown", + "id": "a195559a", + "metadata": {}, + "source": [ + "#Taking a look at how breakout looks and simulate random actions\n", + "env.reset()\n", + "rewards_all=[]\n", + "for epi in range(50):\n", + " state=env.reset()\n", + " rewards=0\n", + " while True:\n", + " action=env.action_space.sample()\n", + " state,reward,done,_=env.step(action)\n", + " env.render()\n", + " rewards+=reward\n", + " if done:\n", + " rewards_all.append(rewards)\n", + " if (epi+1)%5==0:\n", + " print('Episode: ',epi+1,' Reward: ',rewards)\n", + " break \n", + "env.close()\n", + "print('Average rewards for random action Breakout-v0 is: ',sum(rewards_all)/len(rewards_all))" + ] + }, + { + "cell_type": "markdown", + "id": "54c5cdd5", + "metadata": {}, + "source": [ + "### 2. Training\n", + "
    \n", + "
  1. Make the atari env using make_atari_env
  2. \n", + "
  3. Parallelize the learning using VecFrameStack
  4. \n", + "
  5. Create train function for all appropriate algos
  6. \n", + "
  7. Train
  8. \n", + "
  9. Store model
  10. \n", + "
" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "00e701da", + "metadata": {}, + "outputs": [], + "source": [ + "def train_breakout(algo_name, env_name,n_steps,device='cuda'):\n", + " if algo_name=='DQN': #GPU was unable to load the entire experience relay so moved to virtual memory on disk\n", + " device='cpu'\n", + " log_path, render_path, model_path=create_paths(algo_name,env_name,n_steps)\n", + " env=make_atari_env(env_name)\n", + " env=VecFrameStack(env, n_stack=6)\n", + " model=eval(algo_name)('CnnPolicy',env, tensorboard_log=log_path,verbose=1,device=device)\n", + " model.learn(n_steps)\n", + " model.save(os.path.join(model_path,env_name+\"_\"+algo_name+\"_\"+\"model\"))\n", + " del model\n", + " env.close()\n", + "\n", + " return log_path, render_path, model_path" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "65fae03b", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['PPO', 'A2C', 'DQN']\n" + ] + } + ], + "source": [ + "algo_list=get_all_algos(gym.make(env_name))\n", + "print(algo_list)" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "ebcf18c9", + "metadata": {}, + "outputs": [], + "source": [ + "models_records={}\n", + "n_steps=200000" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "52178f03", + "metadata": {}, + "outputs": [], + "source": [ + "def train_experiment(algo_list, env_name,n_steps, models_records):\n", + " for algo in reversed(algo_list):\n", + " print('******* Training ',algo,' *******')\n", + " model_record={}\n", + " log_path, render_path, model_path=train_breakout(algo, env_name,n_steps)\n", + " model_record['log']=log_path\n", + " model_record['render']=render_path\n", + " model_record['model']=model_path\n", + " models_records[algo]=model_record\n", + " gc.collect()\n", + " torch.cuda.empty_cache()" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "0a4d7aa0", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "******* Training DQN *******\n", + "Using cpu device\n", + "Wrapping the env in a VecTransposeImage.\n", + "Logging to Breakout-v0\\DQN_200000\\logs\\DQN_1\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "E:\\Anaconda\\envs\\ai_gym\\lib\\site-packages\\stable_baselines3\\common\\buffers.py:229: UserWarning: This system does not have apparently enough memory to store the complete replay buffer 84.69GB > 13.06GB\n", + " \"This system does not have apparently enough memory to store the complete \"\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| exploration_rate | 0.998 |\n", + "| time/ | |\n", + "| episodes | 4 |\n", + "| fps | 206 |\n", + "| time_elapsed | 0 |\n", + "| total_timesteps | 40 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1 |\n", + "| exploration_rate | 0.996 |\n", + "| time/ | |\n", + "| episodes | 8 |\n", + "| fps | 264 |\n", + "| time_elapsed | 0 |\n", + "| total_timesteps | 83 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 256 |\n", + "| ep_rew_mean | 1 |\n", + "| exploration_rate | 0.992 |\n", + "| time/ | |\n", + "| episodes | 12 |\n", + "| fps | 315 |\n", + "| time_elapsed | 0 |\n", + "| total_timesteps | 160 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 317 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.991 |\n", + "| time/ | |\n", + "| episodes | 16 |\n", + "| fps | 316 |\n", + "| time_elapsed | 0 |\n", + "| total_timesteps | 194 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 319 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.988 |\n", + "| time/ | |\n", + "| episodes | 20 |\n", + "| fps | 327 |\n", + "| time_elapsed | 0 |\n", + "| total_timesteps | 249 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 319 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.986 |\n", + "| time/ | |\n", + "| episodes | 24 |\n", + "| fps | 332 |\n", + "| time_elapsed | 0 |\n", + "| total_timesteps | 288 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.985 |\n", + "| time/ | |\n", + "| episodes | 28 |\n", + "| fps | 324 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 325 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.983 |\n", + "| time/ | |\n", + "| episodes | 32 |\n", + "| fps | 323 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.981 |\n", + "| time/ | |\n", + "| episodes | 36 |\n", + "| fps | 326 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 400 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.978 |\n", + "| time/ | |\n", + "| episodes | 40 |\n", + "| fps | 334 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 466 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.976 |\n", + "| time/ | |\n", + "| episodes | 44 |\n", + "| fps | 338 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 502 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.974 |\n", + "| time/ | |\n", + "| episodes | 48 |\n", + "| fps | 342 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 544 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.972 |\n", + "| time/ | |\n", + "| episodes | 52 |\n", + "| fps | 344 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 587 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.971 |\n", + "| time/ | |\n", + "| episodes | 56 |\n", + "| fps | 342 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 613 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.968 |\n", + "| time/ | |\n", + "| episodes | 60 |\n", + "| fps | 342 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 672 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.967 |\n", + "| time/ | |\n", + "| episodes | 64 |\n", + "| fps | 343 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 697 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.965 |\n", + "| time/ | |\n", + "| episodes | 68 |\n", + "| fps | 341 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 733 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.964 |\n", + "| time/ | |\n", + "| episodes | 72 |\n", + "| fps | 340 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 758 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.961 |\n", + "| time/ | |\n", + "| episodes | 76 |\n", + "| fps | 342 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 819 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.959 |\n", + "| time/ | |\n", + "| episodes | 80 |\n", + "| fps | 342 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 858 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.955 |\n", + "| time/ | |\n", + "| episodes | 84 |\n", + "| fps | 350 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 947 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.954 |\n", + "| time/ | |\n", + "| episodes | 88 |\n", + "| fps | 347 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 972 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.95 |\n", + "| time/ | |\n", + "| episodes | 92 |\n", + "| fps | 351 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 1046 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.949 |\n", + "| time/ | |\n", + "| episodes | 96 |\n", + "| fps | 349 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1072 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.947 |\n", + "| time/ | |\n", + "| episodes | 100 |\n", + "| fps | 350 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1112 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.946 |\n", + "| time/ | |\n", + "| episodes | 104 |\n", + "| fps | 350 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1138 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.944 |\n", + "| time/ | |\n", + "| episodes | 108 |\n", + "| fps | 350 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1174 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.943 |\n", + "| time/ | |\n", + "| episodes | 112 |\n", + "| fps | 349 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1209 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.941 |\n", + "| time/ | |\n", + "| episodes | 116 |\n", + "| fps | 349 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1249 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.939 |\n", + "| time/ | |\n", + "| episodes | 120 |\n", + "| fps | 347 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1282 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.937 |\n", + "| time/ | |\n", + "| episodes | 124 |\n", + "| fps | 349 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1330 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.936 |\n", + "| time/ | |\n", + "| episodes | 128 |\n", + "| fps | 347 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1354 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.932 |\n", + "| time/ | |\n", + "| episodes | 132 |\n", + "| fps | 344 |\n", + "| time_elapsed | 4 |\n", + "| total_timesteps | 1435 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.93 |\n", + "| time/ | |\n", + "| episodes | 136 |\n", + "| fps | 327 |\n", + "| time_elapsed | 4 |\n", + "| total_timesteps | 1476 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.928 |\n", + "| time/ | |\n", + "| episodes | 140 |\n", + "| fps | 325 |\n", + "| time_elapsed | 4 |\n", + "| total_timesteps | 1517 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.927 |\n", + "| time/ | |\n", + "| episodes | 144 |\n", + "| fps | 325 |\n", + "| time_elapsed | 4 |\n", + "| total_timesteps | 1540 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.926 |\n", + "| time/ | |\n", + "| episodes | 148 |\n", + "| fps | 324 |\n", + "| time_elapsed | 4 |\n", + "| total_timesteps | 1566 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.924 |\n", + "| time/ | |\n", + "| episodes | 152 |\n", + "| fps | 321 |\n", + "| time_elapsed | 4 |\n", + "| total_timesteps | 1592 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.923 |\n", + "| time/ | |\n", + "| episodes | 156 |\n", + "| fps | 316 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 1615 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.921 |\n", + "| time/ | |\n", + "| episodes | 160 |\n", + "| fps | 315 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 1672 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.918 |\n", + "| time/ | |\n", + "| episodes | 164 |\n", + "| fps | 316 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 1723 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.916 |\n", + "| time/ | |\n", + "| episodes | 168 |\n", + "| fps | 316 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 1766 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.915 |\n", + "| time/ | |\n", + "| episodes | 172 |\n", + "| fps | 316 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 1792 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.913 |\n", + "| time/ | |\n", + "| episodes | 176 |\n", + "| fps | 316 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 1834 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.911 |\n", + "| time/ | |\n", + "| episodes | 180 |\n", + "| fps | 316 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 1867 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.909 |\n", + "| time/ | |\n", + "| episodes | 184 |\n", + "| fps | 318 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 1924 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.907 |\n", + "| time/ | |\n", + "| episodes | 188 |\n", + "| fps | 318 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 1965 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.905 |\n", + "| time/ | |\n", + "| episodes | 192 |\n", + "| fps | 319 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2005 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.903 |\n", + "| time/ | |\n", + "| episodes | 196 |\n", + "| fps | 319 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2040 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.9 |\n", + "| time/ | |\n", + "| episodes | 200 |\n", + "| fps | 320 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2106 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.899 |\n", + "| time/ | |\n", + "| episodes | 204 |\n", + "| fps | 321 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2132 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.897 |\n", + "| time/ | |\n", + "| episodes | 208 |\n", + "| fps | 320 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2158 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.895 |\n", + "| time/ | |\n", + "| episodes | 212 |\n", + "| fps | 322 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2217 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.894 |\n", + "| time/ | |\n", + "| episodes | 216 |\n", + "| fps | 322 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2241 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.892 |\n", + "| time/ | |\n", + "| episodes | 220 |\n", + "| fps | 322 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2278 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.891 |\n", + "| time/ | |\n", + "| episodes | 224 |\n", + "| fps | 322 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2304 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.887 |\n", + "| time/ | |\n", + "| episodes | 228 |\n", + "| fps | 323 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2371 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.886 |\n", + "| time/ | |\n", + "| episodes | 232 |\n", + "| fps | 323 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2397 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.883 |\n", + "| time/ | |\n", + "| episodes | 236 |\n", + "| fps | 324 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2453 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.882 |\n", + "| time/ | |\n", + "| episodes | 240 |\n", + "| fps | 324 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2475 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.881 |\n", + "| time/ | |\n", + "| episodes | 244 |\n", + "| fps | 324 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2500 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.88 |\n", + "| time/ | |\n", + "| episodes | 248 |\n", + "| fps | 324 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2524 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.878 |\n", + "| time/ | |\n", + "| episodes | 252 |\n", + "| fps | 324 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2560 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.875 |\n", + "| time/ | |\n", + "| episodes | 256 |\n", + "| fps | 325 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 2629 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.873 |\n", + "| time/ | |\n", + "| episodes | 260 |\n", + "| fps | 325 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 2670 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.871 |\n", + "| time/ | |\n", + "| episodes | 264 |\n", + "| fps | 326 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 2711 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.869 |\n", + "| time/ | |\n", + "| episodes | 268 |\n", + "| fps | 327 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 2760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.868 |\n", + "| time/ | |\n", + "| episodes | 272 |\n", + "| fps | 327 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 2786 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.866 |\n", + "| time/ | |\n", + "| episodes | 276 |\n", + "| fps | 327 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 2821 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.865 |\n", + "| time/ | |\n", + "| episodes | 280 |\n", + "| fps | 326 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 2845 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.862 |\n", + "| time/ | |\n", + "| episodes | 284 |\n", + "| fps | 328 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 2912 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.861 |\n", + "| time/ | |\n", + "| episodes | 288 |\n", + "| fps | 327 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 2936 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.858 |\n", + "| time/ | |\n", + "| episodes | 292 |\n", + "| fps | 328 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 2980 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.857 |\n", + "| time/ | |\n", + "| episodes | 296 |\n", + "| fps | 328 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3020 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.854 |\n", + "| time/ | |\n", + "| episodes | 300 |\n", + "| fps | 329 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3074 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.853 |\n", + "| time/ | |\n", + "| episodes | 304 |\n", + "| fps | 328 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3098 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.851 |\n", + "| time/ | |\n", + "| episodes | 308 |\n", + "| fps | 328 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3139 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.85 |\n", + "| time/ | |\n", + "| episodes | 312 |\n", + "| fps | 328 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3164 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.848 |\n", + "| time/ | |\n", + "| episodes | 316 |\n", + "| fps | 329 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3208 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.846 |\n", + "| time/ | |\n", + "| episodes | 320 |\n", + "| fps | 328 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3234 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.845 |\n", + "| time/ | |\n", + "| episodes | 324 |\n", + "| fps | 329 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3257 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.844 |\n", + "| time/ | |\n", + "| episodes | 328 |\n", + "| fps | 328 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3283 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.843 |\n", + "| time/ | |\n", + "| episodes | 332 |\n", + "| fps | 328 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3307 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.841 |\n", + "| time/ | |\n", + "| episodes | 336 |\n", + "| fps | 328 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3348 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.839 |\n", + "| time/ | |\n", + "| episodes | 340 |\n", + "| fps | 329 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3386 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.838 |\n", + "| time/ | |\n", + "| episodes | 344 |\n", + "| fps | 329 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3411 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.837 |\n", + "| time/ | |\n", + "| episodes | 348 |\n", + "| fps | 329 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3437 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.833 |\n", + "| time/ | |\n", + "| episodes | 352 |\n", + "| fps | 329 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3512 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.831 |\n", + "| time/ | |\n", + "| episodes | 356 |\n", + "| fps | 330 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3554 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.83 |\n", + "| time/ | |\n", + "| episodes | 360 |\n", + "| fps | 330 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3580 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.828 |\n", + "| time/ | |\n", + "| episodes | 364 |\n", + "| fps | 330 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3631 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.824 |\n", + "| time/ | |\n", + "| episodes | 368 |\n", + "| fps | 332 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 3715 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.822 |\n", + "| time/ | |\n", + "| episodes | 372 |\n", + "| fps | 332 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 3755 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.82 |\n", + "| time/ | |\n", + "| episodes | 376 |\n", + "| fps | 332 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 3781 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.819 |\n", + "| time/ | |\n", + "| episodes | 380 |\n", + "| fps | 332 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 3808 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.817 |\n", + "| time/ | |\n", + "| episodes | 384 |\n", + "| fps | 333 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 3846 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.815 |\n", + "| time/ | |\n", + "| episodes | 388 |\n", + "| fps | 333 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 3902 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.812 |\n", + "| time/ | |\n", + "| episodes | 392 |\n", + "| fps | 334 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 3949 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.809 |\n", + "| time/ | |\n", + "| episodes | 396 |\n", + "| fps | 335 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4031 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.807 |\n", + "| time/ | |\n", + "| episodes | 400 |\n", + "| fps | 335 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4056 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.805 |\n", + "| time/ | |\n", + "| episodes | 404 |\n", + "| fps | 336 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4107 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.803 |\n", + "| time/ | |\n", + "| episodes | 408 |\n", + "| fps | 336 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4149 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.802 |\n", + "| time/ | |\n", + "| episodes | 412 |\n", + "| fps | 336 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4177 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.8 |\n", + "| time/ | |\n", + "| episodes | 416 |\n", + "| fps | 336 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4204 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.799 |\n", + "| time/ | |\n", + "| episodes | 420 |\n", + "| fps | 336 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4228 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.797 |\n", + "| time/ | |\n", + "| episodes | 424 |\n", + "| fps | 336 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4275 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.796 |\n", + "| time/ | |\n", + "| episodes | 428 |\n", + "| fps | 336 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4302 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.793 |\n", + "| time/ | |\n", + "| episodes | 432 |\n", + "| fps | 337 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4356 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.791 |\n", + "| time/ | |\n", + "| episodes | 436 |\n", + "| fps | 337 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 4398 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.789 |\n", + "| time/ | |\n", + "| episodes | 440 |\n", + "| fps | 336 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 4438 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.788 |\n", + "| time/ | |\n", + "| episodes | 444 |\n", + "| fps | 337 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 4462 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.787 |\n", + "| time/ | |\n", + "| episodes | 448 |\n", + "| fps | 336 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 4487 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.785 |\n", + "| time/ | |\n", + "| episodes | 452 |\n", + "| fps | 336 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 4524 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.782 |\n", + "| time/ | |\n", + "| episodes | 456 |\n", + "| fps | 337 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 4580 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.779 |\n", + "| time/ | |\n", + "| episodes | 460 |\n", + "| fps | 337 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 4646 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.778 |\n", + "| time/ | |\n", + "| episodes | 464 |\n", + "| fps | 337 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 4670 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.776 |\n", + "| time/ | |\n", + "| episodes | 468 |\n", + "| fps | 337 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 4726 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.773 |\n", + "| time/ | |\n", + "| episodes | 472 |\n", + "| fps | 338 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 4784 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.771 |\n", + "| time/ | |\n", + "| episodes | 476 |\n", + "| fps | 337 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 4811 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.769 |\n", + "| time/ | |\n", + "| episodes | 480 |\n", + "| fps | 337 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 4853 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.768 |\n", + "| time/ | |\n", + "| episodes | 484 |\n", + "| fps | 337 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 4879 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.767 |\n", + "| time/ | |\n", + "| episodes | 488 |\n", + "| fps | 337 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 4903 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.766 |\n", + "| time/ | |\n", + "| episodes | 492 |\n", + "| fps | 336 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 4929 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.764 |\n", + "| time/ | |\n", + "| episodes | 496 |\n", + "| fps | 337 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 4978 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.761 |\n", + "| time/ | |\n", + "| episodes | 500 |\n", + "| fps | 337 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 5029 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.759 |\n", + "| time/ | |\n", + "| episodes | 504 |\n", + "| fps | 338 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 5077 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.755 |\n", + "| time/ | |\n", + "| episodes | 508 |\n", + "| fps | 339 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5152 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.753 |\n", + "| time/ | |\n", + "| episodes | 512 |\n", + "| fps | 339 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5193 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.751 |\n", + "| time/ | |\n", + "| episodes | 516 |\n", + "| fps | 340 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5235 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.75 |\n", + "| time/ | |\n", + "| episodes | 520 |\n", + "| fps | 339 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5260 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.748 |\n", + "| time/ | |\n", + "| episodes | 524 |\n", + "| fps | 340 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5311 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.746 |\n", + "| time/ | |\n", + "| episodes | 528 |\n", + "| fps | 340 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5347 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.744 |\n", + "| time/ | |\n", + "| episodes | 532 |\n", + "| fps | 340 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5389 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.743 |\n", + "| time/ | |\n", + "| episodes | 536 |\n", + "| fps | 340 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5415 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.741 |\n", + "| time/ | |\n", + "| episodes | 540 |\n", + "| fps | 340 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 5455 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.74 |\n", + "| time/ | |\n", + "| episodes | 544 |\n", + "| fps | 340 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 5482 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.738 |\n", + "| time/ | |\n", + "| episodes | 548 |\n", + "| fps | 340 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 5520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.736 |\n", + "| time/ | |\n", + "| episodes | 552 |\n", + "| fps | 340 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 5556 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.735 |\n", + "| time/ | |\n", + "| episodes | 556 |\n", + "| fps | 340 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 5579 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.734 |\n", + "| time/ | |\n", + "| episodes | 560 |\n", + "| fps | 340 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 5604 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.732 |\n", + "| time/ | |\n", + "| episodes | 564 |\n", + "| fps | 340 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 5645 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.731 |\n", + "| time/ | |\n", + "| episodes | 568 |\n", + "| fps | 340 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 5670 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.729 |\n", + "| time/ | |\n", + "| episodes | 572 |\n", + "| fps | 340 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 5712 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.727 |\n", + "| time/ | |\n", + "| episodes | 576 |\n", + "| fps | 340 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 5747 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.724 |\n", + "| time/ | |\n", + "| episodes | 580 |\n", + "| fps | 341 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 5816 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.722 |\n", + "| time/ | |\n", + "| episodes | 584 |\n", + "| fps | 341 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 5843 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.721 |\n", + "| time/ | |\n", + "| episodes | 588 |\n", + "| fps | 340 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 5869 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.72 |\n", + "| time/ | |\n", + "| episodes | 592 |\n", + "| fps | 340 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 5893 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.719 |\n", + "| time/ | |\n", + "| episodes | 596 |\n", + "| fps | 339 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 5919 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.717 |\n", + "| time/ | |\n", + "| episodes | 600 |\n", + "| fps | 340 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 5960 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.716 |\n", + "| time/ | |\n", + "| episodes | 604 |\n", + "| fps | 339 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 5983 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.715 |\n", + "| time/ | |\n", + "| episodes | 608 |\n", + "| fps | 339 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 6006 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.19 |\n", + "| exploration_rate | 0.713 |\n", + "| time/ | |\n", + "| episodes | 612 |\n", + "| fps | 338 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 6045 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.2 |\n", + "| exploration_rate | 0.711 |\n", + "| time/ | |\n", + "| episodes | 616 |\n", + "| fps | 338 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 6088 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.708 |\n", + "| time/ | |\n", + "| episodes | 620 |\n", + "| fps | 338 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 6153 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.706 |\n", + "| time/ | |\n", + "| episodes | 624 |\n", + "| fps | 338 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 6192 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.705 |\n", + "| time/ | |\n", + "| episodes | 628 |\n", + "| fps | 337 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 6216 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.703 |\n", + "| time/ | |\n", + "| episodes | 632 |\n", + "| fps | 336 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 6243 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.16 |\n", + "| exploration_rate | 0.702 |\n", + "| time/ | |\n", + "| episodes | 636 |\n", + "| fps | 335 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 6269 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.15 |\n", + "| exploration_rate | 0.701 |\n", + "| time/ | |\n", + "| episodes | 640 |\n", + "| fps | 335 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 6295 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.15 |\n", + "| exploration_rate | 0.699 |\n", + "| time/ | |\n", + "| episodes | 644 |\n", + "| fps | 335 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 6346 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.697 |\n", + "| time/ | |\n", + "| episodes | 648 |\n", + "| fps | 334 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 6371 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.696 |\n", + "| time/ | |\n", + "| episodes | 652 |\n", + "| fps | 334 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 6395 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.694 |\n", + "| time/ | |\n", + "| episodes | 656 |\n", + "| fps | 333 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 6435 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.693 |\n", + "| time/ | |\n", + "| episodes | 660 |\n", + "| fps | 332 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 6467 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.691 |\n", + "| time/ | |\n", + "| episodes | 664 |\n", + "| fps | 332 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 6503 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.15 |\n", + "| exploration_rate | 0.69 |\n", + "| time/ | |\n", + "| episodes | 668 |\n", + "| fps | 331 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 6529 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.15 |\n", + "| exploration_rate | 0.689 |\n", + "| time/ | |\n", + "| episodes | 672 |\n", + "| fps | 331 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 6555 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.14 |\n", + "| exploration_rate | 0.687 |\n", + "| time/ | |\n", + "| episodes | 676 |\n", + "| fps | 330 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 6582 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.16 |\n", + "| exploration_rate | 0.684 |\n", + "| time/ | |\n", + "| episodes | 680 |\n", + "| fps | 331 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 6643 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.16 |\n", + "| exploration_rate | 0.683 |\n", + "| time/ | |\n", + "| episodes | 684 |\n", + "| fps | 330 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 6667 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.13 |\n", + "| exploration_rate | 0.681 |\n", + "| time/ | |\n", + "| episodes | 688 |\n", + "| fps | 330 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 6706 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.13 |\n", + "| exploration_rate | 0.68 |\n", + "| time/ | |\n", + "| episodes | 692 |\n", + "| fps | 330 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 6731 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.13 |\n", + "| exploration_rate | 0.678 |\n", + "| time/ | |\n", + "| episodes | 696 |\n", + "| fps | 330 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 6772 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 256 |\n", + "| ep_rew_mean | 1.1 |\n", + "| exploration_rate | 0.677 |\n", + "| time/ | |\n", + "| episodes | 700 |\n", + "| fps | 329 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 6795 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 256 |\n", + "| ep_rew_mean | 1.1 |\n", + "| exploration_rate | 0.676 |\n", + "| time/ | |\n", + "| episodes | 704 |\n", + "| fps | 329 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 6829 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.12 |\n", + "| exploration_rate | 0.672 |\n", + "| time/ | |\n", + "| episodes | 708 |\n", + "| fps | 329 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 6901 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.669 |\n", + "| time/ | |\n", + "| episodes | 712 |\n", + "| fps | 329 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 6974 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.665 |\n", + "| time/ | |\n", + "| episodes | 716 |\n", + "| fps | 330 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 7059 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.19 |\n", + "| exploration_rate | 0.663 |\n", + "| time/ | |\n", + "| episodes | 720 |\n", + "| fps | 330 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 7100 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.19 |\n", + "| exploration_rate | 0.662 |\n", + "| time/ | |\n", + "| episodes | 724 |\n", + "| fps | 330 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 7126 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.66 |\n", + "| time/ | |\n", + "| episodes | 728 |\n", + "| fps | 329 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 7150 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.16 |\n", + "| exploration_rate | 0.658 |\n", + "| time/ | |\n", + "| episodes | 732 |\n", + "| fps | 330 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 7193 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.657 |\n", + "| time/ | |\n", + "| episodes | 736 |\n", + "| fps | 329 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 7231 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.16 |\n", + "| exploration_rate | 0.655 |\n", + "| time/ | |\n", + "| episodes | 740 |\n", + "| fps | 329 |\n", + "| time_elapsed | 22 |\n", + "| total_timesteps | 7255 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.16 |\n", + "| exploration_rate | 0.653 |\n", + "| time/ | |\n", + "| episodes | 744 |\n", + "| fps | 329 |\n", + "| time_elapsed | 22 |\n", + "| total_timesteps | 7312 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.651 |\n", + "| time/ | |\n", + "| episodes | 748 |\n", + "| fps | 328 |\n", + "| time_elapsed | 22 |\n", + "| total_timesteps | 7353 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.19 |\n", + "| exploration_rate | 0.648 |\n", + "| time/ | |\n", + "| episodes | 752 |\n", + "| fps | 327 |\n", + "| time_elapsed | 22 |\n", + "| total_timesteps | 7413 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.647 |\n", + "| time/ | |\n", + "| episodes | 756 |\n", + "| fps | 327 |\n", + "| time_elapsed | 22 |\n", + "| total_timesteps | 7440 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.642 |\n", + "| time/ | |\n", + "| episodes | 760 |\n", + "| fps | 327 |\n", + "| time_elapsed | 22 |\n", + "| total_timesteps | 7527 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.64 |\n", + "| time/ | |\n", + "| episodes | 764 |\n", + "| fps | 327 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 7583 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.638 |\n", + "| time/ | |\n", + "| episodes | 768 |\n", + "| fps | 327 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 7630 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.635 |\n", + "| time/ | |\n", + "| episodes | 772 |\n", + "| fps | 327 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 7691 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.633 |\n", + "| time/ | |\n", + "| episodes | 776 |\n", + "| fps | 327 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 7717 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.631 |\n", + "| time/ | |\n", + "| episodes | 780 |\n", + "| fps | 327 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 7759 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.63 |\n", + "| time/ | |\n", + "| episodes | 784 |\n", + "| fps | 327 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 7782 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.628 |\n", + "| time/ | |\n", + "| episodes | 788 |\n", + "| fps | 327 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 7826 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.626 |\n", + "| time/ | |\n", + "| episodes | 792 |\n", + "| fps | 327 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 7878 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.625 |\n", + "| time/ | |\n", + "| episodes | 796 |\n", + "| fps | 327 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 7902 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.623 |\n", + "| time/ | |\n", + "| episodes | 800 |\n", + "| fps | 327 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 7943 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.621 |\n", + "| time/ | |\n", + "| episodes | 804 |\n", + "| fps | 327 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 7982 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.62 |\n", + "| time/ | |\n", + "| episodes | 808 |\n", + "| fps | 327 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 8007 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.618 |\n", + "| time/ | |\n", + "| episodes | 812 |\n", + "| fps | 327 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 8035 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.617 |\n", + "| time/ | |\n", + "| episodes | 816 |\n", + "| fps | 326 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 8061 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.615 |\n", + "| time/ | |\n", + "| episodes | 820 |\n", + "| fps | 326 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 8111 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.611 |\n", + "| time/ | |\n", + "| episodes | 824 |\n", + "| fps | 326 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 8187 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.61 |\n", + "| time/ | |\n", + "| episodes | 828 |\n", + "| fps | 326 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 8211 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.609 |\n", + "| time/ | |\n", + "| episodes | 832 |\n", + "| fps | 326 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 8235 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.608 |\n", + "| time/ | |\n", + "| episodes | 836 |\n", + "| fps | 326 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 8263 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.604 |\n", + "| time/ | |\n", + "| episodes | 840 |\n", + "| fps | 326 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 8337 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.602 |\n", + "| time/ | |\n", + "| episodes | 844 |\n", + "| fps | 326 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 8378 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.6 |\n", + "| time/ | |\n", + "| episodes | 848 |\n", + "| fps | 326 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 8413 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.599 |\n", + "| time/ | |\n", + "| episodes | 852 |\n", + "| fps | 326 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 8437 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.596 |\n", + "| time/ | |\n", + "| episodes | 856 |\n", + "| fps | 326 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 8497 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.595 |\n", + "| time/ | |\n", + "| episodes | 860 |\n", + "| fps | 326 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 8520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.593 |\n", + "| time/ | |\n", + "| episodes | 864 |\n", + "| fps | 326 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 8576 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.591 |\n", + "| time/ | |\n", + "| episodes | 868 |\n", + "| fps | 326 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 8617 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.589 |\n", + "| time/ | |\n", + "| episodes | 872 |\n", + "| fps | 327 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 8659 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.587 |\n", + "| time/ | |\n", + "| episodes | 876 |\n", + "| fps | 326 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 8685 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.586 |\n", + "| time/ | |\n", + "| episodes | 880 |\n", + "| fps | 326 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 8710 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.584 |\n", + "| time/ | |\n", + "| episodes | 884 |\n", + "| fps | 327 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 8752 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.582 |\n", + "| time/ | |\n", + "| episodes | 888 |\n", + "| fps | 327 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 8802 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.58 |\n", + "| time/ | |\n", + "| episodes | 892 |\n", + "| fps | 327 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 8844 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.579 |\n", + "| time/ | |\n", + "| episodes | 896 |\n", + "| fps | 326 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 8868 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.575 |\n", + "| time/ | |\n", + "| episodes | 900 |\n", + "| fps | 327 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 8940 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.574 |\n", + "| time/ | |\n", + "| episodes | 904 |\n", + "| fps | 327 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 8965 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.573 |\n", + "| time/ | |\n", + "| episodes | 908 |\n", + "| fps | 326 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 8991 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.2 |\n", + "| exploration_rate | 0.571 |\n", + "| time/ | |\n", + "| episodes | 912 |\n", + "| fps | 326 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 9033 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.57 |\n", + "| time/ | |\n", + "| episodes | 916 |\n", + "| fps | 325 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 9059 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.566 |\n", + "| time/ | |\n", + "| episodes | 920 |\n", + "| fps | 326 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 9139 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.564 |\n", + "| time/ | |\n", + "| episodes | 924 |\n", + "| fps | 326 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 9189 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.562 |\n", + "| time/ | |\n", + "| episodes | 928 |\n", + "| fps | 326 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 9228 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.56 |\n", + "| time/ | |\n", + "| episodes | 932 |\n", + "| fps | 325 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 9260 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.558 |\n", + "| time/ | |\n", + "| episodes | 936 |\n", + "| fps | 325 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 9301 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.556 |\n", + "| time/ | |\n", + "| episodes | 940 |\n", + "| fps | 325 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 9344 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.554 |\n", + "| time/ | |\n", + "| episodes | 944 |\n", + "| fps | 325 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 9383 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.553 |\n", + "| time/ | |\n", + "| episodes | 948 |\n", + "| fps | 325 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 9407 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.552 |\n", + "| time/ | |\n", + "| episodes | 952 |\n", + "| fps | 325 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 9432 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.549 |\n", + "| time/ | |\n", + "| episodes | 956 |\n", + "| fps | 324 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 9490 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.548 |\n", + "| time/ | |\n", + "| episodes | 960 |\n", + "| fps | 324 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 9516 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.546 |\n", + "| time/ | |\n", + "| episodes | 964 |\n", + "| fps | 324 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 9552 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.544 |\n", + "| time/ | |\n", + "| episodes | 968 |\n", + "| fps | 324 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 9593 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.543 |\n", + "| time/ | |\n", + "| episodes | 972 |\n", + "| fps | 324 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 9615 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.542 |\n", + "| time/ | |\n", + "| episodes | 976 |\n", + "| fps | 324 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 9640 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.54 |\n", + "| time/ | |\n", + "| episodes | 980 |\n", + "| fps | 324 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 9686 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.539 |\n", + "| time/ | |\n", + "| episodes | 984 |\n", + "| fps | 324 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 9711 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.537 |\n", + "| time/ | |\n", + "| episodes | 988 |\n", + "| fps | 323 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 9749 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.534 |\n", + "| time/ | |\n", + "| episodes | 992 |\n", + "| fps | 324 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 9817 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.532 |\n", + "| time/ | |\n", + "| episodes | 996 |\n", + "| fps | 324 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 9858 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.53 |\n", + "| time/ | |\n", + "| episodes | 1000 |\n", + "| fps | 324 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 9885 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.527 |\n", + "| time/ | |\n", + "| episodes | 1004 |\n", + "| fps | 324 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 9952 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.526 |\n", + "| time/ | |\n", + "| episodes | 1008 |\n", + "| fps | 324 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 9989 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.524 |\n", + "| time/ | |\n", + "| episodes | 1012 |\n", + "| fps | 323 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 10030 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.522 |\n", + "| time/ | |\n", + "| episodes | 1016 |\n", + "| fps | 323 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 10071 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.519 |\n", + "| time/ | |\n", + "| episodes | 1020 |\n", + "| fps | 323 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 10120 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.517 |\n", + "| time/ | |\n", + "| episodes | 1024 |\n", + "| fps | 323 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 10162 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.515 |\n", + "| time/ | |\n", + "| episodes | 1028 |\n", + "| fps | 323 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 10203 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.513 |\n", + "| time/ | |\n", + "| episodes | 1032 |\n", + "| fps | 323 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 10247 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.512 |\n", + "| time/ | |\n", + "| episodes | 1036 |\n", + "| fps | 323 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 10274 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.509 |\n", + "| time/ | |\n", + "| episodes | 1040 |\n", + "| fps | 323 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 10343 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.506 |\n", + "| time/ | |\n", + "| episodes | 1044 |\n", + "| fps | 323 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 10409 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.504 |\n", + "| time/ | |\n", + "| episodes | 1048 |\n", + "| fps | 323 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 10452 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.502 |\n", + "| time/ | |\n", + "| episodes | 1052 |\n", + "| fps | 323 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 10478 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.499 |\n", + "| time/ | |\n", + "| episodes | 1056 |\n", + "| fps | 323 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 10540 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.498 |\n", + "| time/ | |\n", + "| episodes | 1060 |\n", + "| fps | 323 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 10565 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.496 |\n", + "| time/ | |\n", + "| episodes | 1064 |\n", + "| fps | 324 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 10615 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.493 |\n", + "| time/ | |\n", + "| episodes | 1068 |\n", + "| fps | 324 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 10669 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.49 |\n", + "| time/ | |\n", + "| episodes | 1072 |\n", + "| fps | 324 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 10743 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.487 |\n", + "| time/ | |\n", + "| episodes | 1076 |\n", + "| fps | 324 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 10809 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.483 |\n", + "| time/ | |\n", + "| episodes | 1080 |\n", + "| fps | 324 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 10887 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.479 |\n", + "| time/ | |\n", + "| episodes | 1084 |\n", + "| fps | 324 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 10978 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.477 |\n", + "| time/ | |\n", + "| episodes | 1088 |\n", + "| fps | 324 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 11005 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.476 |\n", + "| time/ | |\n", + "| episodes | 1092 |\n", + "| fps | 324 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 11032 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.474 |\n", + "| time/ | |\n", + "| episodes | 1096 |\n", + "| fps | 324 |\n", + "| time_elapsed | 34 |\n", + "| total_timesteps | 11075 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.472 |\n", + "| time/ | |\n", + "| episodes | 1100 |\n", + "| fps | 324 |\n", + "| time_elapsed | 34 |\n", + "| total_timesteps | 11125 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.47 |\n", + "| time/ | |\n", + "| episodes | 1104 |\n", + "| fps | 324 |\n", + "| time_elapsed | 34 |\n", + "| total_timesteps | 11167 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.467 |\n", + "| time/ | |\n", + "| episodes | 1108 |\n", + "| fps | 324 |\n", + "| time_elapsed | 34 |\n", + "| total_timesteps | 11217 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.464 |\n", + "| time/ | |\n", + "| episodes | 1112 |\n", + "| fps | 325 |\n", + "| time_elapsed | 34 |\n", + "| total_timesteps | 11291 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.46 |\n", + "| time/ | |\n", + "| episodes | 1116 |\n", + "| fps | 325 |\n", + "| time_elapsed | 34 |\n", + "| total_timesteps | 11359 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.459 |\n", + "| time/ | |\n", + "| episodes | 1120 |\n", + "| fps | 325 |\n", + "| time_elapsed | 34 |\n", + "| total_timesteps | 11385 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.457 |\n", + "| time/ | |\n", + "| episodes | 1124 |\n", + "| fps | 325 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 11436 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.453 |\n", + "| time/ | |\n", + "| episodes | 1128 |\n", + "| fps | 326 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 11521 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.451 |\n", + "| time/ | |\n", + "| episodes | 1132 |\n", + "| fps | 326 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 11562 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.448 |\n", + "| time/ | |\n", + "| episodes | 1136 |\n", + "| fps | 326 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 11612 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.447 |\n", + "| time/ | |\n", + "| episodes | 1140 |\n", + "| fps | 326 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 11637 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.446 |\n", + "| time/ | |\n", + "| episodes | 1144 |\n", + "| fps | 326 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 11664 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.443 |\n", + "| time/ | |\n", + "| episodes | 1148 |\n", + "| fps | 326 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 11724 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.442 |\n", + "| time/ | |\n", + "| episodes | 1152 |\n", + "| fps | 326 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 11748 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.441 |\n", + "| time/ | |\n", + "| episodes | 1156 |\n", + "| fps | 326 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 11775 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.438 |\n", + "| time/ | |\n", + "| episodes | 1160 |\n", + "| fps | 327 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 11824 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.436 |\n", + "| time/ | |\n", + "| episodes | 1164 |\n", + "| fps | 327 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 11866 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.434 |\n", + "| time/ | |\n", + "| episodes | 1168 |\n", + "| fps | 327 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 11908 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.433 |\n", + "| time/ | |\n", + "| episodes | 1172 |\n", + "| fps | 327 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 11934 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.431 |\n", + "| time/ | |\n", + "| episodes | 1176 |\n", + "| fps | 327 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 11971 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.43 |\n", + "| time/ | |\n", + "| episodes | 1180 |\n", + "| fps | 327 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 12008 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.426 |\n", + "| time/ | |\n", + "| episodes | 1184 |\n", + "| fps | 327 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 12075 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.424 |\n", + "| time/ | |\n", + "| episodes | 1188 |\n", + "| fps | 327 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 12117 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.423 |\n", + "| time/ | |\n", + "| episodes | 1192 |\n", + "| fps | 328 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 12144 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.422 |\n", + "| time/ | |\n", + "| episodes | 1196 |\n", + "| fps | 327 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 12170 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.421 |\n", + "| time/ | |\n", + "| episodes | 1200 |\n", + "| fps | 327 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 12194 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.418 |\n", + "| time/ | |\n", + "| episodes | 1204 |\n", + "| fps | 328 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 12245 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.417 |\n", + "| time/ | |\n", + "| episodes | 1208 |\n", + "| fps | 327 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 12271 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.415 |\n", + "| time/ | |\n", + "| episodes | 1212 |\n", + "| fps | 328 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 12323 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.412 |\n", + "| time/ | |\n", + "| episodes | 1216 |\n", + "| fps | 328 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 12381 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.411 |\n", + "| time/ | |\n", + "| episodes | 1220 |\n", + "| fps | 328 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 12404 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.409 |\n", + "| time/ | |\n", + "| episodes | 1224 |\n", + "| fps | 328 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 12442 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.407 |\n", + "| time/ | |\n", + "| episodes | 1228 |\n", + "| fps | 328 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 12494 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.404 |\n", + "| time/ | |\n", + "| episodes | 1232 |\n", + "| fps | 329 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 12544 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.401 |\n", + "| time/ | |\n", + "| episodes | 1236 |\n", + "| fps | 329 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 12601 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.398 |\n", + "| time/ | |\n", + "| episodes | 1240 |\n", + "| fps | 329 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 12675 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.396 |\n", + "| time/ | |\n", + "| episodes | 1244 |\n", + "| fps | 330 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 12726 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.394 |\n", + "| time/ | |\n", + "| episodes | 1248 |\n", + "| fps | 330 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 12767 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.392 |\n", + "| time/ | |\n", + "| episodes | 1252 |\n", + "| fps | 329 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 12802 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.39 |\n", + "| time/ | |\n", + "| episodes | 1256 |\n", + "| fps | 330 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 12844 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.389 |\n", + "| time/ | |\n", + "| episodes | 1260 |\n", + "| fps | 329 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 12871 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.387 |\n", + "| time/ | |\n", + "| episodes | 1264 |\n", + "| fps | 330 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 12905 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.384 |\n", + "| time/ | |\n", + "| episodes | 1268 |\n", + "| fps | 330 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 12968 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.382 |\n", + "| time/ | |\n", + "| episodes | 1272 |\n", + "| fps | 330 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 13008 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.38 |\n", + "| time/ | |\n", + "| episodes | 1276 |\n", + "| fps | 330 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 13058 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.379 |\n", + "| time/ | |\n", + "| episodes | 1280 |\n", + "| fps | 330 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 13083 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.377 |\n", + "| time/ | |\n", + "| episodes | 1284 |\n", + "| fps | 330 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 13122 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.374 |\n", + "| time/ | |\n", + "| episodes | 1288 |\n", + "| fps | 330 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 13171 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.373 |\n", + "| time/ | |\n", + "| episodes | 1292 |\n", + "| fps | 330 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 13198 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.372 |\n", + "| time/ | |\n", + "| episodes | 1296 |\n", + "| fps | 330 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 13227 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.37 |\n", + "| time/ | |\n", + "| episodes | 1300 |\n", + "| fps | 330 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 13254 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.369 |\n", + "| time/ | |\n", + "| episodes | 1304 |\n", + "| fps | 330 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 13281 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.366 |\n", + "| time/ | |\n", + "| episodes | 1308 |\n", + "| fps | 330 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 13339 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.364 |\n", + "| time/ | |\n", + "| episodes | 1312 |\n", + "| fps | 330 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 13380 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.36 |\n", + "| time/ | |\n", + "| episodes | 1316 |\n", + "| fps | 331 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 13467 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.359 |\n", + "| time/ | |\n", + "| episodes | 1320 |\n", + "| fps | 331 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 13502 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.357 |\n", + "| time/ | |\n", + "| episodes | 1324 |\n", + "| fps | 331 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 13528 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.356 |\n", + "| time/ | |\n", + "| episodes | 1328 |\n", + "| fps | 331 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 13551 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.353 |\n", + "| time/ | |\n", + "| episodes | 1332 |\n", + "| fps | 331 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 13611 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.352 |\n", + "| time/ | |\n", + "| episodes | 1336 |\n", + "| fps | 331 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 13635 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.35 |\n", + "| time/ | |\n", + "| episodes | 1340 |\n", + "| fps | 331 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 13675 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.349 |\n", + "| time/ | |\n", + "| episodes | 1344 |\n", + "| fps | 331 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 13711 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.348 |\n", + "| time/ | |\n", + "| episodes | 1348 |\n", + "| fps | 331 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 13736 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.345 |\n", + "| time/ | |\n", + "| episodes | 1352 |\n", + "| fps | 331 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 13789 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.344 |\n", + "| time/ | |\n", + "| episodes | 1356 |\n", + "| fps | 331 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 13812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.342 |\n", + "| time/ | |\n", + "| episodes | 1360 |\n", + "| fps | 331 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 13862 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.34 |\n", + "| time/ | |\n", + "| episodes | 1364 |\n", + "| fps | 331 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 13902 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.337 |\n", + "| time/ | |\n", + "| episodes | 1368 |\n", + "| fps | 332 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 13959 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.336 |\n", + "| time/ | |\n", + "| episodes | 1372 |\n", + "| fps | 332 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 13983 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.334 |\n", + "| time/ | |\n", + "| episodes | 1376 |\n", + "| fps | 332 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 14025 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.332 |\n", + "| time/ | |\n", + "| episodes | 1380 |\n", + "| fps | 332 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 14065 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.331 |\n", + "| time/ | |\n", + "| episodes | 1384 |\n", + "| fps | 332 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 14088 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.328 |\n", + "| time/ | |\n", + "| episodes | 1388 |\n", + "| fps | 332 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 14156 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.325 |\n", + "| time/ | |\n", + "| episodes | 1392 |\n", + "| fps | 332 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 14206 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.324 |\n", + "| time/ | |\n", + "| episodes | 1396 |\n", + "| fps | 332 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 14240 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.321 |\n", + "| time/ | |\n", + "| episodes | 1400 |\n", + "| fps | 332 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 14292 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.319 |\n", + "| time/ | |\n", + "| episodes | 1404 |\n", + "| fps | 333 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 14340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.316 |\n", + "| time/ | |\n", + "| episodes | 1408 |\n", + "| fps | 333 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 14395 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.314 |\n", + "| time/ | |\n", + "| episodes | 1412 |\n", + "| fps | 333 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 14432 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.313 |\n", + "| time/ | |\n", + "| episodes | 1416 |\n", + "| fps | 333 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 14472 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.311 |\n", + "| time/ | |\n", + "| episodes | 1420 |\n", + "| fps | 333 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 14514 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.309 |\n", + "| time/ | |\n", + "| episodes | 1424 |\n", + "| fps | 333 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 14539 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.307 |\n", + "| time/ | |\n", + "| episodes | 1428 |\n", + "| fps | 333 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 14587 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.306 |\n", + "| time/ | |\n", + "| episodes | 1432 |\n", + "| fps | 333 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 14612 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.305 |\n", + "| time/ | |\n", + "| episodes | 1436 |\n", + "| fps | 333 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 14639 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.301 |\n", + "| time/ | |\n", + "| episodes | 1440 |\n", + "| fps | 333 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 14714 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.3 |\n", + "| time/ | |\n", + "| episodes | 1444 |\n", + "| fps | 333 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 14740 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.298 |\n", + "| time/ | |\n", + "| episodes | 1448 |\n", + "| fps | 333 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 14774 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.297 |\n", + "| time/ | |\n", + "| episodes | 1452 |\n", + "| fps | 333 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 14797 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.296 |\n", + "| time/ | |\n", + "| episodes | 1456 |\n", + "| fps | 333 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 14820 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.295 |\n", + "| time/ | |\n", + "| episodes | 1460 |\n", + "| fps | 333 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 14846 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.293 |\n", + "| time/ | |\n", + "| episodes | 1464 |\n", + "| fps | 333 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 14885 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.292 |\n", + "| time/ | |\n", + "| episodes | 1468 |\n", + "| fps | 333 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 14910 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.29 |\n", + "| time/ | |\n", + "| episodes | 1472 |\n", + "| fps | 333 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 14952 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.289 |\n", + "| time/ | |\n", + "| episodes | 1476 |\n", + "| fps | 333 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 14976 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.285 |\n", + "| time/ | |\n", + "| episodes | 1480 |\n", + "| fps | 333 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 15050 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.284 |\n", + "| time/ | |\n", + "| episodes | 1484 |\n", + "| fps | 333 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 15074 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.283 |\n", + "| time/ | |\n", + "| episodes | 1488 |\n", + "| fps | 333 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 15099 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.28 |\n", + "| time/ | |\n", + "| episodes | 1492 |\n", + "| fps | 333 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 15163 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.277 |\n", + "| time/ | |\n", + "| episodes | 1496 |\n", + "| fps | 333 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 15230 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.275 |\n", + "| time/ | |\n", + "| episodes | 1500 |\n", + "| fps | 333 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 15265 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.271 |\n", + "| time/ | |\n", + "| episodes | 1504 |\n", + "| fps | 334 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 15352 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.27 |\n", + "| time/ | |\n", + "| episodes | 1508 |\n", + "| fps | 333 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 15377 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.268 |\n", + "| time/ | |\n", + "| episodes | 1512 |\n", + "| fps | 333 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 15404 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.266 |\n", + "| time/ | |\n", + "| episodes | 1516 |\n", + "| fps | 333 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 15457 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.264 |\n", + "| time/ | |\n", + "| episodes | 1520 |\n", + "| fps | 333 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 15493 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.262 |\n", + "| time/ | |\n", + "| episodes | 1524 |\n", + "| fps | 334 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 15529 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.261 |\n", + "| time/ | |\n", + "| episodes | 1528 |\n", + "| fps | 333 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 15565 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.259 |\n", + "| time/ | |\n", + "| episodes | 1532 |\n", + "| fps | 334 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 15601 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.256 |\n", + "| time/ | |\n", + "| episodes | 1536 |\n", + "| fps | 334 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 15668 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.254 |\n", + "| time/ | |\n", + "| episodes | 1540 |\n", + "| fps | 334 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 15709 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.252 |\n", + "| time/ | |\n", + "| episodes | 1544 |\n", + "| fps | 334 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 15742 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.25 |\n", + "| time/ | |\n", + "| episodes | 1548 |\n", + "| fps | 334 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 15795 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.247 |\n", + "| time/ | |\n", + "| episodes | 1552 |\n", + "| fps | 334 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 15844 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.245 |\n", + "| time/ | |\n", + "| episodes | 1556 |\n", + "| fps | 334 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 15901 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.241 |\n", + "| time/ | |\n", + "| episodes | 1560 |\n", + "| fps | 334 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 15975 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.239 |\n", + "| time/ | |\n", + "| episodes | 1564 |\n", + "| fps | 334 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 16027 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.238 |\n", + "| time/ | |\n", + "| episodes | 1568 |\n", + "| fps | 334 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 16052 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.235 |\n", + "| time/ | |\n", + "| episodes | 1572 |\n", + "| fps | 334 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 16103 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.232 |\n", + "| time/ | |\n", + "| episodes | 1576 |\n", + "| fps | 334 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 16171 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.229 |\n", + "| time/ | |\n", + "| episodes | 1580 |\n", + "| fps | 335 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 16223 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.227 |\n", + "| time/ | |\n", + "| episodes | 1584 |\n", + "| fps | 335 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 16266 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.226 |\n", + "| time/ | |\n", + "| episodes | 1588 |\n", + "| fps | 334 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 16291 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.222 |\n", + "| time/ | |\n", + "| episodes | 1592 |\n", + "| fps | 335 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 16377 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.221 |\n", + "| time/ | |\n", + "| episodes | 1596 |\n", + "| fps | 335 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 16402 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.218 |\n", + "| time/ | |\n", + "| episodes | 1600 |\n", + "| fps | 335 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 16453 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.217 |\n", + "| time/ | |\n", + "| episodes | 1604 |\n", + "| fps | 335 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 16486 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.216 |\n", + "| time/ | |\n", + "| episodes | 1608 |\n", + "| fps | 335 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 16511 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.213 |\n", + "| time/ | |\n", + "| episodes | 1612 |\n", + "| fps | 335 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 16561 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.211 |\n", + "| time/ | |\n", + "| episodes | 1616 |\n", + "| fps | 335 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 16603 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.209 |\n", + "| time/ | |\n", + "| episodes | 1620 |\n", + "| fps | 335 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 16657 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.208 |\n", + "| time/ | |\n", + "| episodes | 1624 |\n", + "| fps | 335 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 16684 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.204 |\n", + "| time/ | |\n", + "| episodes | 1628 |\n", + "| fps | 335 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 16760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.202 |\n", + "| time/ | |\n", + "| episodes | 1632 |\n", + "| fps | 335 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 16801 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.199 |\n", + "| time/ | |\n", + "| episodes | 1636 |\n", + "| fps | 335 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 16853 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.197 |\n", + "| time/ | |\n", + "| episodes | 1640 |\n", + "| fps | 335 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 16904 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.196 |\n", + "| time/ | |\n", + "| episodes | 1644 |\n", + "| fps | 335 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 16929 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.193 |\n", + "| time/ | |\n", + "| episodes | 1648 |\n", + "| fps | 335 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 16981 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.191 |\n", + "| time/ | |\n", + "| episodes | 1652 |\n", + "| fps | 335 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 17022 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.19 |\n", + "| time/ | |\n", + "| episodes | 1656 |\n", + "| fps | 335 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 17045 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.188 |\n", + "| time/ | |\n", + "| episodes | 1660 |\n", + "| fps | 335 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 17099 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.187 |\n", + "| time/ | |\n", + "| episodes | 1664 |\n", + "| fps | 335 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 17124 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.185 |\n", + "| time/ | |\n", + "| episodes | 1668 |\n", + "| fps | 335 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 17162 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.183 |\n", + "| time/ | |\n", + "| episodes | 1672 |\n", + "| fps | 335 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 17204 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.181 |\n", + "| time/ | |\n", + "| episodes | 1676 |\n", + "| fps | 335 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 17237 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.179 |\n", + "| time/ | |\n", + "| episodes | 1680 |\n", + "| fps | 335 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 17287 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.178 |\n", + "| time/ | |\n", + "| episodes | 1684 |\n", + "| fps | 334 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 17314 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.176 |\n", + "| time/ | |\n", + "| episodes | 1688 |\n", + "| fps | 334 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 17340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.174 |\n", + "| time/ | |\n", + "| episodes | 1692 |\n", + "| fps | 334 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 17399 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.172 |\n", + "| time/ | |\n", + "| episodes | 1696 |\n", + "| fps | 334 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 17434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.17 |\n", + "| time/ | |\n", + "| episodes | 1700 |\n", + "| fps | 334 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 17473 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.169 |\n", + "| time/ | |\n", + "| episodes | 1704 |\n", + "| fps | 334 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 17499 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.168 |\n", + "| time/ | |\n", + "| episodes | 1708 |\n", + "| fps | 334 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 17525 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.166 |\n", + "| time/ | |\n", + "| episodes | 1712 |\n", + "| fps | 334 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 17549 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.165 |\n", + "| time/ | |\n", + "| episodes | 1716 |\n", + "| fps | 334 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 17584 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.163 |\n", + "| time/ | |\n", + "| episodes | 1720 |\n", + "| fps | 334 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 17631 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.161 |\n", + "| time/ | |\n", + "| episodes | 1724 |\n", + "| fps | 334 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 17671 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.159 |\n", + "| time/ | |\n", + "| episodes | 1728 |\n", + "| fps | 334 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 17696 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.158 |\n", + "| time/ | |\n", + "| episodes | 1732 |\n", + "| fps | 333 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 17720 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.156 |\n", + "| time/ | |\n", + "| episodes | 1736 |\n", + "| fps | 333 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 17775 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.155 |\n", + "| time/ | |\n", + "| episodes | 1740 |\n", + "| fps | 333 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 17797 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.15 |\n", + "| time/ | |\n", + "| episodes | 1744 |\n", + "| fps | 334 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 17897 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.147 |\n", + "| time/ | |\n", + "| episodes | 1748 |\n", + "| fps | 334 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 17949 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.145 |\n", + "| time/ | |\n", + "| episodes | 1752 |\n", + "| fps | 334 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 18002 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.144 |\n", + "| time/ | |\n", + "| episodes | 1756 |\n", + "| fps | 334 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 18028 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.142 |\n", + "| time/ | |\n", + "| episodes | 1760 |\n", + "| fps | 334 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 18069 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.14 |\n", + "| time/ | |\n", + "| episodes | 1764 |\n", + "| fps | 334 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 18097 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.138 |\n", + "| time/ | |\n", + "| episodes | 1768 |\n", + "| fps | 334 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 18138 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.136 |\n", + "| time/ | |\n", + "| episodes | 1772 |\n", + "| fps | 334 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 18194 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.133 |\n", + "| time/ | |\n", + "| episodes | 1776 |\n", + "| fps | 334 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 18249 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.131 |\n", + "| time/ | |\n", + "| episodes | 1780 |\n", + "| fps | 334 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 18301 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.128 |\n", + "| time/ | |\n", + "| episodes | 1784 |\n", + "| fps | 334 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 18353 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.126 |\n", + "| time/ | |\n", + "| episodes | 1788 |\n", + "| fps | 334 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 18409 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.124 |\n", + "| time/ | |\n", + "| episodes | 1792 |\n", + "| fps | 334 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 18436 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.123 |\n", + "| time/ | |\n", + "| episodes | 1796 |\n", + "| fps | 334 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 18463 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.121 |\n", + "| time/ | |\n", + "| episodes | 1800 |\n", + "| fps | 334 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 18515 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.118 |\n", + "| time/ | |\n", + "| episodes | 1804 |\n", + "| fps | 334 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 18576 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.116 |\n", + "| time/ | |\n", + "| episodes | 1808 |\n", + "| fps | 334 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 18601 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.115 |\n", + "| time/ | |\n", + "| episodes | 1812 |\n", + "| fps | 334 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 18627 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.113 |\n", + "| time/ | |\n", + "| episodes | 1816 |\n", + "| fps | 334 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 18679 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.112 |\n", + "| time/ | |\n", + "| episodes | 1820 |\n", + "| fps | 334 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 18705 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.11 |\n", + "| time/ | |\n", + "| episodes | 1824 |\n", + "| fps | 334 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 18733 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.109 |\n", + "| time/ | |\n", + "| episodes | 1828 |\n", + "| fps | 334 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 18760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.107 |\n", + "| time/ | |\n", + "| episodes | 1832 |\n", + "| fps | 334 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 18802 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.106 |\n", + "| time/ | |\n", + "| episodes | 1836 |\n", + "| fps | 334 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 18829 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.103 |\n", + "| time/ | |\n", + "| episodes | 1840 |\n", + "| fps | 334 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 18879 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.102 |\n", + "| time/ | |\n", + "| episodes | 1844 |\n", + "| fps | 334 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 18905 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.0993 |\n", + "| time/ | |\n", + "| episodes | 1848 |\n", + "| fps | 334 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 18963 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.0973 |\n", + "| time/ | |\n", + "| episodes | 1852 |\n", + "| fps | 334 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 19004 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.0947 |\n", + "| time/ | |\n", + "| episodes | 1856 |\n", + "| fps | 334 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 19060 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.0936 |\n", + "| time/ | |\n", + "| episodes | 1860 |\n", + "| fps | 334 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 19083 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.0919 |\n", + "| time/ | |\n", + "| episodes | 1864 |\n", + "| fps | 334 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 19118 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.0887 |\n", + "| time/ | |\n", + "| episodes | 1868 |\n", + "| fps | 334 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 19185 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.0875 |\n", + "| time/ | |\n", + "| episodes | 1872 |\n", + "| fps | 334 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 19211 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.0863 |\n", + "| time/ | |\n", + "| episodes | 1876 |\n", + "| fps | 334 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 19235 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.0851 |\n", + "| time/ | |\n", + "| episodes | 1880 |\n", + "| fps | 334 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 19260 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.0839 |\n", + "| time/ | |\n", + "| episodes | 1884 |\n", + "| fps | 334 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 19286 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.0814 |\n", + "| time/ | |\n", + "| episodes | 1888 |\n", + "| fps | 334 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 19339 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.0802 |\n", + "| time/ | |\n", + "| episodes | 1892 |\n", + "| fps | 334 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 19364 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.0789 |\n", + "| time/ | |\n", + "| episodes | 1896 |\n", + "| fps | 334 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 19392 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.0765 |\n", + "| time/ | |\n", + "| episodes | 1900 |\n", + "| fps | 334 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 19442 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.0748 |\n", + "| time/ | |\n", + "| episodes | 1904 |\n", + "| fps | 334 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 19478 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.0737 |\n", + "| time/ | |\n", + "| episodes | 1908 |\n", + "| fps | 334 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 19501 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.072 |\n", + "| time/ | |\n", + "| episodes | 1912 |\n", + "| fps | 334 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 19537 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.0708 |\n", + "| time/ | |\n", + "| episodes | 1916 |\n", + "| fps | 334 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 19563 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.0668 |\n", + "| time/ | |\n", + "| episodes | 1920 |\n", + "| fps | 334 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 19647 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.0649 |\n", + "| time/ | |\n", + "| episodes | 1924 |\n", + "| fps | 334 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 19686 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.0637 |\n", + "| time/ | |\n", + "| episodes | 1928 |\n", + "| fps | 334 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 19712 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.0624 |\n", + "| time/ | |\n", + "| episodes | 1932 |\n", + "| fps | 334 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 19740 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.0611 |\n", + "| time/ | |\n", + "| episodes | 1936 |\n", + "| fps | 334 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 19767 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.0597 |\n", + "| time/ | |\n", + "| episodes | 1940 |\n", + "| fps | 334 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 19795 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.0575 |\n", + "| time/ | |\n", + "| episodes | 1944 |\n", + "| fps | 334 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 19843 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.0554 |\n", + "| time/ | |\n", + "| episodes | 1948 |\n", + "| fps | 334 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 19886 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.0542 |\n", + "| time/ | |\n", + "| episodes | 1952 |\n", + "| fps | 334 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 19911 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.053 |\n", + "| time/ | |\n", + "| episodes | 1956 |\n", + "| fps | 334 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 19936 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.0518 |\n", + "| time/ | |\n", + "| episodes | 1960 |\n", + "| fps | 334 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 19962 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 1964 |\n", + "| fps | 334 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 20009 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 1968 |\n", + "| fps | 334 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 20061 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 1972 |\n", + "| fps | 334 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 20095 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 1976 |\n", + "| fps | 334 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 20120 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 1980 |\n", + "| fps | 334 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 20179 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 1984 |\n", + "| fps | 334 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 20205 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 1988 |\n", + "| fps | 334 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 20255 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 1992 |\n", + "| fps | 334 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 20280 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 1996 |\n", + "| fps | 334 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 20311 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2000 |\n", + "| fps | 334 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 20336 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2004 |\n", + "| fps | 334 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 20360 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2008 |\n", + "| fps | 334 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 20383 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2012 |\n", + "| fps | 334 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 20431 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2016 |\n", + "| fps | 334 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 20496 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2020 |\n", + "| fps | 334 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 20534 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2024 |\n", + "| fps | 334 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 20559 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2028 |\n", + "| fps | 334 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 20597 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2032 |\n", + "| fps | 334 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 20637 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2036 |\n", + "| fps | 334 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 20680 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2040 |\n", + "| fps | 334 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 20701 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2044 |\n", + "| fps | 334 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 20760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2048 |\n", + "| fps | 334 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 20786 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2052 |\n", + "| fps | 334 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 20812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2056 |\n", + "| fps | 334 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 20879 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2060 |\n", + "| fps | 334 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 20951 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2064 |\n", + "| fps | 334 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 20973 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2068 |\n", + "| fps | 334 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 21057 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2072 |\n", + "| fps | 334 |\n", + "| time_elapsed | 63 |\n", + "| total_timesteps | 21091 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2076 |\n", + "| fps | 334 |\n", + "| time_elapsed | 63 |\n", + "| total_timesteps | 21159 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2080 |\n", + "| fps | 334 |\n", + "| time_elapsed | 63 |\n", + "| total_timesteps | 21198 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2084 |\n", + "| fps | 334 |\n", + "| time_elapsed | 63 |\n", + "| total_timesteps | 21328 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2088 |\n", + "| fps | 334 |\n", + "| time_elapsed | 63 |\n", + "| total_timesteps | 21366 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2092 |\n", + "| fps | 334 |\n", + "| time_elapsed | 63 |\n", + "| total_timesteps | 21391 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2096 |\n", + "| fps | 335 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 21465 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2100 |\n", + "| fps | 335 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 21517 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2104 |\n", + "| fps | 335 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 21568 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2108 |\n", + "| fps | 335 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 21629 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2112 |\n", + "| fps | 335 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 21691 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2116 |\n", + "| fps | 335 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 21750 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2120 |\n", + "| fps | 335 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 21808 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2124 |\n", + "| fps | 335 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 21837 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2128 |\n", + "| fps | 335 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 21861 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2132 |\n", + "| fps | 335 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 21886 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2136 |\n", + "| fps | 335 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 21936 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2140 |\n", + "| fps | 335 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 21962 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2144 |\n", + "| fps | 335 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 22013 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2148 |\n", + "| fps | 335 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 22070 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2152 |\n", + "| fps | 335 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 22097 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2156 |\n", + "| fps | 335 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 22140 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2160 |\n", + "| fps | 335 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 22207 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2164 |\n", + "| fps | 335 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 22233 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2168 |\n", + "| fps | 335 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 22308 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2172 |\n", + "| fps | 335 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 22350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2176 |\n", + "| fps | 335 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 22411 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2180 |\n", + "| fps | 336 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 22453 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2184 |\n", + "| fps | 336 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 22503 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2188 |\n", + "| fps | 336 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 22557 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2192 |\n", + "| fps | 336 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 22581 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2196 |\n", + "| fps | 336 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 22618 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2200 |\n", + "| fps | 336 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 22661 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2204 |\n", + "| fps | 336 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 22698 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2208 |\n", + "| fps | 336 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 22737 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2212 |\n", + "| fps | 336 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 22795 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2216 |\n", + "| fps | 336 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 22837 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2220 |\n", + "| fps | 336 |\n", + "| time_elapsed | 68 |\n", + "| total_timesteps | 22918 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2224 |\n", + "| fps | 336 |\n", + "| time_elapsed | 68 |\n", + "| total_timesteps | 23000 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2228 |\n", + "| fps | 336 |\n", + "| time_elapsed | 68 |\n", + "| total_timesteps | 23026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2232 |\n", + "| fps | 336 |\n", + "| time_elapsed | 68 |\n", + "| total_timesteps | 23053 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2236 |\n", + "| fps | 336 |\n", + "| time_elapsed | 68 |\n", + "| total_timesteps | 23093 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2240 |\n", + "| fps | 336 |\n", + "| time_elapsed | 68 |\n", + "| total_timesteps | 23174 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2244 |\n", + "| fps | 336 |\n", + "| time_elapsed | 68 |\n", + "| total_timesteps | 23224 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2248 |\n", + "| fps | 336 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 23251 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2252 |\n", + "| fps | 336 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 23339 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2256 |\n", + "| fps | 336 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 23362 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2260 |\n", + "| fps | 336 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 23422 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2264 |\n", + "| fps | 337 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 23449 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2268 |\n", + "| fps | 336 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 23474 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2272 |\n", + "| fps | 336 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 23502 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2276 |\n", + "| fps | 336 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 23524 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2280 |\n", + "| fps | 336 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 23550 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2284 |\n", + "| fps | 336 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 23576 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2288 |\n", + "| fps | 336 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 23602 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2292 |\n", + "| fps | 336 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 23636 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2296 |\n", + "| fps | 336 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 23672 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2300 |\n", + "| fps | 336 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 23775 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2304 |\n", + "| fps | 337 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 23801 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2308 |\n", + "| fps | 337 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 23839 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2312 |\n", + "| fps | 337 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 23879 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2316 |\n", + "| fps | 336 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 23922 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2320 |\n", + "| fps | 336 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 23948 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2324 |\n", + "| fps | 336 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 23988 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2328 |\n", + "| fps | 336 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 24030 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2332 |\n", + "| fps | 337 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 24088 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2336 |\n", + "| fps | 337 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 24113 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2340 |\n", + "| fps | 336 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 24141 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2344 |\n", + "| fps | 336 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 24167 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2348 |\n", + "| fps | 336 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 24202 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2352 |\n", + "| fps | 336 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 24241 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2356 |\n", + "| fps | 336 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 24316 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2360 |\n", + "| fps | 336 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 24357 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2364 |\n", + "| fps | 337 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 24466 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2368 |\n", + "| fps | 337 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 24492 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2372 |\n", + "| fps | 337 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 24520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2376 |\n", + "| fps | 337 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 24545 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2380 |\n", + "| fps | 337 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 24597 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2384 |\n", + "| fps | 337 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 24623 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2388 |\n", + "| fps | 337 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 24648 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2392 |\n", + "| fps | 337 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 24720 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2396 |\n", + "| fps | 337 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 24746 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2400 |\n", + "| fps | 337 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 24781 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2404 |\n", + "| fps | 337 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 24830 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2408 |\n", + "| fps | 337 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 24854 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2412 |\n", + "| fps | 336 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 24907 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2416 |\n", + "| fps | 336 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 24943 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2420 |\n", + "| fps | 336 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 24974 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2424 |\n", + "| fps | 336 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 24999 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2428 |\n", + "| fps | 336 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 25090 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2432 |\n", + "| fps | 336 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 25117 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2436 |\n", + "| fps | 336 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 25143 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2440 |\n", + "| fps | 336 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 25168 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2444 |\n", + "| fps | 336 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 25195 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2448 |\n", + "| fps | 336 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 25262 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2452 |\n", + "| fps | 336 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 25323 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2456 |\n", + "| fps | 336 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 25357 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2460 |\n", + "| fps | 336 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 25399 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2464 |\n", + "| fps | 336 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 25479 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2468 |\n", + "| fps | 336 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 25507 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2472 |\n", + "| fps | 336 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 25531 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2476 |\n", + "| fps | 336 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 25558 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2480 |\n", + "| fps | 336 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 25614 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2484 |\n", + "| fps | 336 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 25650 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2488 |\n", + "| fps | 336 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 25676 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2492 |\n", + "| fps | 336 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 25725 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2496 |\n", + "| fps | 336 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 25771 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2500 |\n", + "| fps | 336 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 25839 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2504 |\n", + "| fps | 336 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 25881 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2508 |\n", + "| fps | 336 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 25909 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2512 |\n", + "| fps | 336 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 25935 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2516 |\n", + "| fps | 336 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 25962 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2520 |\n", + "| fps | 336 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 26019 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2524 |\n", + "| fps | 336 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 26054 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2528 |\n", + "| fps | 337 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 26129 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2532 |\n", + "| fps | 337 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 26215 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2536 |\n", + "| fps | 337 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 26258 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2540 |\n", + "| fps | 337 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 26285 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2544 |\n", + "| fps | 337 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 26325 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2548 |\n", + "| fps | 337 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 26350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2552 |\n", + "| fps | 337 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 26406 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2556 |\n", + "| fps | 337 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 26434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2560 |\n", + "| fps | 337 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 26460 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2564 |\n", + "| fps | 337 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 26499 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2568 |\n", + "| fps | 337 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 26535 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2572 |\n", + "| fps | 337 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 26562 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2576 |\n", + "| fps | 337 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 26588 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2580 |\n", + "| fps | 337 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 26615 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2584 |\n", + "| fps | 337 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 26642 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2588 |\n", + "| fps | 337 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 26733 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2592 |\n", + "| fps | 337 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 26769 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2596 |\n", + "| fps | 337 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 26796 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2600 |\n", + "| fps | 337 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 26855 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2604 |\n", + "| fps | 337 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 26903 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2608 |\n", + "| fps | 337 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 26951 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2612 |\n", + "| fps | 337 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 26990 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2616 |\n", + "| fps | 337 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 27015 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2620 |\n", + "| fps | 337 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 27076 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2624 |\n", + "| fps | 337 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 27135 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2628 |\n", + "| fps | 337 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 27176 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2632 |\n", + "| fps | 337 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 27202 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2636 |\n", + "| fps | 337 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 27250 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2640 |\n", + "| fps | 337 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 27276 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2644 |\n", + "| fps | 337 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 27302 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2648 |\n", + "| fps | 337 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 27363 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2652 |\n", + "| fps | 337 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 27385 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2656 |\n", + "| fps | 337 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 27422 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2660 |\n", + "| fps | 337 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 27481 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2664 |\n", + "| fps | 337 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 27520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2668 |\n", + "| fps | 337 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 27563 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2672 |\n", + "| fps | 337 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 27589 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2676 |\n", + "| fps | 337 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 27616 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2680 |\n", + "| fps | 337 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 27662 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2684 |\n", + "| fps | 337 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 27686 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2688 |\n", + "| fps | 337 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 27727 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2692 |\n", + "| fps | 337 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 27786 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2696 |\n", + "| fps | 337 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 27849 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2700 |\n", + "| fps | 337 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 27873 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2704 |\n", + "| fps | 338 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 27960 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2708 |\n", + "| fps | 338 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 27986 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2712 |\n", + "| fps | 338 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 28052 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2716 |\n", + "| fps | 338 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 28094 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2720 |\n", + "| fps | 338 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 28116 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2724 |\n", + "| fps | 338 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 28157 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2728 |\n", + "| fps | 338 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 28182 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2732 |\n", + "| fps | 338 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 28241 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2736 |\n", + "| fps | 338 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 28304 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2740 |\n", + "| fps | 338 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 28330 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2744 |\n", + "| fps | 338 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 28354 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2748 |\n", + "| fps | 338 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 28423 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2752 |\n", + "| fps | 338 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 28488 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2756 |\n", + "| fps | 338 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 28529 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2760 |\n", + "| fps | 338 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 28581 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2764 |\n", + "| fps | 338 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 28606 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2768 |\n", + "| fps | 338 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 28674 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2772 |\n", + "| fps | 338 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 28709 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2776 |\n", + "| fps | 338 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 28735 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2780 |\n", + "| fps | 338 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 28803 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2784 |\n", + "| fps | 338 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 28845 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2788 |\n", + "| fps | 338 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 28885 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2792 |\n", + "| fps | 338 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 28936 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2796 |\n", + "| fps | 338 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 28988 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2800 |\n", + "| fps | 338 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 29052 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2804 |\n", + "| fps | 338 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 29102 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2808 |\n", + "| fps | 338 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 29129 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2812 |\n", + "| fps | 338 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 29186 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2816 |\n", + "| fps | 339 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 29259 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2820 |\n", + "| fps | 339 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 29321 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2824 |\n", + "| fps | 339 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 29372 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2828 |\n", + "| fps | 339 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 29399 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2832 |\n", + "| fps | 339 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 29445 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2836 |\n", + "| fps | 339 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 29470 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2840 |\n", + "| fps | 339 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 29514 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2844 |\n", + "| fps | 339 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 29541 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2848 |\n", + "| fps | 339 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 29637 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2852 |\n", + "| fps | 339 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 29663 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2856 |\n", + "| fps | 339 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 29697 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2860 |\n", + "| fps | 339 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 29747 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2864 |\n", + "| fps | 339 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 29772 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2868 |\n", + "| fps | 339 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 29796 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2872 |\n", + "| fps | 339 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 29822 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2876 |\n", + "| fps | 339 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 29848 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2880 |\n", + "| fps | 339 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 29891 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2884 |\n", + "| fps | 339 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 29942 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2888 |\n", + "| fps | 339 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 30026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2892 |\n", + "| fps | 339 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 30066 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2896 |\n", + "| fps | 339 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 30108 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2900 |\n", + "| fps | 339 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 30155 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2904 |\n", + "| fps | 339 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 30197 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2908 |\n", + "| fps | 339 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 30252 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2912 |\n", + "| fps | 339 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 30303 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2916 |\n", + "| fps | 339 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 30347 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2920 |\n", + "| fps | 339 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 30388 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2924 |\n", + "| fps | 339 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 30416 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2928 |\n", + "| fps | 339 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 30460 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2932 |\n", + "| fps | 339 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 30500 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2936 |\n", + "| fps | 339 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 30525 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2940 |\n", + "| fps | 339 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 30597 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2944 |\n", + "| fps | 340 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 30673 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2948 |\n", + "| fps | 340 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 30730 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2952 |\n", + "| fps | 340 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 30794 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2956 |\n", + "| fps | 340 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 30829 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2960 |\n", + "| fps | 340 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 30853 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2964 |\n", + "| fps | 340 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 30904 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2968 |\n", + "| fps | 340 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 30929 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2972 |\n", + "| fps | 340 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 31002 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2976 |\n", + "| fps | 340 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 31068 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2980 |\n", + "| fps | 340 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 31093 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2984 |\n", + "| fps | 340 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 31118 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2988 |\n", + "| fps | 340 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 31166 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2992 |\n", + "| fps | 340 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 31190 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 2996 |\n", + "| fps | 340 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 31236 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3000 |\n", + "| fps | 340 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 31288 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3004 |\n", + "| fps | 340 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 31354 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3008 |\n", + "| fps | 340 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 31442 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3012 |\n", + "| fps | 340 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 31466 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3016 |\n", + "| fps | 340 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 31506 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3020 |\n", + "| fps | 340 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 31532 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3024 |\n", + "| fps | 340 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 31597 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3028 |\n", + "| fps | 340 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 31667 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3032 |\n", + "| fps | 340 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 31717 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3036 |\n", + "| fps | 340 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 31752 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3040 |\n", + "| fps | 340 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 31792 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3044 |\n", + "| fps | 340 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 31829 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3048 |\n", + "| fps | 340 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 31880 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3052 |\n", + "| fps | 340 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 31906 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3056 |\n", + "| fps | 340 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 31966 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3060 |\n", + "| fps | 340 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 31991 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3064 |\n", + "| fps | 340 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 32031 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3068 |\n", + "| fps | 340 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 32073 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3072 |\n", + "| fps | 340 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 32115 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3076 |\n", + "| fps | 340 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 32153 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3080 |\n", + "| fps | 340 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 32178 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3084 |\n", + "| fps | 340 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 32210 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3088 |\n", + "| fps | 341 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 32308 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3092 |\n", + "| fps | 341 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 32358 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3096 |\n", + "| fps | 341 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 32400 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3100 |\n", + "| fps | 341 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 32456 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3104 |\n", + "| fps | 341 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 32481 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3108 |\n", + "| fps | 341 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 32518 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3112 |\n", + "| fps | 341 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 32558 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3116 |\n", + "| fps | 341 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 32602 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3120 |\n", + "| fps | 341 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 32630 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3124 |\n", + "| fps | 341 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 32672 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3128 |\n", + "| fps | 341 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 32708 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3132 |\n", + "| fps | 341 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 32748 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3136 |\n", + "| fps | 341 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 32790 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3140 |\n", + "| fps | 341 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 32853 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3144 |\n", + "| fps | 341 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 32894 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3148 |\n", + "| fps | 341 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 32930 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3152 |\n", + "| fps | 341 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 32980 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3156 |\n", + "| fps | 341 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 33073 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3160 |\n", + "| fps | 341 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 33108 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3164 |\n", + "| fps | 341 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 33134 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3168 |\n", + "| fps | 341 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 33193 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3172 |\n", + "| fps | 341 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 33247 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3176 |\n", + "| fps | 341 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 33282 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3180 |\n", + "| fps | 341 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 33335 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3184 |\n", + "| fps | 341 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 33374 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3188 |\n", + "| fps | 341 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 33400 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3192 |\n", + "| fps | 341 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 33427 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3196 |\n", + "| fps | 341 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 33454 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3200 |\n", + "| fps | 341 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 33503 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3204 |\n", + "| fps | 341 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 33528 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3208 |\n", + "| fps | 341 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 33597 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3212 |\n", + "| fps | 341 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 33679 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3216 |\n", + "| fps | 341 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 33723 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3220 |\n", + "| fps | 341 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 33781 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3224 |\n", + "| fps | 341 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 33860 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3228 |\n", + "| fps | 341 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 33893 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3232 |\n", + "| fps | 341 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 33935 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3236 |\n", + "| fps | 341 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 33986 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3240 |\n", + "| fps | 341 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 34035 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3244 |\n", + "| fps | 341 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 34075 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3248 |\n", + "| fps | 341 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 34101 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3252 |\n", + "| fps | 341 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 34143 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3256 |\n", + "| fps | 341 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 34194 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3260 |\n", + "| fps | 341 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 34218 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3264 |\n", + "| fps | 341 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 34275 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3268 |\n", + "| fps | 341 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 34300 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3272 |\n", + "| fps | 341 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 34355 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3276 |\n", + "| fps | 341 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 34379 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3280 |\n", + "| fps | 341 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 34446 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3284 |\n", + "| fps | 341 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 34488 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3288 |\n", + "| fps | 341 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 34543 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3292 |\n", + "| fps | 341 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 34628 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3296 |\n", + "| fps | 341 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 34687 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3300 |\n", + "| fps | 341 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 34713 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3304 |\n", + "| fps | 341 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 34750 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3308 |\n", + "| fps | 341 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 34799 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3312 |\n", + "| fps | 341 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 34825 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3316 |\n", + "| fps | 341 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 34851 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3320 |\n", + "| fps | 341 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 34895 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3324 |\n", + "| fps | 341 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 34920 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3328 |\n", + "| fps | 341 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 34970 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3332 |\n", + "| fps | 341 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 35044 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3336 |\n", + "| fps | 340 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 35088 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3340 |\n", + "| fps | 341 |\n", + "| time_elapsed | 103 |\n", + "| total_timesteps | 35180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3344 |\n", + "| fps | 341 |\n", + "| time_elapsed | 103 |\n", + "| total_timesteps | 35242 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3348 |\n", + "| fps | 341 |\n", + "| time_elapsed | 103 |\n", + "| total_timesteps | 35268 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3352 |\n", + "| fps | 341 |\n", + "| time_elapsed | 103 |\n", + "| total_timesteps | 35290 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3356 |\n", + "| fps | 340 |\n", + "| time_elapsed | 103 |\n", + "| total_timesteps | 35355 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3360 |\n", + "| fps | 340 |\n", + "| time_elapsed | 103 |\n", + "| total_timesteps | 35396 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3364 |\n", + "| fps | 341 |\n", + "| time_elapsed | 103 |\n", + "| total_timesteps | 35439 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3368 |\n", + "| fps | 340 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 35482 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3372 |\n", + "| fps | 340 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 35549 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3376 |\n", + "| fps | 340 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 35591 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3380 |\n", + "| fps | 340 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 35614 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3384 |\n", + "| fps | 341 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 35680 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3388 |\n", + "| fps | 341 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 35738 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3392 |\n", + "| fps | 341 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 35773 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3396 |\n", + "| fps | 340 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 35801 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3400 |\n", + "| fps | 341 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 35843 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3404 |\n", + "| fps | 341 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 35894 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3408 |\n", + "| fps | 341 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 35918 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3412 |\n", + "| fps | 341 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 35961 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3416 |\n", + "| fps | 341 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 36001 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3420 |\n", + "| fps | 340 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 36022 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3424 |\n", + "| fps | 340 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 36048 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3428 |\n", + "| fps | 340 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 36084 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3432 |\n", + "| fps | 340 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 36119 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3436 |\n", + "| fps | 341 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 36192 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3440 |\n", + "| fps | 341 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 36242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3444 |\n", + "| fps | 341 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 36278 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3448 |\n", + "| fps | 341 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 36304 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3452 |\n", + "| fps | 341 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 36367 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3456 |\n", + "| fps | 341 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 36460 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3460 |\n", + "| fps | 341 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 36520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3464 |\n", + "| fps | 341 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 36593 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3468 |\n", + "| fps | 341 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 36635 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3472 |\n", + "| fps | 341 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 36708 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3476 |\n", + "| fps | 341 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 36736 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3480 |\n", + "| fps | 341 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 36777 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3484 |\n", + "| fps | 341 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 36832 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3488 |\n", + "| fps | 341 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 36858 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3492 |\n", + "| fps | 341 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 36899 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3496 |\n", + "| fps | 341 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 36924 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3500 |\n", + "| fps | 341 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 37017 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3504 |\n", + "| fps | 341 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 37106 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3508 |\n", + "| fps | 341 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 37164 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3512 |\n", + "| fps | 341 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 37232 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3516 |\n", + "| fps | 341 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 37258 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3520 |\n", + "| fps | 341 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 37284 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3524 |\n", + "| fps | 341 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 37308 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3528 |\n", + "| fps | 341 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 37334 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3532 |\n", + "| fps | 341 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 37387 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3536 |\n", + "| fps | 341 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 37449 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3540 |\n", + "| fps | 341 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 37519 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3544 |\n", + "| fps | 342 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 37594 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3548 |\n", + "| fps | 342 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 37650 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3552 |\n", + "| fps | 341 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 37675 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3556 |\n", + "| fps | 341 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 37735 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3560 |\n", + "| fps | 341 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 37759 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3564 |\n", + "| fps | 341 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 37785 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3568 |\n", + "| fps | 341 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 37808 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3572 |\n", + "| fps | 341 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 37859 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3576 |\n", + "| fps | 341 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 37912 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3580 |\n", + "| fps | 341 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 37954 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3584 |\n", + "| fps | 341 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 37980 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3588 |\n", + "| fps | 342 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 38056 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3592 |\n", + "| fps | 342 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 38128 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3596 |\n", + "| fps | 342 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 38178 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3600 |\n", + "| fps | 342 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 38213 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3604 |\n", + "| fps | 342 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 38265 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3608 |\n", + "| fps | 342 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 38301 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3612 |\n", + "| fps | 342 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 38328 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3616 |\n", + "| fps | 342 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 38361 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3620 |\n", + "| fps | 342 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 38405 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3624 |\n", + "| fps | 342 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 38442 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3628 |\n", + "| fps | 342 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 38508 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3632 |\n", + "| fps | 342 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 38559 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3636 |\n", + "| fps | 342 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 38594 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3640 |\n", + "| fps | 342 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 38637 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3644 |\n", + "| fps | 342 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 38661 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3648 |\n", + "| fps | 342 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 38688 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3652 |\n", + "| fps | 342 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 38745 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3656 |\n", + "| fps | 342 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 38786 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3660 |\n", + "| fps | 342 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 38823 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3664 |\n", + "| fps | 342 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 38850 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3668 |\n", + "| fps | 342 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 38875 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3672 |\n", + "| fps | 342 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 38917 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3676 |\n", + "| fps | 342 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 38959 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3680 |\n", + "| fps | 342 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 38993 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3684 |\n", + "| fps | 342 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 39017 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3688 |\n", + "| fps | 342 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 39043 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3692 |\n", + "| fps | 342 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 39067 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3696 |\n", + "| fps | 342 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 39117 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3700 |\n", + "| fps | 342 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 39157 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3704 |\n", + "| fps | 342 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 39215 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3708 |\n", + "| fps | 342 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 39242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3712 |\n", + "| fps | 342 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 39267 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3716 |\n", + "| fps | 342 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 39292 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3720 |\n", + "| fps | 342 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 39341 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3724 |\n", + "| fps | 342 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 39392 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3728 |\n", + "| fps | 342 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 39417 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3732 |\n", + "| fps | 342 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 39442 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3736 |\n", + "| fps | 342 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 39502 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3740 |\n", + "| fps | 342 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 39542 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3744 |\n", + "| fps | 342 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 39591 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3748 |\n", + "| fps | 342 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 39650 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3752 |\n", + "| fps | 342 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 39724 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3756 |\n", + "| fps | 342 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 39764 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3760 |\n", + "| fps | 342 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 39811 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3764 |\n", + "| fps | 342 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 39837 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3768 |\n", + "| fps | 342 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 39908 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3772 |\n", + "| fps | 342 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 39935 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3776 |\n", + "| fps | 342 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 39960 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3780 |\n", + "| fps | 342 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 39984 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3784 |\n", + "| fps | 342 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 40008 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3788 |\n", + "| fps | 342 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 40032 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3792 |\n", + "| fps | 342 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 40083 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3796 |\n", + "| fps | 342 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 40109 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3800 |\n", + "| fps | 342 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 40149 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3804 |\n", + "| fps | 342 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 40174 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3808 |\n", + "| fps | 342 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 40199 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3812 |\n", + "| fps | 342 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 40226 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3816 |\n", + "| fps | 342 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 40251 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3820 |\n", + "| fps | 342 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 40279 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3824 |\n", + "| fps | 342 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 40319 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3828 |\n", + "| fps | 342 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 40342 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3832 |\n", + "| fps | 342 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 40419 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3836 |\n", + "| fps | 342 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 40459 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3840 |\n", + "| fps | 342 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 40486 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3844 |\n", + "| fps | 342 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 40513 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3848 |\n", + "| fps | 342 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 40578 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3852 |\n", + "| fps | 342 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 40605 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3856 |\n", + "| fps | 342 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 40647 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3860 |\n", + "| fps | 342 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 40673 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3864 |\n", + "| fps | 342 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 40710 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3868 |\n", + "| fps | 342 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 40746 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3872 |\n", + "| fps | 342 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 40789 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3876 |\n", + "| fps | 342 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 40812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3880 |\n", + "| fps | 342 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 40848 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3884 |\n", + "| fps | 342 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 40873 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3888 |\n", + "| fps | 342 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 40927 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3892 |\n", + "| fps | 342 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 40952 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3896 |\n", + "| fps | 342 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 41026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3900 |\n", + "| fps | 342 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 41053 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3904 |\n", + "| fps | 342 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 41080 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3908 |\n", + "| fps | 342 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 41107 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3912 |\n", + "| fps | 342 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 41163 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3916 |\n", + "| fps | 342 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 41191 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3920 |\n", + "| fps | 342 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 41229 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3924 |\n", + "| fps | 342 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 41257 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3928 |\n", + "| fps | 342 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 41344 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3932 |\n", + "| fps | 342 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 41368 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3936 |\n", + "| fps | 342 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 41410 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3940 |\n", + "| fps | 342 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 41512 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3944 |\n", + "| fps | 342 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 41569 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3948 |\n", + "| fps | 342 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 41635 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3952 |\n", + "| fps | 342 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 41674 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3956 |\n", + "| fps | 342 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 41732 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3960 |\n", + "| fps | 342 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 41774 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3964 |\n", + "| fps | 342 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 41826 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3968 |\n", + "| fps | 342 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 41850 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3972 |\n", + "| fps | 342 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 41891 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3976 |\n", + "| fps | 342 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 41933 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3980 |\n", + "| fps | 342 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 41965 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3984 |\n", + "| fps | 342 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 42020 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3988 |\n", + "| fps | 342 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 42061 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3992 |\n", + "| fps | 342 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 42100 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 3996 |\n", + "| fps | 342 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 42159 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4000 |\n", + "| fps | 342 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 42181 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4004 |\n", + "| fps | 342 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 42237 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4008 |\n", + "| fps | 342 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 42289 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4012 |\n", + "| fps | 342 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 42312 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4016 |\n", + "| fps | 342 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 42339 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4020 |\n", + "| fps | 342 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 42395 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4024 |\n", + "| fps | 342 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 42436 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4028 |\n", + "| fps | 342 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 42463 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4032 |\n", + "| fps | 342 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 42505 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4036 |\n", + "| fps | 342 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 42546 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4040 |\n", + "| fps | 343 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 42616 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4044 |\n", + "| fps | 343 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 42705 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4048 |\n", + "| fps | 343 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 42744 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4052 |\n", + "| fps | 343 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 42768 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4056 |\n", + "| fps | 343 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 42808 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4060 |\n", + "| fps | 343 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 42842 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4064 |\n", + "| fps | 343 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 42866 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4068 |\n", + "| fps | 343 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 42906 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4072 |\n", + "| fps | 343 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 42940 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4076 |\n", + "| fps | 343 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 42984 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4080 |\n", + "| fps | 343 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 43023 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4084 |\n", + "| fps | 343 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 43046 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4088 |\n", + "| fps | 343 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 43096 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4092 |\n", + "| fps | 343 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 43191 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4096 |\n", + "| fps | 343 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 43297 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4100 |\n", + "| fps | 343 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 43322 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4104 |\n", + "| fps | 343 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 43378 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4108 |\n", + "| fps | 343 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 43457 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4112 |\n", + "| fps | 343 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 43549 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4116 |\n", + "| fps | 343 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 43588 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4120 |\n", + "| fps | 343 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 43614 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4124 |\n", + "| fps | 343 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 43641 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4128 |\n", + "| fps | 343 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 43691 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4132 |\n", + "| fps | 343 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 43759 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4136 |\n", + "| fps | 343 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 43784 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4140 |\n", + "| fps | 343 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 43841 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4144 |\n", + "| fps | 343 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 43900 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4148 |\n", + "| fps | 343 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 43925 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4152 |\n", + "| fps | 343 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 43951 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4156 |\n", + "| fps | 343 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 44003 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4160 |\n", + "| fps | 343 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 44032 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4164 |\n", + "| fps | 343 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 44071 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4168 |\n", + "| fps | 343 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 44096 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4172 |\n", + "| fps | 343 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 44134 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4176 |\n", + "| fps | 343 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 44159 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4180 |\n", + "| fps | 343 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 44211 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4184 |\n", + "| fps | 343 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 44248 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4188 |\n", + "| fps | 344 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 44306 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4192 |\n", + "| fps | 344 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 44332 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4196 |\n", + "| fps | 344 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 44370 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4200 |\n", + "| fps | 344 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 44421 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4204 |\n", + "| fps | 344 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 44464 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4208 |\n", + "| fps | 344 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 44490 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4212 |\n", + "| fps | 343 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 44518 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4216 |\n", + "| fps | 344 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 44585 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4220 |\n", + "| fps | 343 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 44619 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4224 |\n", + "| fps | 343 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 44645 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4228 |\n", + "| fps | 343 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 44681 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4232 |\n", + "| fps | 343 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 44738 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4236 |\n", + "| fps | 344 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 44806 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4240 |\n", + "| fps | 343 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 44831 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4244 |\n", + "| fps | 343 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 44856 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4248 |\n", + "| fps | 343 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 44881 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4252 |\n", + "| fps | 343 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 44932 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4256 |\n", + "| fps | 343 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 44991 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4260 |\n", + "| fps | 343 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 45026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4264 |\n", + "| fps | 343 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 45061 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4268 |\n", + "| fps | 343 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 45087 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4272 |\n", + "| fps | 343 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 45152 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4276 |\n", + "| fps | 343 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 45189 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4280 |\n", + "| fps | 343 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 45216 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4284 |\n", + "| fps | 343 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 45241 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4288 |\n", + "| fps | 343 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 45282 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4292 |\n", + "| fps | 343 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 45317 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4296 |\n", + "| fps | 343 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 45373 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4300 |\n", + "| fps | 343 |\n", + "| time_elapsed | 132 |\n", + "| total_timesteps | 45399 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4304 |\n", + "| fps | 343 |\n", + "| time_elapsed | 132 |\n", + "| total_timesteps | 45425 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4308 |\n", + "| fps | 343 |\n", + "| time_elapsed | 132 |\n", + "| total_timesteps | 45466 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4312 |\n", + "| fps | 343 |\n", + "| time_elapsed | 132 |\n", + "| total_timesteps | 45507 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4316 |\n", + "| fps | 343 |\n", + "| time_elapsed | 132 |\n", + "| total_timesteps | 45534 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4320 |\n", + "| fps | 343 |\n", + "| time_elapsed | 132 |\n", + "| total_timesteps | 45560 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4324 |\n", + "| fps | 344 |\n", + "| time_elapsed | 132 |\n", + "| total_timesteps | 45651 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4328 |\n", + "| fps | 344 |\n", + "| time_elapsed | 132 |\n", + "| total_timesteps | 45708 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4332 |\n", + "| fps | 344 |\n", + "| time_elapsed | 132 |\n", + "| total_timesteps | 45734 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4336 |\n", + "| fps | 344 |\n", + "| time_elapsed | 133 |\n", + "| total_timesteps | 45809 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4340 |\n", + "| fps | 344 |\n", + "| time_elapsed | 133 |\n", + "| total_timesteps | 45833 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4344 |\n", + "| fps | 344 |\n", + "| time_elapsed | 133 |\n", + "| total_timesteps | 45868 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4348 |\n", + "| fps | 344 |\n", + "| time_elapsed | 133 |\n", + "| total_timesteps | 45903 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4352 |\n", + "| fps | 344 |\n", + "| time_elapsed | 133 |\n", + "| total_timesteps | 45963 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4356 |\n", + "| fps | 344 |\n", + "| time_elapsed | 133 |\n", + "| total_timesteps | 46031 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4360 |\n", + "| fps | 344 |\n", + "| time_elapsed | 133 |\n", + "| total_timesteps | 46071 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4364 |\n", + "| fps | 344 |\n", + "| time_elapsed | 133 |\n", + "| total_timesteps | 46112 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4368 |\n", + "| fps | 344 |\n", + "| time_elapsed | 134 |\n", + "| total_timesteps | 46163 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4372 |\n", + "| fps | 344 |\n", + "| time_elapsed | 134 |\n", + "| total_timesteps | 46197 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4376 |\n", + "| fps | 344 |\n", + "| time_elapsed | 134 |\n", + "| total_timesteps | 46238 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4380 |\n", + "| fps | 344 |\n", + "| time_elapsed | 134 |\n", + "| total_timesteps | 46261 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4384 |\n", + "| fps | 344 |\n", + "| time_elapsed | 134 |\n", + "| total_timesteps | 46302 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4388 |\n", + "| fps | 344 |\n", + "| time_elapsed | 134 |\n", + "| total_timesteps | 46343 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4392 |\n", + "| fps | 344 |\n", + "| time_elapsed | 134 |\n", + "| total_timesteps | 46408 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4396 |\n", + "| fps | 344 |\n", + "| time_elapsed | 134 |\n", + "| total_timesteps | 46436 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4400 |\n", + "| fps | 344 |\n", + "| time_elapsed | 134 |\n", + "| total_timesteps | 46475 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4404 |\n", + "| fps | 344 |\n", + "| time_elapsed | 135 |\n", + "| total_timesteps | 46515 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4408 |\n", + "| fps | 344 |\n", + "| time_elapsed | 135 |\n", + "| total_timesteps | 46540 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4412 |\n", + "| fps | 344 |\n", + "| time_elapsed | 135 |\n", + "| total_timesteps | 46575 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4416 |\n", + "| fps | 344 |\n", + "| time_elapsed | 135 |\n", + "| total_timesteps | 46624 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4420 |\n", + "| fps | 344 |\n", + "| time_elapsed | 135 |\n", + "| total_timesteps | 46680 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4424 |\n", + "| fps | 344 |\n", + "| time_elapsed | 135 |\n", + "| total_timesteps | 46707 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4428 |\n", + "| fps | 344 |\n", + "| time_elapsed | 135 |\n", + "| total_timesteps | 46748 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4432 |\n", + "| fps | 344 |\n", + "| time_elapsed | 135 |\n", + "| total_timesteps | 46775 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4436 |\n", + "| fps | 344 |\n", + "| time_elapsed | 135 |\n", + "| total_timesteps | 46801 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4440 |\n", + "| fps | 344 |\n", + "| time_elapsed | 136 |\n", + "| total_timesteps | 46843 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4444 |\n", + "| fps | 344 |\n", + "| time_elapsed | 136 |\n", + "| total_timesteps | 46882 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4448 |\n", + "| fps | 344 |\n", + "| time_elapsed | 136 |\n", + "| total_timesteps | 46910 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4452 |\n", + "| fps | 344 |\n", + "| time_elapsed | 136 |\n", + "| total_timesteps | 46961 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4456 |\n", + "| fps | 344 |\n", + "| time_elapsed | 136 |\n", + "| total_timesteps | 47034 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4460 |\n", + "| fps | 344 |\n", + "| time_elapsed | 136 |\n", + "| total_timesteps | 47122 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4464 |\n", + "| fps | 344 |\n", + "| time_elapsed | 136 |\n", + "| total_timesteps | 47165 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4468 |\n", + "| fps | 344 |\n", + "| time_elapsed | 137 |\n", + "| total_timesteps | 47222 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4472 |\n", + "| fps | 344 |\n", + "| time_elapsed | 137 |\n", + "| total_timesteps | 47246 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4476 |\n", + "| fps | 344 |\n", + "| time_elapsed | 137 |\n", + "| total_timesteps | 47290 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4480 |\n", + "| fps | 344 |\n", + "| time_elapsed | 137 |\n", + "| total_timesteps | 47316 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4484 |\n", + "| fps | 344 |\n", + "| time_elapsed | 137 |\n", + "| total_timesteps | 47340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4488 |\n", + "| fps | 344 |\n", + "| time_elapsed | 137 |\n", + "| total_timesteps | 47367 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4492 |\n", + "| fps | 344 |\n", + "| time_elapsed | 137 |\n", + "| total_timesteps | 47400 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4496 |\n", + "| fps | 344 |\n", + "| time_elapsed | 137 |\n", + "| total_timesteps | 47442 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4500 |\n", + "| fps | 344 |\n", + "| time_elapsed | 137 |\n", + "| total_timesteps | 47469 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4504 |\n", + "| fps | 344 |\n", + "| time_elapsed | 138 |\n", + "| total_timesteps | 47521 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4508 |\n", + "| fps | 344 |\n", + "| time_elapsed | 138 |\n", + "| total_timesteps | 47544 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4512 |\n", + "| fps | 344 |\n", + "| time_elapsed | 138 |\n", + "| total_timesteps | 47587 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4516 |\n", + "| fps | 344 |\n", + "| time_elapsed | 138 |\n", + "| total_timesteps | 47651 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4520 |\n", + "| fps | 344 |\n", + "| time_elapsed | 138 |\n", + "| total_timesteps | 47702 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4524 |\n", + "| fps | 344 |\n", + "| time_elapsed | 138 |\n", + "| total_timesteps | 47735 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4528 |\n", + "| fps | 344 |\n", + "| time_elapsed | 138 |\n", + "| total_timesteps | 47770 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4532 |\n", + "| fps | 344 |\n", + "| time_elapsed | 138 |\n", + "| total_timesteps | 47808 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4536 |\n", + "| fps | 344 |\n", + "| time_elapsed | 139 |\n", + "| total_timesteps | 47864 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4540 |\n", + "| fps | 344 |\n", + "| time_elapsed | 139 |\n", + "| total_timesteps | 47889 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4544 |\n", + "| fps | 344 |\n", + "| time_elapsed | 139 |\n", + "| total_timesteps | 47916 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4548 |\n", + "| fps | 344 |\n", + "| time_elapsed | 139 |\n", + "| total_timesteps | 47958 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4552 |\n", + "| fps | 344 |\n", + "| time_elapsed | 139 |\n", + "| total_timesteps | 47999 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4556 |\n", + "| fps | 344 |\n", + "| time_elapsed | 139 |\n", + "| total_timesteps | 48025 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4560 |\n", + "| fps | 344 |\n", + "| time_elapsed | 139 |\n", + "| total_timesteps | 48077 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4564 |\n", + "| fps | 344 |\n", + "| time_elapsed | 139 |\n", + "| total_timesteps | 48121 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4568 |\n", + "| fps | 344 |\n", + "| time_elapsed | 139 |\n", + "| total_timesteps | 48180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4572 |\n", + "| fps | 344 |\n", + "| time_elapsed | 140 |\n", + "| total_timesteps | 48232 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4576 |\n", + "| fps | 344 |\n", + "| time_elapsed | 140 |\n", + "| total_timesteps | 48273 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4580 |\n", + "| fps | 344 |\n", + "| time_elapsed | 140 |\n", + "| total_timesteps | 48296 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4584 |\n", + "| fps | 344 |\n", + "| time_elapsed | 140 |\n", + "| total_timesteps | 48323 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4588 |\n", + "| fps | 344 |\n", + "| time_elapsed | 140 |\n", + "| total_timesteps | 48371 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4592 |\n", + "| fps | 344 |\n", + "| time_elapsed | 140 |\n", + "| total_timesteps | 48446 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4596 |\n", + "| fps | 344 |\n", + "| time_elapsed | 140 |\n", + "| total_timesteps | 48499 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4600 |\n", + "| fps | 344 |\n", + "| time_elapsed | 140 |\n", + "| total_timesteps | 48525 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4604 |\n", + "| fps | 344 |\n", + "| time_elapsed | 140 |\n", + "| total_timesteps | 48549 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4608 |\n", + "| fps | 344 |\n", + "| time_elapsed | 141 |\n", + "| total_timesteps | 48583 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4612 |\n", + "| fps | 344 |\n", + "| time_elapsed | 141 |\n", + "| total_timesteps | 48632 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4616 |\n", + "| fps | 344 |\n", + "| time_elapsed | 141 |\n", + "| total_timesteps | 48659 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4620 |\n", + "| fps | 344 |\n", + "| time_elapsed | 141 |\n", + "| total_timesteps | 48683 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4624 |\n", + "| fps | 344 |\n", + "| time_elapsed | 141 |\n", + "| total_timesteps | 48711 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4628 |\n", + "| fps | 344 |\n", + "| time_elapsed | 141 |\n", + "| total_timesteps | 48790 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4632 |\n", + "| fps | 344 |\n", + "| time_elapsed | 141 |\n", + "| total_timesteps | 48830 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4636 |\n", + "| fps | 344 |\n", + "| time_elapsed | 141 |\n", + "| total_timesteps | 48873 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4640 |\n", + "| fps | 344 |\n", + "| time_elapsed | 142 |\n", + "| total_timesteps | 48914 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4644 |\n", + "| fps | 344 |\n", + "| time_elapsed | 142 |\n", + "| total_timesteps | 48971 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4648 |\n", + "| fps | 344 |\n", + "| time_elapsed | 142 |\n", + "| total_timesteps | 49027 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4652 |\n", + "| fps | 344 |\n", + "| time_elapsed | 142 |\n", + "| total_timesteps | 49049 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4656 |\n", + "| fps | 344 |\n", + "| time_elapsed | 142 |\n", + "| total_timesteps | 49125 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4660 |\n", + "| fps | 344 |\n", + "| time_elapsed | 142 |\n", + "| total_timesteps | 49168 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4664 |\n", + "| fps | 344 |\n", + "| time_elapsed | 143 |\n", + "| total_timesteps | 49209 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4668 |\n", + "| fps | 344 |\n", + "| time_elapsed | 143 |\n", + "| total_timesteps | 49259 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4672 |\n", + "| fps | 344 |\n", + "| time_elapsed | 143 |\n", + "| total_timesteps | 49298 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4676 |\n", + "| fps | 344 |\n", + "| time_elapsed | 143 |\n", + "| total_timesteps | 49324 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4680 |\n", + "| fps | 343 |\n", + "| time_elapsed | 143 |\n", + "| total_timesteps | 49365 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4684 |\n", + "| fps | 343 |\n", + "| time_elapsed | 143 |\n", + "| total_timesteps | 49390 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4688 |\n", + "| fps | 343 |\n", + "| time_elapsed | 143 |\n", + "| total_timesteps | 49434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4692 |\n", + "| fps | 343 |\n", + "| time_elapsed | 143 |\n", + "| total_timesteps | 49473 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4696 |\n", + "| fps | 343 |\n", + "| time_elapsed | 143 |\n", + "| total_timesteps | 49515 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4700 |\n", + "| fps | 343 |\n", + "| time_elapsed | 144 |\n", + "| total_timesteps | 49565 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4704 |\n", + "| fps | 343 |\n", + "| time_elapsed | 144 |\n", + "| total_timesteps | 49589 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4708 |\n", + "| fps | 343 |\n", + "| time_elapsed | 144 |\n", + "| total_timesteps | 49632 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4712 |\n", + "| fps | 343 |\n", + "| time_elapsed | 144 |\n", + "| total_timesteps | 49682 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4716 |\n", + "| fps | 343 |\n", + "| time_elapsed | 144 |\n", + "| total_timesteps | 49727 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4720 |\n", + "| fps | 343 |\n", + "| time_elapsed | 144 |\n", + "| total_timesteps | 49786 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4724 |\n", + "| fps | 343 |\n", + "| time_elapsed | 144 |\n", + "| total_timesteps | 49812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4728 |\n", + "| fps | 343 |\n", + "| time_elapsed | 144 |\n", + "| total_timesteps | 49839 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4732 |\n", + "| fps | 343 |\n", + "| time_elapsed | 145 |\n", + "| total_timesteps | 49874 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4736 |\n", + "| fps | 343 |\n", + "| time_elapsed | 145 |\n", + "| total_timesteps | 49901 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4740 |\n", + "| fps | 343 |\n", + "| time_elapsed | 145 |\n", + "| total_timesteps | 49925 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4744 |\n", + "| fps | 343 |\n", + "| time_elapsed | 145 |\n", + "| total_timesteps | 49948 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4748 |\n", + "| fps | 343 |\n", + "| time_elapsed | 145 |\n", + "| total_timesteps | 49997 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4752 |\n", + "| fps | 342 |\n", + "| time_elapsed | 146 |\n", + "| total_timesteps | 50036 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0288 |\n", + "| n_updates | 8 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4756 |\n", + "| fps | 340 |\n", + "| time_elapsed | 147 |\n", + "| total_timesteps | 50087 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000307 |\n", + "| n_updates | 21 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4760 |\n", + "| fps | 339 |\n", + "| time_elapsed | 147 |\n", + "| total_timesteps | 50136 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0146 |\n", + "| n_updates | 33 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4764 |\n", + "| fps | 337 |\n", + "| time_elapsed | 148 |\n", + "| total_timesteps | 50184 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0157 |\n", + "| n_updates | 45 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4768 |\n", + "| fps | 334 |\n", + "| time_elapsed | 150 |\n", + "| total_timesteps | 50283 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0148 |\n", + "| n_updates | 70 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4772 |\n", + "| fps | 332 |\n", + "| time_elapsed | 151 |\n", + "| total_timesteps | 50350 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0154 |\n", + "| n_updates | 87 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4776 |\n", + "| fps | 330 |\n", + "| time_elapsed | 152 |\n", + "| total_timesteps | 50401 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000221 |\n", + "| n_updates | 100 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4780 |\n", + "| fps | 328 |\n", + "| time_elapsed | 153 |\n", + "| total_timesteps | 50447 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0145 |\n", + "| n_updates | 111 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4784 |\n", + "| fps | 327 |\n", + "| time_elapsed | 154 |\n", + "| total_timesteps | 50481 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000163 |\n", + "| n_updates | 120 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4788 |\n", + "| fps | 325 |\n", + "| time_elapsed | 155 |\n", + "| total_timesteps | 50549 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0286 |\n", + "| n_updates | 137 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4792 |\n", + "| fps | 324 |\n", + "| time_elapsed | 156 |\n", + "| total_timesteps | 50602 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000945 |\n", + "| n_updates | 150 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4796 |\n", + "| fps | 322 |\n", + "| time_elapsed | 157 |\n", + "| total_timesteps | 50661 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0455 |\n", + "| n_updates | 165 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4800 |\n", + "| fps | 321 |\n", + "| time_elapsed | 157 |\n", + "| total_timesteps | 50688 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.015 |\n", + "| n_updates | 171 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4804 |\n", + "| fps | 320 |\n", + "| time_elapsed | 158 |\n", + "| total_timesteps | 50722 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0146 |\n", + "| n_updates | 180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4808 |\n", + "| fps | 319 |\n", + "| time_elapsed | 158 |\n", + "| total_timesteps | 50757 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0168 |\n", + "| n_updates | 189 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4812 |\n", + "| fps | 318 |\n", + "| time_elapsed | 159 |\n", + "| total_timesteps | 50794 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00109 |\n", + "| n_updates | 198 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4816 |\n", + "| fps | 316 |\n", + "| time_elapsed | 160 |\n", + "| total_timesteps | 50837 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000384 |\n", + "| n_updates | 209 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4820 |\n", + "| fps | 315 |\n", + "| time_elapsed | 161 |\n", + "| total_timesteps | 50883 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0432 |\n", + "| n_updates | 220 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4824 |\n", + "| fps | 314 |\n", + "| time_elapsed | 162 |\n", + "| total_timesteps | 50933 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00154 |\n", + "| n_updates | 233 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4828 |\n", + "| fps | 312 |\n", + "| time_elapsed | 162 |\n", + "| total_timesteps | 50982 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000391 |\n", + "| n_updates | 245 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4832 |\n", + "| fps | 312 |\n", + "| time_elapsed | 163 |\n", + "| total_timesteps | 51009 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000302 |\n", + "| n_updates | 252 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4836 |\n", + "| fps | 310 |\n", + "| time_elapsed | 164 |\n", + "| total_timesteps | 51053 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000729 |\n", + "| n_updates | 263 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4840 |\n", + "| fps | 310 |\n", + "| time_elapsed | 164 |\n", + "| total_timesteps | 51079 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0287 |\n", + "| n_updates | 269 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4844 |\n", + "| fps | 309 |\n", + "| time_elapsed | 165 |\n", + "| total_timesteps | 51101 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000506 |\n", + "| n_updates | 275 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4848 |\n", + "| fps | 307 |\n", + "| time_elapsed | 166 |\n", + "| total_timesteps | 51174 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0143 |\n", + "| n_updates | 293 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4852 |\n", + "| fps | 306 |\n", + "| time_elapsed | 167 |\n", + "| total_timesteps | 51221 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0144 |\n", + "| n_updates | 305 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4856 |\n", + "| fps | 305 |\n", + "| time_elapsed | 167 |\n", + "| total_timesteps | 51258 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000311 |\n", + "| n_updates | 314 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4860 |\n", + "| fps | 303 |\n", + "| time_elapsed | 169 |\n", + "| total_timesteps | 51317 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0148 |\n", + "| n_updates | 329 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4864 |\n", + "| fps | 302 |\n", + "| time_elapsed | 169 |\n", + "| total_timesteps | 51368 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00126 |\n", + "| n_updates | 341 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4868 |\n", + "| fps | 300 |\n", + "| time_elapsed | 170 |\n", + "| total_timesteps | 51419 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00114 |\n", + "| n_updates | 354 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4872 |\n", + "| fps | 299 |\n", + "| time_elapsed | 171 |\n", + "| total_timesteps | 51470 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.016 |\n", + "| n_updates | 367 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4876 |\n", + "| fps | 298 |\n", + "| time_elapsed | 172 |\n", + "| total_timesteps | 51496 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00144 |\n", + "| n_updates | 373 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4880 |\n", + "| fps | 297 |\n", + "| time_elapsed | 173 |\n", + "| total_timesteps | 51556 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00104 |\n", + "| n_updates | 388 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4884 |\n", + "| fps | 296 |\n", + "| time_elapsed | 173 |\n", + "| total_timesteps | 51591 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0143 |\n", + "| n_updates | 397 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4888 |\n", + "| fps | 295 |\n", + "| time_elapsed | 174 |\n", + "| total_timesteps | 51628 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0012 |\n", + "| n_updates | 406 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4892 |\n", + "| fps | 294 |\n", + "| time_elapsed | 175 |\n", + "| total_timesteps | 51674 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.015 |\n", + "| n_updates | 418 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4896 |\n", + "| fps | 293 |\n", + "| time_elapsed | 176 |\n", + "| total_timesteps | 51701 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0286 |\n", + "| n_updates | 425 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4900 |\n", + "| fps | 292 |\n", + "| time_elapsed | 176 |\n", + "| total_timesteps | 51737 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.029 |\n", + "| n_updates | 434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4904 |\n", + "| fps | 292 |\n", + "| time_elapsed | 177 |\n", + "| total_timesteps | 51772 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00103 |\n", + "| n_updates | 442 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4908 |\n", + "| fps | 290 |\n", + "| time_elapsed | 178 |\n", + "| total_timesteps | 51846 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0144 |\n", + "| n_updates | 461 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4912 |\n", + "| fps | 289 |\n", + "| time_elapsed | 178 |\n", + "| total_timesteps | 51871 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0296 |\n", + "| n_updates | 467 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4916 |\n", + "| fps | 288 |\n", + "| time_elapsed | 180 |\n", + "| total_timesteps | 51944 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0284 |\n", + "| n_updates | 485 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4920 |\n", + "| fps | 287 |\n", + "| time_elapsed | 180 |\n", + "| total_timesteps | 51969 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0424 |\n", + "| n_updates | 492 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4924 |\n", + "| fps | 286 |\n", + "| time_elapsed | 181 |\n", + "| total_timesteps | 52012 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0291 |\n", + "| n_updates | 502 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4928 |\n", + "| fps | 285 |\n", + "| time_elapsed | 182 |\n", + "| total_timesteps | 52056 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0146 |\n", + "| n_updates | 513 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4932 |\n", + "| fps | 284 |\n", + "| time_elapsed | 183 |\n", + "| total_timesteps | 52097 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000605 |\n", + "| n_updates | 524 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4936 |\n", + "| fps | 284 |\n", + "| time_elapsed | 183 |\n", + "| total_timesteps | 52121 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0578 |\n", + "| n_updates | 530 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4940 |\n", + "| fps | 282 |\n", + "| time_elapsed | 184 |\n", + "| total_timesteps | 52167 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0278 |\n", + "| n_updates | 541 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4944 |\n", + "| fps | 281 |\n", + "| time_elapsed | 185 |\n", + "| total_timesteps | 52238 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0292 |\n", + "| n_updates | 559 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4948 |\n", + "| fps | 280 |\n", + "| time_elapsed | 186 |\n", + "| total_timesteps | 52276 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000451 |\n", + "| n_updates | 568 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4952 |\n", + "| fps | 279 |\n", + "| time_elapsed | 187 |\n", + "| total_timesteps | 52316 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0295 |\n", + "| n_updates | 578 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4956 |\n", + "| fps | 278 |\n", + "| time_elapsed | 188 |\n", + "| total_timesteps | 52359 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000539 |\n", + "| n_updates | 589 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4960 |\n", + "| fps | 277 |\n", + "| time_elapsed | 188 |\n", + "| total_timesteps | 52382 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000597 |\n", + "| n_updates | 595 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4964 |\n", + "| fps | 277 |\n", + "| time_elapsed | 189 |\n", + "| total_timesteps | 52407 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000559 |\n", + "| n_updates | 601 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4968 |\n", + "| fps | 276 |\n", + "| time_elapsed | 189 |\n", + "| total_timesteps | 52430 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0147 |\n", + "| n_updates | 607 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4972 |\n", + "| fps | 275 |\n", + "| time_elapsed | 190 |\n", + "| total_timesteps | 52475 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0149 |\n", + "| n_updates | 618 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4976 |\n", + "| fps | 274 |\n", + "| time_elapsed | 191 |\n", + "| total_timesteps | 52520 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000221 |\n", + "| n_updates | 629 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4980 |\n", + "| fps | 273 |\n", + "| time_elapsed | 192 |\n", + "| total_timesteps | 52585 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0277 |\n", + "| n_updates | 646 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4984 |\n", + "| fps | 272 |\n", + "| time_elapsed | 193 |\n", + "| total_timesteps | 52639 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0147 |\n", + "| n_updates | 659 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4988 |\n", + "| fps | 271 |\n", + "| time_elapsed | 193 |\n", + "| total_timesteps | 52666 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0436 |\n", + "| n_updates | 666 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4992 |\n", + "| fps | 270 |\n", + "| time_elapsed | 194 |\n", + "| total_timesteps | 52718 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00126 |\n", + "| n_updates | 679 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 4996 |\n", + "| fps | 269 |\n", + "| time_elapsed | 195 |\n", + "| total_timesteps | 52767 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.069 |\n", + "| n_updates | 691 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5000 |\n", + "| fps | 268 |\n", + "| time_elapsed | 196 |\n", + "| total_timesteps | 52814 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.014 |\n", + "| n_updates | 703 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5004 |\n", + "| fps | 267 |\n", + "| time_elapsed | 197 |\n", + "| total_timesteps | 52875 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0432 |\n", + "| n_updates | 718 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5008 |\n", + "| fps | 266 |\n", + "| time_elapsed | 198 |\n", + "| total_timesteps | 52933 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.015 |\n", + "| n_updates | 733 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5012 |\n", + "| fps | 265 |\n", + "| time_elapsed | 199 |\n", + "| total_timesteps | 52985 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0155 |\n", + "| n_updates | 746 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5016 |\n", + "| fps | 264 |\n", + "| time_elapsed | 200 |\n", + "| total_timesteps | 53011 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0293 |\n", + "| n_updates | 752 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5020 |\n", + "| fps | 264 |\n", + "| time_elapsed | 200 |\n", + "| total_timesteps | 53038 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000472 |\n", + "| n_updates | 759 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5024 |\n", + "| fps | 263 |\n", + "| time_elapsed | 201 |\n", + "| total_timesteps | 53096 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0148 |\n", + "| n_updates | 773 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5028 |\n", + "| fps | 262 |\n", + "| time_elapsed | 202 |\n", + "| total_timesteps | 53137 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0297 |\n", + "| n_updates | 784 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5032 |\n", + "| fps | 262 |\n", + "| time_elapsed | 202 |\n", + "| total_timesteps | 53162 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0149 |\n", + "| n_updates | 790 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5036 |\n", + "| fps | 261 |\n", + "| time_elapsed | 203 |\n", + "| total_timesteps | 53188 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0144 |\n", + "| n_updates | 796 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5040 |\n", + "| fps | 260 |\n", + "| time_elapsed | 203 |\n", + "| total_timesteps | 53215 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000521 |\n", + "| n_updates | 803 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5044 |\n", + "| fps | 259 |\n", + "| time_elapsed | 205 |\n", + "| total_timesteps | 53288 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000426 |\n", + "| n_updates | 821 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5048 |\n", + "| fps | 258 |\n", + "| time_elapsed | 206 |\n", + "| total_timesteps | 53347 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0296 |\n", + "| n_updates | 836 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5052 |\n", + "| fps | 257 |\n", + "| time_elapsed | 207 |\n", + "| total_timesteps | 53397 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000546 |\n", + "| n_updates | 849 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5056 |\n", + "| fps | 256 |\n", + "| time_elapsed | 208 |\n", + "| total_timesteps | 53440 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0145 |\n", + "| n_updates | 859 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5060 |\n", + "| fps | 255 |\n", + "| time_elapsed | 209 |\n", + "| total_timesteps | 53523 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000511 |\n", + "| n_updates | 880 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5064 |\n", + "| fps | 254 |\n", + "| time_elapsed | 210 |\n", + "| total_timesteps | 53549 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000711 |\n", + "| n_updates | 887 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5068 |\n", + "| fps | 253 |\n", + "| time_elapsed | 211 |\n", + "| total_timesteps | 53645 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0146 |\n", + "| n_updates | 911 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5072 |\n", + "| fps | 252 |\n", + "| time_elapsed | 212 |\n", + "| total_timesteps | 53681 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0285 |\n", + "| n_updates | 920 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5076 |\n", + "| fps | 251 |\n", + "| time_elapsed | 213 |\n", + "| total_timesteps | 53741 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00168 |\n", + "| n_updates | 935 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5080 |\n", + "| fps | 250 |\n", + "| time_elapsed | 214 |\n", + "| total_timesteps | 53786 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000836 |\n", + "| n_updates | 946 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5084 |\n", + "| fps | 249 |\n", + "| time_elapsed | 215 |\n", + "| total_timesteps | 53836 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.015 |\n", + "| n_updates | 958 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5088 |\n", + "| fps | 249 |\n", + "| time_elapsed | 215 |\n", + "| total_timesteps | 53858 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0144 |\n", + "| n_updates | 964 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5092 |\n", + "| fps | 248 |\n", + "| time_elapsed | 216 |\n", + "| total_timesteps | 53901 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0147 |\n", + "| n_updates | 975 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5096 |\n", + "| fps | 247 |\n", + "| time_elapsed | 217 |\n", + "| total_timesteps | 53940 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0297 |\n", + "| n_updates | 984 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5100 |\n", + "| fps | 247 |\n", + "| time_elapsed | 218 |\n", + "| total_timesteps | 53987 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0283 |\n", + "| n_updates | 996 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5104 |\n", + "| fps | 246 |\n", + "| time_elapsed | 219 |\n", + "| total_timesteps | 54032 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.015 |\n", + "| n_updates | 1007 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5108 |\n", + "| fps | 245 |\n", + "| time_elapsed | 220 |\n", + "| total_timesteps | 54097 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0281 |\n", + "| n_updates | 1024 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5112 |\n", + "| fps | 244 |\n", + "| time_elapsed | 220 |\n", + "| total_timesteps | 54118 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0149 |\n", + "| n_updates | 1029 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5116 |\n", + "| fps | 244 |\n", + "| time_elapsed | 221 |\n", + "| total_timesteps | 54166 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.015 |\n", + "| n_updates | 1041 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5120 |\n", + "| fps | 243 |\n", + "| time_elapsed | 222 |\n", + "| total_timesteps | 54223 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0294 |\n", + "| n_updates | 1055 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5124 |\n", + "| fps | 242 |\n", + "| time_elapsed | 223 |\n", + "| total_timesteps | 54269 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0282 |\n", + "| n_updates | 1067 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5128 |\n", + "| fps | 241 |\n", + "| time_elapsed | 225 |\n", + "| total_timesteps | 54336 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00131 |\n", + "| n_updates | 1083 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5132 |\n", + "| fps | 240 |\n", + "| time_elapsed | 226 |\n", + "| total_timesteps | 54403 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0146 |\n", + "| n_updates | 1100 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5136 |\n", + "| fps | 239 |\n", + "| time_elapsed | 227 |\n", + "| total_timesteps | 54447 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0284 |\n", + "| n_updates | 1111 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5140 |\n", + "| fps | 238 |\n", + "| time_elapsed | 228 |\n", + "| total_timesteps | 54497 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000534 |\n", + "| n_updates | 1124 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5144 |\n", + "| fps | 237 |\n", + "| time_elapsed | 229 |\n", + "| total_timesteps | 54564 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0147 |\n", + "| n_updates | 1140 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5148 |\n", + "| fps | 237 |\n", + "| time_elapsed | 230 |\n", + "| total_timesteps | 54616 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0147 |\n", + "| n_updates | 1153 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5152 |\n", + "| fps | 236 |\n", + "| time_elapsed | 230 |\n", + "| total_timesteps | 54642 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0146 |\n", + "| n_updates | 1160 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5156 |\n", + "| fps | 236 |\n", + "| time_elapsed | 231 |\n", + "| total_timesteps | 54684 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0143 |\n", + "| n_updates | 1170 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5160 |\n", + "| fps | 235 |\n", + "| time_elapsed | 232 |\n", + "| total_timesteps | 54711 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0147 |\n", + "| n_updates | 1177 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5164 |\n", + "| fps | 235 |\n", + "| time_elapsed | 232 |\n", + "| total_timesteps | 54753 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0149 |\n", + "| n_updates | 1188 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5168 |\n", + "| fps | 234 |\n", + "| time_elapsed | 233 |\n", + "| total_timesteps | 54800 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000543 |\n", + "| n_updates | 1199 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5172 |\n", + "| fps | 233 |\n", + "| time_elapsed | 234 |\n", + "| total_timesteps | 54836 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0153 |\n", + "| n_updates | 1208 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5176 |\n", + "| fps | 233 |\n", + "| time_elapsed | 235 |\n", + "| total_timesteps | 54865 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0152 |\n", + "| n_updates | 1216 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5180 |\n", + "| fps | 232 |\n", + "| time_elapsed | 235 |\n", + "| total_timesteps | 54907 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0289 |\n", + "| n_updates | 1226 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5184 |\n", + "| fps | 232 |\n", + "| time_elapsed | 236 |\n", + "| total_timesteps | 54950 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000932 |\n", + "| n_updates | 1237 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5188 |\n", + "| fps | 231 |\n", + "| time_elapsed | 237 |\n", + "| total_timesteps | 54977 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0426 |\n", + "| n_updates | 1244 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5192 |\n", + "| fps | 231 |\n", + "| time_elapsed | 237 |\n", + "| total_timesteps | 55018 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0431 |\n", + "| n_updates | 1254 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5196 |\n", + "| fps | 230 |\n", + "| time_elapsed | 238 |\n", + "| total_timesteps | 55065 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0286 |\n", + "| n_updates | 1266 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5200 |\n", + "| fps | 230 |\n", + "| time_elapsed | 239 |\n", + "| total_timesteps | 55100 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000741 |\n", + "| n_updates | 1274 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5204 |\n", + "| fps | 229 |\n", + "| time_elapsed | 240 |\n", + "| total_timesteps | 55147 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000546 |\n", + "| n_updates | 1286 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5208 |\n", + "| fps | 228 |\n", + "| time_elapsed | 241 |\n", + "| total_timesteps | 55189 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000986 |\n", + "| n_updates | 1297 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5212 |\n", + "| fps | 228 |\n", + "| time_elapsed | 241 |\n", + "| total_timesteps | 55225 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0149 |\n", + "| n_updates | 1306 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5216 |\n", + "| fps | 227 |\n", + "| time_elapsed | 242 |\n", + "| total_timesteps | 55267 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0142 |\n", + "| n_updates | 1316 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5220 |\n", + "| fps | 227 |\n", + "| time_elapsed | 243 |\n", + "| total_timesteps | 55294 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000454 |\n", + "| n_updates | 1323 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5224 |\n", + "| fps | 226 |\n", + "| time_elapsed | 243 |\n", + "| total_timesteps | 55325 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000881 |\n", + "| n_updates | 1331 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5228 |\n", + "| fps | 226 |\n", + "| time_elapsed | 244 |\n", + "| total_timesteps | 55366 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000616 |\n", + "| n_updates | 1341 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5232 |\n", + "| fps | 226 |\n", + "| time_elapsed | 245 |\n", + "| total_timesteps | 55392 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0282 |\n", + "| n_updates | 1347 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5236 |\n", + "| fps | 225 |\n", + "| time_elapsed | 245 |\n", + "| total_timesteps | 55429 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00206 |\n", + "| n_updates | 1357 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5240 |\n", + "| fps | 225 |\n", + "| time_elapsed | 246 |\n", + "| total_timesteps | 55464 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0153 |\n", + "| n_updates | 1365 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5244 |\n", + "| fps | 224 |\n", + "| time_elapsed | 247 |\n", + "| total_timesteps | 55512 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0147 |\n", + "| n_updates | 1377 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5248 |\n", + "| fps | 224 |\n", + "| time_elapsed | 247 |\n", + "| total_timesteps | 55535 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0142 |\n", + "| n_updates | 1383 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5252 |\n", + "| fps | 223 |\n", + "| time_elapsed | 249 |\n", + "| total_timesteps | 55602 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0144 |\n", + "| n_updates | 1400 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5256 |\n", + "| fps | 222 |\n", + "| time_elapsed | 249 |\n", + "| total_timesteps | 55626 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0144 |\n", + "| n_updates | 1406 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5260 |\n", + "| fps | 222 |\n", + "| time_elapsed | 250 |\n", + "| total_timesteps | 55674 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0149 |\n", + "| n_updates | 1418 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5264 |\n", + "| fps | 221 |\n", + "| time_elapsed | 251 |\n", + "| total_timesteps | 55740 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0145 |\n", + "| n_updates | 1434 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5268 |\n", + "| fps | 220 |\n", + "| time_elapsed | 252 |\n", + "| total_timesteps | 55787 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000953 |\n", + "| n_updates | 1446 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5272 |\n", + "| fps | 220 |\n", + "| time_elapsed | 253 |\n", + "| total_timesteps | 55853 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000878 |\n", + "| n_updates | 1463 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5276 |\n", + "| fps | 219 |\n", + "| time_elapsed | 254 |\n", + "| total_timesteps | 55888 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00119 |\n", + "| n_updates | 1471 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5280 |\n", + "| fps | 219 |\n", + "| time_elapsed | 254 |\n", + "| total_timesteps | 55914 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.039 |\n", + "| n_updates | 1478 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5284 |\n", + "| fps | 219 |\n", + "| time_elapsed | 255 |\n", + "| total_timesteps | 55939 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000656 |\n", + "| n_updates | 1484 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5288 |\n", + "| fps | 218 |\n", + "| time_elapsed | 255 |\n", + "| total_timesteps | 55967 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0147 |\n", + "| n_updates | 1491 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5292 |\n", + "| fps | 218 |\n", + "| time_elapsed | 256 |\n", + "| total_timesteps | 55991 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000621 |\n", + "| n_updates | 1497 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5296 |\n", + "| fps | 217 |\n", + "| time_elapsed | 257 |\n", + "| total_timesteps | 56046 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0399 |\n", + "| n_updates | 1511 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5300 |\n", + "| fps | 217 |\n", + "| time_elapsed | 258 |\n", + "| total_timesteps | 56081 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0269 |\n", + "| n_updates | 1520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5304 |\n", + "| fps | 216 |\n", + "| time_elapsed | 258 |\n", + "| total_timesteps | 56132 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000683 |\n", + "| n_updates | 1532 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5308 |\n", + "| fps | 216 |\n", + "| time_elapsed | 260 |\n", + "| total_timesteps | 56190 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.012 |\n", + "| n_updates | 1547 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5312 |\n", + "| fps | 215 |\n", + "| time_elapsed | 260 |\n", + "| total_timesteps | 56215 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0269 |\n", + "| n_updates | 1553 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5316 |\n", + "| fps | 215 |\n", + "| time_elapsed | 261 |\n", + "| total_timesteps | 56251 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0111 |\n", + "| n_updates | 1562 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5320 |\n", + "| fps | 215 |\n", + "| time_elapsed | 261 |\n", + "| total_timesteps | 56276 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00101 |\n", + "| n_updates | 1568 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5324 |\n", + "| fps | 214 |\n", + "| time_elapsed | 262 |\n", + "| total_timesteps | 56302 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.012 |\n", + "| n_updates | 1575 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5328 |\n", + "| fps | 213 |\n", + "| time_elapsed | 263 |\n", + "| total_timesteps | 56394 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0117 |\n", + "| n_updates | 1598 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5332 |\n", + "| fps | 213 |\n", + "| time_elapsed | 264 |\n", + "| total_timesteps | 56420 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00831 |\n", + "| n_updates | 1604 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5336 |\n", + "| fps | 212 |\n", + "| time_elapsed | 265 |\n", + "| total_timesteps | 56487 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00172 |\n", + "| n_updates | 1621 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5340 |\n", + "| fps | 212 |\n", + "| time_elapsed | 266 |\n", + "| total_timesteps | 56515 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0132 |\n", + "| n_updates | 1628 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5344 |\n", + "| fps | 211 |\n", + "| time_elapsed | 267 |\n", + "| total_timesteps | 56557 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0106 |\n", + "| n_updates | 1639 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5348 |\n", + "| fps | 211 |\n", + "| time_elapsed | 267 |\n", + "| total_timesteps | 56594 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00098 |\n", + "| n_updates | 1648 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5352 |\n", + "| fps | 210 |\n", + "| time_elapsed | 268 |\n", + "| total_timesteps | 56642 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00514 |\n", + "| n_updates | 1660 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5356 |\n", + "| fps | 210 |\n", + "| time_elapsed | 269 |\n", + "| total_timesteps | 56691 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00495 |\n", + "| n_updates | 1672 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5360 |\n", + "| fps | 209 |\n", + "| time_elapsed | 270 |\n", + "| total_timesteps | 56733 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000961 |\n", + "| n_updates | 1683 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5364 |\n", + "| fps | 208 |\n", + "| time_elapsed | 272 |\n", + "| total_timesteps | 56823 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000128 |\n", + "| n_updates | 1705 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5368 |\n", + "| fps | 207 |\n", + "| time_elapsed | 273 |\n", + "| total_timesteps | 56876 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0141 |\n", + "| n_updates | 1718 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5372 |\n", + "| fps | 207 |\n", + "| time_elapsed | 274 |\n", + "| total_timesteps | 56903 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0164 |\n", + "| n_updates | 1725 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5376 |\n", + "| fps | 206 |\n", + "| time_elapsed | 275 |\n", + "| total_timesteps | 56987 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00486 |\n", + "| n_updates | 1746 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5380 |\n", + "| fps | 206 |\n", + "| time_elapsed | 276 |\n", + "| total_timesteps | 57015 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0194 |\n", + "| n_updates | 1753 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5384 |\n", + "| fps | 205 |\n", + "| time_elapsed | 276 |\n", + "| total_timesteps | 57042 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00445 |\n", + "| n_updates | 1760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5388 |\n", + "| fps | 205 |\n", + "| time_elapsed | 277 |\n", + "| total_timesteps | 57094 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00735 |\n", + "| n_updates | 1773 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5392 |\n", + "| fps | 204 |\n", + "| time_elapsed | 278 |\n", + "| total_timesteps | 57137 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00801 |\n", + "| n_updates | 1784 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5396 |\n", + "| fps | 204 |\n", + "| time_elapsed | 279 |\n", + "| total_timesteps | 57163 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0182 |\n", + "| n_updates | 1790 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5400 |\n", + "| fps | 204 |\n", + "| time_elapsed | 279 |\n", + "| total_timesteps | 57186 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00881 |\n", + "| n_updates | 1796 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5404 |\n", + "| fps | 203 |\n", + "| time_elapsed | 280 |\n", + "| total_timesteps | 57232 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00121 |\n", + "| n_updates | 1807 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5408 |\n", + "| fps | 203 |\n", + "| time_elapsed | 281 |\n", + "| total_timesteps | 57273 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.012 |\n", + "| n_updates | 1818 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5412 |\n", + "| fps | 203 |\n", + "| time_elapsed | 281 |\n", + "| total_timesteps | 57299 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0236 |\n", + "| n_updates | 1824 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5416 |\n", + "| fps | 202 |\n", + "| time_elapsed | 283 |\n", + "| total_timesteps | 57386 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00282 |\n", + "| n_updates | 1846 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5420 |\n", + "| fps | 201 |\n", + "| time_elapsed | 284 |\n", + "| total_timesteps | 57440 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000308 |\n", + "| n_updates | 1859 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5424 |\n", + "| fps | 201 |\n", + "| time_elapsed | 285 |\n", + "| total_timesteps | 57487 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00228 |\n", + "| n_updates | 1871 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5428 |\n", + "| fps | 201 |\n", + "| time_elapsed | 286 |\n", + "| total_timesteps | 57531 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0024 |\n", + "| n_updates | 1882 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5432 |\n", + "| fps | 200 |\n", + "| time_elapsed | 286 |\n", + "| total_timesteps | 57558 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00165 |\n", + "| n_updates | 1889 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5436 |\n", + "| fps | 200 |\n", + "| time_elapsed | 287 |\n", + "| total_timesteps | 57625 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000557 |\n", + "| n_updates | 1906 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5440 |\n", + "| fps | 199 |\n", + "| time_elapsed | 288 |\n", + "| total_timesteps | 57677 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00958 |\n", + "| n_updates | 1919 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5444 |\n", + "| fps | 199 |\n", + "| time_elapsed | 289 |\n", + "| total_timesteps | 57730 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00315 |\n", + "| n_updates | 1932 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5448 |\n", + "| fps | 198 |\n", + "| time_elapsed | 290 |\n", + "| total_timesteps | 57757 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00084 |\n", + "| n_updates | 1939 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5452 |\n", + "| fps | 198 |\n", + "| time_elapsed | 291 |\n", + "| total_timesteps | 57806 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00755 |\n", + "| n_updates | 1951 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5456 |\n", + "| fps | 198 |\n", + "| time_elapsed | 291 |\n", + "| total_timesteps | 57834 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0108 |\n", + "| n_updates | 1958 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5460 |\n", + "| fps | 197 |\n", + "| time_elapsed | 293 |\n", + "| total_timesteps | 57902 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00378 |\n", + "| n_updates | 1975 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5464 |\n", + "| fps | 197 |\n", + "| time_elapsed | 294 |\n", + "| total_timesteps | 57953 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00979 |\n", + "| n_updates | 1988 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5468 |\n", + "| fps | 196 |\n", + "| time_elapsed | 294 |\n", + "| total_timesteps | 58000 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000964 |\n", + "| n_updates | 1999 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5472 |\n", + "| fps | 196 |\n", + "| time_elapsed | 295 |\n", + "| total_timesteps | 58053 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0133 |\n", + "| n_updates | 2013 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5476 |\n", + "| fps | 195 |\n", + "| time_elapsed | 297 |\n", + "| total_timesteps | 58139 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 9e-05 |\n", + "| n_updates | 2034 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5480 |\n", + "| fps | 195 |\n", + "| time_elapsed | 298 |\n", + "| total_timesteps | 58182 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00661 |\n", + "| n_updates | 2045 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5484 |\n", + "| fps | 194 |\n", + "| time_elapsed | 299 |\n", + "| total_timesteps | 58231 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0205 |\n", + "| n_updates | 2057 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5488 |\n", + "| fps | 194 |\n", + "| time_elapsed | 300 |\n", + "| total_timesteps | 58281 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00217 |\n", + "| n_updates | 2070 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5492 |\n", + "| fps | 193 |\n", + "| time_elapsed | 301 |\n", + "| total_timesteps | 58318 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0138 |\n", + "| n_updates | 2079 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5496 |\n", + "| fps | 193 |\n", + "| time_elapsed | 301 |\n", + "| total_timesteps | 58344 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00214 |\n", + "| n_updates | 2085 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5500 |\n", + "| fps | 193 |\n", + "| time_elapsed | 302 |\n", + "| total_timesteps | 58404 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0162 |\n", + "| n_updates | 2100 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5504 |\n", + "| fps | 192 |\n", + "| time_elapsed | 303 |\n", + "| total_timesteps | 58441 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00868 |\n", + "| n_updates | 2110 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5508 |\n", + "| fps | 192 |\n", + "| time_elapsed | 304 |\n", + "| total_timesteps | 58488 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00562 |\n", + "| n_updates | 2121 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5512 |\n", + "| fps | 191 |\n", + "| time_elapsed | 304 |\n", + "| total_timesteps | 58526 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0104 |\n", + "| n_updates | 2131 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5516 |\n", + "| fps | 191 |\n", + "| time_elapsed | 305 |\n", + "| total_timesteps | 58548 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0064 |\n", + "| n_updates | 2136 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5520 |\n", + "| fps | 191 |\n", + "| time_elapsed | 305 |\n", + "| total_timesteps | 58584 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00129 |\n", + "| n_updates | 2145 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5524 |\n", + "| fps | 191 |\n", + "| time_elapsed | 306 |\n", + "| total_timesteps | 58610 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00855 |\n", + "| n_updates | 2152 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5528 |\n", + "| fps | 190 |\n", + "| time_elapsed | 307 |\n", + "| total_timesteps | 58652 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0003 |\n", + "| n_updates | 2162 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5532 |\n", + "| fps | 190 |\n", + "| time_elapsed | 307 |\n", + "| total_timesteps | 58679 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000147 |\n", + "| n_updates | 2169 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5536 |\n", + "| fps | 190 |\n", + "| time_elapsed | 308 |\n", + "| total_timesteps | 58744 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00809 |\n", + "| n_updates | 2185 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5540 |\n", + "| fps | 189 |\n", + "| time_elapsed | 310 |\n", + "| total_timesteps | 58808 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00835 |\n", + "| n_updates | 2201 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5544 |\n", + "| fps | 189 |\n", + "| time_elapsed | 310 |\n", + "| total_timesteps | 58833 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000118 |\n", + "| n_updates | 2208 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5548 |\n", + "| fps | 188 |\n", + "| time_elapsed | 311 |\n", + "| total_timesteps | 58885 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00642 |\n", + "| n_updates | 2221 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5552 |\n", + "| fps | 188 |\n", + "| time_elapsed | 312 |\n", + "| total_timesteps | 58927 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00692 |\n", + "| n_updates | 2231 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5556 |\n", + "| fps | 188 |\n", + "| time_elapsed | 312 |\n", + "| total_timesteps | 58953 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0118 |\n", + "| n_updates | 2238 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5560 |\n", + "| fps | 187 |\n", + "| time_elapsed | 313 |\n", + "| total_timesteps | 59005 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0196 |\n", + "| n_updates | 2251 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5564 |\n", + "| fps | 187 |\n", + "| time_elapsed | 315 |\n", + "| total_timesteps | 59065 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000201 |\n", + "| n_updates | 2266 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5568 |\n", + "| fps | 186 |\n", + "| time_elapsed | 316 |\n", + "| total_timesteps | 59141 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00167 |\n", + "| n_updates | 2285 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5572 |\n", + "| fps | 186 |\n", + "| time_elapsed | 317 |\n", + "| total_timesteps | 59196 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 6.98e-05 |\n", + "| n_updates | 2298 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5576 |\n", + "| fps | 186 |\n", + "| time_elapsed | 318 |\n", + "| total_timesteps | 59218 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0183 |\n", + "| n_updates | 2304 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5580 |\n", + "| fps | 185 |\n", + "| time_elapsed | 319 |\n", + "| total_timesteps | 59300 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00428 |\n", + "| n_updates | 2324 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5584 |\n", + "| fps | 185 |\n", + "| time_elapsed | 320 |\n", + "| total_timesteps | 59354 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0127 |\n", + "| n_updates | 2338 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5588 |\n", + "| fps | 184 |\n", + "| time_elapsed | 321 |\n", + "| total_timesteps | 59381 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0122 |\n", + "| n_updates | 2345 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5592 |\n", + "| fps | 183 |\n", + "| time_elapsed | 322 |\n", + "| total_timesteps | 59419 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00403 |\n", + "| n_updates | 2354 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5596 |\n", + "| fps | 182 |\n", + "| time_elapsed | 325 |\n", + "| total_timesteps | 59489 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 2372 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5600 |\n", + "| fps | 182 |\n", + "| time_elapsed | 325 |\n", + "| total_timesteps | 59514 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00522 |\n", + "| n_updates | 2378 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5604 |\n", + "| fps | 182 |\n", + "| time_elapsed | 326 |\n", + "| total_timesteps | 59541 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00505 |\n", + "| n_updates | 2385 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5608 |\n", + "| fps | 182 |\n", + "| time_elapsed | 326 |\n", + "| total_timesteps | 59583 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00349 |\n", + "| n_updates | 2395 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5612 |\n", + "| fps | 181 |\n", + "| time_elapsed | 328 |\n", + "| total_timesteps | 59646 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0125 |\n", + "| n_updates | 2411 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5616 |\n", + "| fps | 181 |\n", + "| time_elapsed | 329 |\n", + "| total_timesteps | 59689 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00609 |\n", + "| n_updates | 2422 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5620 |\n", + "| fps | 180 |\n", + "| time_elapsed | 330 |\n", + "| total_timesteps | 59764 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00485 |\n", + "| n_updates | 2440 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5624 |\n", + "| fps | 180 |\n", + "| time_elapsed | 331 |\n", + "| total_timesteps | 59815 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0105 |\n", + "| n_updates | 2453 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5628 |\n", + "| fps | 180 |\n", + "| time_elapsed | 332 |\n", + "| total_timesteps | 59856 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00107 |\n", + "| n_updates | 2463 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5632 |\n", + "| fps | 179 |\n", + "| time_elapsed | 333 |\n", + "| total_timesteps | 59906 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0152 |\n", + "| n_updates | 2476 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5636 |\n", + "| fps | 179 |\n", + "| time_elapsed | 333 |\n", + "| total_timesteps | 59933 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00677 |\n", + "| n_updates | 2483 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5640 |\n", + "| fps | 179 |\n", + "| time_elapsed | 334 |\n", + "| total_timesteps | 59982 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000152 |\n", + "| n_updates | 2495 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5644 |\n", + "| fps | 178 |\n", + "| time_elapsed | 335 |\n", + "| total_timesteps | 60028 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000297 |\n", + "| n_updates | 2506 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5648 |\n", + "| fps | 178 |\n", + "| time_elapsed | 336 |\n", + "| total_timesteps | 60052 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0147 |\n", + "| n_updates | 2512 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5652 |\n", + "| fps | 178 |\n", + "| time_elapsed | 336 |\n", + "| total_timesteps | 60077 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00848 |\n", + "| n_updates | 2519 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5656 |\n", + "| fps | 178 |\n", + "| time_elapsed | 337 |\n", + "| total_timesteps | 60111 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0019 |\n", + "| n_updates | 2527 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5660 |\n", + "| fps | 177 |\n", + "| time_elapsed | 337 |\n", + "| total_timesteps | 60138 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00585 |\n", + "| n_updates | 2534 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5664 |\n", + "| fps | 177 |\n", + "| time_elapsed | 339 |\n", + "| total_timesteps | 60227 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00555 |\n", + "| n_updates | 2556 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5668 |\n", + "| fps | 177 |\n", + "| time_elapsed | 340 |\n", + "| total_timesteps | 60261 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0017 |\n", + "| n_updates | 2565 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5672 |\n", + "| fps | 176 |\n", + "| time_elapsed | 341 |\n", + "| total_timesteps | 60312 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00903 |\n", + "| n_updates | 2577 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5676 |\n", + "| fps | 176 |\n", + "| time_elapsed | 342 |\n", + "| total_timesteps | 60380 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00286 |\n", + "| n_updates | 2594 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5680 |\n", + "| fps | 175 |\n", + "| time_elapsed | 343 |\n", + "| total_timesteps | 60406 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00453 |\n", + "| n_updates | 2601 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5684 |\n", + "| fps | 175 |\n", + "| time_elapsed | 344 |\n", + "| total_timesteps | 60442 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00362 |\n", + "| n_updates | 2610 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5688 |\n", + "| fps | 175 |\n", + "| time_elapsed | 345 |\n", + "| total_timesteps | 60492 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00638 |\n", + "| n_updates | 2622 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5692 |\n", + "| fps | 175 |\n", + "| time_elapsed | 345 |\n", + "| total_timesteps | 60518 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00161 |\n", + "| n_updates | 2629 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5696 |\n", + "| fps | 174 |\n", + "| time_elapsed | 346 |\n", + "| total_timesteps | 60569 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00246 |\n", + "| n_updates | 2642 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5700 |\n", + "| fps | 174 |\n", + "| time_elapsed | 347 |\n", + "| total_timesteps | 60617 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00324 |\n", + "| n_updates | 2654 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5704 |\n", + "| fps | 174 |\n", + "| time_elapsed | 348 |\n", + "| total_timesteps | 60644 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00104 |\n", + "| n_updates | 2660 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5708 |\n", + "| fps | 174 |\n", + "| time_elapsed | 348 |\n", + "| total_timesteps | 60670 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00486 |\n", + "| n_updates | 2667 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5712 |\n", + "| fps | 173 |\n", + "| time_elapsed | 349 |\n", + "| total_timesteps | 60732 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00162 |\n", + "| n_updates | 2682 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5716 |\n", + "| fps | 173 |\n", + "| time_elapsed | 350 |\n", + "| total_timesteps | 60758 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000828 |\n", + "| n_updates | 2689 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5720 |\n", + "| fps | 173 |\n", + "| time_elapsed | 351 |\n", + "| total_timesteps | 60811 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00542 |\n", + "| n_updates | 2702 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5724 |\n", + "| fps | 172 |\n", + "| time_elapsed | 351 |\n", + "| total_timesteps | 60835 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000917 |\n", + "| n_updates | 2708 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5728 |\n", + "| fps | 172 |\n", + "| time_elapsed | 352 |\n", + "| total_timesteps | 60884 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0158 |\n", + "| n_updates | 2720 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5732 |\n", + "| fps | 172 |\n", + "| time_elapsed | 353 |\n", + "| total_timesteps | 60908 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0014 |\n", + "| n_updates | 2726 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5736 |\n", + "| fps | 172 |\n", + "| time_elapsed | 354 |\n", + "| total_timesteps | 60930 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00347 |\n", + "| n_updates | 2732 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5740 |\n", + "| fps | 171 |\n", + "| time_elapsed | 354 |\n", + "| total_timesteps | 60956 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00745 |\n", + "| n_updates | 2738 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5744 |\n", + "| fps | 171 |\n", + "| time_elapsed | 355 |\n", + "| total_timesteps | 60990 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0023 |\n", + "| n_updates | 2747 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5748 |\n", + "| fps | 171 |\n", + "| time_elapsed | 356 |\n", + "| total_timesteps | 61015 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0074 |\n", + "| n_updates | 2753 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5752 |\n", + "| fps | 170 |\n", + "| time_elapsed | 357 |\n", + "| total_timesteps | 61041 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00393 |\n", + "| n_updates | 2760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5756 |\n", + "| fps | 170 |\n", + "| time_elapsed | 358 |\n", + "| total_timesteps | 61111 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000946 |\n", + "| n_updates | 2777 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5760 |\n", + "| fps | 170 |\n", + "| time_elapsed | 359 |\n", + "| total_timesteps | 61139 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00275 |\n", + "| n_updates | 2784 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5764 |\n", + "| fps | 170 |\n", + "| time_elapsed | 359 |\n", + "| total_timesteps | 61167 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000912 |\n", + "| n_updates | 2791 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5768 |\n", + "| fps | 169 |\n", + "| time_elapsed | 361 |\n", + "| total_timesteps | 61225 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00703 |\n", + "| n_updates | 2806 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5772 |\n", + "| fps | 169 |\n", + "| time_elapsed | 361 |\n", + "| total_timesteps | 61251 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00578 |\n", + "| n_updates | 2812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5776 |\n", + "| fps | 169 |\n", + "| time_elapsed | 362 |\n", + "| total_timesteps | 61288 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.016 |\n", + "| n_updates | 2821 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5780 |\n", + "| fps | 168 |\n", + "| time_elapsed | 364 |\n", + "| total_timesteps | 61364 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0138 |\n", + "| n_updates | 2840 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5784 |\n", + "| fps | 168 |\n", + "| time_elapsed | 365 |\n", + "| total_timesteps | 61414 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000131 |\n", + "| n_updates | 2853 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5788 |\n", + "| fps | 167 |\n", + "| time_elapsed | 366 |\n", + "| total_timesteps | 61465 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00518 |\n", + "| n_updates | 2866 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5792 |\n", + "| fps | 167 |\n", + "| time_elapsed | 366 |\n", + "| total_timesteps | 61491 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000916 |\n", + "| n_updates | 2872 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5796 |\n", + "| fps | 167 |\n", + "| time_elapsed | 367 |\n", + "| total_timesteps | 61518 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0109 |\n", + "| n_updates | 2879 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5800 |\n", + "| fps | 167 |\n", + "| time_elapsed | 367 |\n", + "| total_timesteps | 61546 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000268 |\n", + "| n_updates | 2886 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5804 |\n", + "| fps | 167 |\n", + "| time_elapsed | 368 |\n", + "| total_timesteps | 61606 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000446 |\n", + "| n_updates | 2901 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5808 |\n", + "| fps | 166 |\n", + "| time_elapsed | 370 |\n", + "| total_timesteps | 61669 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00147 |\n", + "| n_updates | 2917 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5812 |\n", + "| fps | 166 |\n", + "| time_elapsed | 371 |\n", + "| total_timesteps | 61714 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0239 |\n", + "| n_updates | 2928 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5816 |\n", + "| fps | 166 |\n", + "| time_elapsed | 371 |\n", + "| total_timesteps | 61750 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000831 |\n", + "| n_updates | 2937 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5820 |\n", + "| fps | 165 |\n", + "| time_elapsed | 372 |\n", + "| total_timesteps | 61793 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000797 |\n", + "| n_updates | 2948 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5824 |\n", + "| fps | 165 |\n", + "| time_elapsed | 373 |\n", + "| total_timesteps | 61821 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0136 |\n", + "| n_updates | 2955 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5828 |\n", + "| fps | 165 |\n", + "| time_elapsed | 373 |\n", + "| total_timesteps | 61848 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00199 |\n", + "| n_updates | 2961 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5832 |\n", + "| fps | 165 |\n", + "| time_elapsed | 374 |\n", + "| total_timesteps | 61896 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0091 |\n", + "| n_updates | 2973 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5836 |\n", + "| fps | 164 |\n", + "| time_elapsed | 375 |\n", + "| total_timesteps | 61917 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 2979 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5840 |\n", + "| fps | 164 |\n", + "| time_elapsed | 376 |\n", + "| total_timesteps | 61964 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00549 |\n", + "| n_updates | 2990 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5844 |\n", + "| fps | 164 |\n", + "| time_elapsed | 378 |\n", + "| total_timesteps | 62066 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00786 |\n", + "| n_updates | 3016 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5848 |\n", + "| fps | 163 |\n", + "| time_elapsed | 379 |\n", + "| total_timesteps | 62111 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00383 |\n", + "| n_updates | 3027 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5852 |\n", + "| fps | 163 |\n", + "| time_elapsed | 379 |\n", + "| total_timesteps | 62133 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.007 |\n", + "| n_updates | 3033 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5856 |\n", + "| fps | 163 |\n", + "| time_elapsed | 380 |\n", + "| total_timesteps | 62182 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000118 |\n", + "| n_updates | 3045 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5860 |\n", + "| fps | 163 |\n", + "| time_elapsed | 381 |\n", + "| total_timesteps | 62230 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0159 |\n", + "| n_updates | 3057 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5864 |\n", + "| fps | 162 |\n", + "| time_elapsed | 382 |\n", + "| total_timesteps | 62255 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0131 |\n", + "| n_updates | 3063 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5868 |\n", + "| fps | 162 |\n", + "| time_elapsed | 383 |\n", + "| total_timesteps | 62303 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00666 |\n", + "| n_updates | 3075 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5872 |\n", + "| fps | 162 |\n", + "| time_elapsed | 384 |\n", + "| total_timesteps | 62353 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.005 |\n", + "| n_updates | 3088 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5876 |\n", + "| fps | 162 |\n", + "| time_elapsed | 384 |\n", + "| total_timesteps | 62376 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0178 |\n", + "| n_updates | 3093 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5880 |\n", + "| fps | 162 |\n", + "| time_elapsed | 385 |\n", + "| total_timesteps | 62397 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 4.37e-05 |\n", + "| n_updates | 3099 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5884 |\n", + "| fps | 161 |\n", + "| time_elapsed | 385 |\n", + "| total_timesteps | 62431 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00402 |\n", + "| n_updates | 3107 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5888 |\n", + "| fps | 161 |\n", + "| time_elapsed | 386 |\n", + "| total_timesteps | 62455 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0014 |\n", + "| n_updates | 3113 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5892 |\n", + "| fps | 161 |\n", + "| time_elapsed | 386 |\n", + "| total_timesteps | 62481 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 3120 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5896 |\n", + "| fps | 161 |\n", + "| time_elapsed | 387 |\n", + "| total_timesteps | 62509 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00158 |\n", + "| n_updates | 3127 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5900 |\n", + "| fps | 161 |\n", + "| time_elapsed | 387 |\n", + "| total_timesteps | 62536 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00459 |\n", + "| n_updates | 3133 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5904 |\n", + "| fps | 161 |\n", + "| time_elapsed | 388 |\n", + "| total_timesteps | 62561 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 9.16e-05 |\n", + "| n_updates | 3140 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5908 |\n", + "| fps | 160 |\n", + "| time_elapsed | 388 |\n", + "| total_timesteps | 62588 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000123 |\n", + "| n_updates | 3146 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5912 |\n", + "| fps | 160 |\n", + "| time_elapsed | 389 |\n", + "| total_timesteps | 62625 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00301 |\n", + "| n_updates | 3156 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5916 |\n", + "| fps | 160 |\n", + "| time_elapsed | 389 |\n", + "| total_timesteps | 62652 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00232 |\n", + "| n_updates | 3162 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5920 |\n", + "| fps | 160 |\n", + "| time_elapsed | 391 |\n", + "| total_timesteps | 62704 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0189 |\n", + "| n_updates | 3175 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5924 |\n", + "| fps | 159 |\n", + "| time_elapsed | 392 |\n", + "| total_timesteps | 62770 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00175 |\n", + "| n_updates | 3192 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5928 |\n", + "| fps | 159 |\n", + "| time_elapsed | 393 |\n", + "| total_timesteps | 62838 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000754 |\n", + "| n_updates | 3209 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5932 |\n", + "| fps | 159 |\n", + "| time_elapsed | 394 |\n", + "| total_timesteps | 62863 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00141 |\n", + "| n_updates | 3215 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5936 |\n", + "| fps | 159 |\n", + "| time_elapsed | 395 |\n", + "| total_timesteps | 62913 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00363 |\n", + "| n_updates | 3228 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5940 |\n", + "| fps | 158 |\n", + "| time_elapsed | 396 |\n", + "| total_timesteps | 62950 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000275 |\n", + "| n_updates | 3237 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5944 |\n", + "| fps | 158 |\n", + "| time_elapsed | 396 |\n", + "| total_timesteps | 62987 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000774 |\n", + "| n_updates | 3246 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5948 |\n", + "| fps | 158 |\n", + "| time_elapsed | 397 |\n", + "| total_timesteps | 63028 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0215 |\n", + "| n_updates | 3256 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5952 |\n", + "| fps | 158 |\n", + "| time_elapsed | 398 |\n", + "| total_timesteps | 63067 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0189 |\n", + "| n_updates | 3266 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5956 |\n", + "| fps | 158 |\n", + "| time_elapsed | 398 |\n", + "| total_timesteps | 63093 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00636 |\n", + "| n_updates | 3273 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5960 |\n", + "| fps | 158 |\n", + "| time_elapsed | 399 |\n", + "| total_timesteps | 63121 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0013 |\n", + "| n_updates | 3280 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5964 |\n", + "| fps | 157 |\n", + "| time_elapsed | 399 |\n", + "| total_timesteps | 63144 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00092 |\n", + "| n_updates | 3285 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5968 |\n", + "| fps | 157 |\n", + "| time_elapsed | 400 |\n", + "| total_timesteps | 63194 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000617 |\n", + "| n_updates | 3298 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5972 |\n", + "| fps | 157 |\n", + "| time_elapsed | 401 |\n", + "| total_timesteps | 63227 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00822 |\n", + "| n_updates | 3306 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5976 |\n", + "| fps | 157 |\n", + "| time_elapsed | 402 |\n", + "| total_timesteps | 63302 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00135 |\n", + "| n_updates | 3325 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5980 |\n", + "| fps | 156 |\n", + "| time_elapsed | 403 |\n", + "| total_timesteps | 63352 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00193 |\n", + "| n_updates | 3337 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5984 |\n", + "| fps | 156 |\n", + "| time_elapsed | 404 |\n", + "| total_timesteps | 63378 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00244 |\n", + "| n_updates | 3344 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5988 |\n", + "| fps | 156 |\n", + "| time_elapsed | 404 |\n", + "| total_timesteps | 63403 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00368 |\n", + "| n_updates | 3350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5992 |\n", + "| fps | 156 |\n", + "| time_elapsed | 405 |\n", + "| total_timesteps | 63428 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00065 |\n", + "| n_updates | 3356 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 5996 |\n", + "| fps | 156 |\n", + "| time_elapsed | 406 |\n", + "| total_timesteps | 63476 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00841 |\n", + "| n_updates | 3368 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6000 |\n", + "| fps | 156 |\n", + "| time_elapsed | 406 |\n", + "| total_timesteps | 63511 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000538 |\n", + "| n_updates | 3377 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6004 |\n", + "| fps | 155 |\n", + "| time_elapsed | 407 |\n", + "| total_timesteps | 63536 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0139 |\n", + "| n_updates | 3383 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6008 |\n", + "| fps | 155 |\n", + "| time_elapsed | 408 |\n", + "| total_timesteps | 63581 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000496 |\n", + "| n_updates | 3395 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6012 |\n", + "| fps | 155 |\n", + "| time_elapsed | 408 |\n", + "| total_timesteps | 63607 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00176 |\n", + "| n_updates | 3401 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6016 |\n", + "| fps | 155 |\n", + "| time_elapsed | 410 |\n", + "| total_timesteps | 63680 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0113 |\n", + "| n_updates | 3419 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6020 |\n", + "| fps | 154 |\n", + "| time_elapsed | 411 |\n", + "| total_timesteps | 63722 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00866 |\n", + "| n_updates | 3430 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6024 |\n", + "| fps | 154 |\n", + "| time_elapsed | 411 |\n", + "| total_timesteps | 63760 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.011 |\n", + "| n_updates | 3439 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6028 |\n", + "| fps | 154 |\n", + "| time_elapsed | 412 |\n", + "| total_timesteps | 63785 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00012 |\n", + "| n_updates | 3446 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6032 |\n", + "| fps | 154 |\n", + "| time_elapsed | 412 |\n", + "| total_timesteps | 63810 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00188 |\n", + "| n_updates | 3452 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6036 |\n", + "| fps | 154 |\n", + "| time_elapsed | 413 |\n", + "| total_timesteps | 63836 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00184 |\n", + "| n_updates | 3458 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6040 |\n", + "| fps | 154 |\n", + "| time_elapsed | 414 |\n", + "| total_timesteps | 63904 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00545 |\n", + "| n_updates | 3475 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6044 |\n", + "| fps | 153 |\n", + "| time_elapsed | 415 |\n", + "| total_timesteps | 63941 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0024 |\n", + "| n_updates | 3485 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6048 |\n", + "| fps | 153 |\n", + "| time_elapsed | 416 |\n", + "| total_timesteps | 64011 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000353 |\n", + "| n_updates | 3502 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6052 |\n", + "| fps | 153 |\n", + "| time_elapsed | 417 |\n", + "| total_timesteps | 64036 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000892 |\n", + "| n_updates | 3508 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6056 |\n", + "| fps | 153 |\n", + "| time_elapsed | 418 |\n", + "| total_timesteps | 64084 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00268 |\n", + "| n_updates | 3520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6060 |\n", + "| fps | 152 |\n", + "| time_elapsed | 419 |\n", + "| total_timesteps | 64151 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00137 |\n", + "| n_updates | 3537 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6064 |\n", + "| fps | 152 |\n", + "| time_elapsed | 420 |\n", + "| total_timesteps | 64192 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0108 |\n", + "| n_updates | 3547 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6068 |\n", + "| fps | 152 |\n", + "| time_elapsed | 421 |\n", + "| total_timesteps | 64232 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000149 |\n", + "| n_updates | 3557 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6072 |\n", + "| fps | 152 |\n", + "| time_elapsed | 422 |\n", + "| total_timesteps | 64274 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00941 |\n", + "| n_updates | 3568 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6076 |\n", + "| fps | 152 |\n", + "| time_elapsed | 422 |\n", + "| total_timesteps | 64300 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0113 |\n", + "| n_updates | 3574 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6080 |\n", + "| fps | 152 |\n", + "| time_elapsed | 423 |\n", + "| total_timesteps | 64325 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00699 |\n", + "| n_updates | 3581 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6084 |\n", + "| fps | 151 |\n", + "| time_elapsed | 423 |\n", + "| total_timesteps | 64346 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00358 |\n", + "| n_updates | 3586 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6088 |\n", + "| fps | 151 |\n", + "| time_elapsed | 425 |\n", + "| total_timesteps | 64422 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0183 |\n", + "| n_updates | 3605 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6092 |\n", + "| fps | 151 |\n", + "| time_elapsed | 425 |\n", + "| total_timesteps | 64447 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00385 |\n", + "| n_updates | 3611 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6096 |\n", + "| fps | 151 |\n", + "| time_elapsed | 426 |\n", + "| total_timesteps | 64474 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00323 |\n", + "| n_updates | 3618 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6100 |\n", + "| fps | 151 |\n", + "| time_elapsed | 426 |\n", + "| total_timesteps | 64516 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00159 |\n", + "| n_updates | 3628 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6104 |\n", + "| fps | 150 |\n", + "| time_elapsed | 428 |\n", + "| total_timesteps | 64582 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0159 |\n", + "| n_updates | 3645 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6108 |\n", + "| fps | 150 |\n", + "| time_elapsed | 429 |\n", + "| total_timesteps | 64624 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00661 |\n", + "| n_updates | 3655 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6112 |\n", + "| fps | 150 |\n", + "| time_elapsed | 429 |\n", + "| total_timesteps | 64650 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000548 |\n", + "| n_updates | 3662 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6116 |\n", + "| fps | 150 |\n", + "| time_elapsed | 430 |\n", + "| total_timesteps | 64696 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00269 |\n", + "| n_updates | 3673 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6120 |\n", + "| fps | 150 |\n", + "| time_elapsed | 430 |\n", + "| total_timesteps | 64719 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00247 |\n", + "| n_updates | 3679 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6124 |\n", + "| fps | 149 |\n", + "| time_elapsed | 432 |\n", + "| total_timesteps | 64808 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00813 |\n", + "| n_updates | 3701 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6128 |\n", + "| fps | 149 |\n", + "| time_elapsed | 433 |\n", + "| total_timesteps | 64844 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000446 |\n", + "| n_updates | 3710 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6132 |\n", + "| fps | 149 |\n", + "| time_elapsed | 434 |\n", + "| total_timesteps | 64880 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00827 |\n", + "| n_updates | 3719 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6136 |\n", + "| fps | 149 |\n", + "| time_elapsed | 434 |\n", + "| total_timesteps | 64918 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00264 |\n", + "| n_updates | 3729 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6140 |\n", + "| fps | 149 |\n", + "| time_elapsed | 435 |\n", + "| total_timesteps | 64944 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 3.88e-05 |\n", + "| n_updates | 3735 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6144 |\n", + "| fps | 149 |\n", + "| time_elapsed | 436 |\n", + "| total_timesteps | 64980 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0089 |\n", + "| n_updates | 3744 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6148 |\n", + "| fps | 148 |\n", + "| time_elapsed | 436 |\n", + "| total_timesteps | 65007 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00994 |\n", + "| n_updates | 3751 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6152 |\n", + "| fps | 148 |\n", + "| time_elapsed | 437 |\n", + "| total_timesteps | 65033 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000749 |\n", + "| n_updates | 3758 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6156 |\n", + "| fps | 148 |\n", + "| time_elapsed | 437 |\n", + "| total_timesteps | 65059 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0153 |\n", + "| n_updates | 3764 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6160 |\n", + "| fps | 148 |\n", + "| time_elapsed | 439 |\n", + "| total_timesteps | 65142 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00126 |\n", + "| n_updates | 3785 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6164 |\n", + "| fps | 148 |\n", + "| time_elapsed | 440 |\n", + "| total_timesteps | 65210 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00778 |\n", + "| n_updates | 3802 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6168 |\n", + "| fps | 147 |\n", + "| time_elapsed | 441 |\n", + "| total_timesteps | 65268 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00656 |\n", + "| n_updates | 3816 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6172 |\n", + "| fps | 147 |\n", + "| time_elapsed | 442 |\n", + "| total_timesteps | 65313 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00926 |\n", + "| n_updates | 3828 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6176 |\n", + "| fps | 147 |\n", + "| time_elapsed | 443 |\n", + "| total_timesteps | 65337 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00516 |\n", + "| n_updates | 3834 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6180 |\n", + "| fps | 147 |\n", + "| time_elapsed | 443 |\n", + "| total_timesteps | 65374 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0221 |\n", + "| n_updates | 3843 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6184 |\n", + "| fps | 147 |\n", + "| time_elapsed | 444 |\n", + "| total_timesteps | 65408 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000166 |\n", + "| n_updates | 3851 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6188 |\n", + "| fps | 147 |\n", + "| time_elapsed | 445 |\n", + "| total_timesteps | 65441 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 6.5e-05 |\n", + "| n_updates | 3860 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6192 |\n", + "| fps | 146 |\n", + "| time_elapsed | 446 |\n", + "| total_timesteps | 65486 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 8.12e-05 |\n", + "| n_updates | 3871 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6196 |\n", + "| fps | 146 |\n", + "| time_elapsed | 446 |\n", + "| total_timesteps | 65512 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00748 |\n", + "| n_updates | 3877 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6200 |\n", + "| fps | 146 |\n", + "| time_elapsed | 446 |\n", + "| total_timesteps | 65536 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0119 |\n", + "| n_updates | 3883 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6204 |\n", + "| fps | 146 |\n", + "| time_elapsed | 448 |\n", + "| total_timesteps | 65600 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000482 |\n", + "| n_updates | 3899 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6208 |\n", + "| fps | 146 |\n", + "| time_elapsed | 449 |\n", + "| total_timesteps | 65651 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00862 |\n", + "| n_updates | 3912 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6212 |\n", + "| fps | 145 |\n", + "| time_elapsed | 450 |\n", + "| total_timesteps | 65692 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00792 |\n", + "| n_updates | 3922 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6216 |\n", + "| fps | 145 |\n", + "| time_elapsed | 451 |\n", + "| total_timesteps | 65744 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 3.58e-05 |\n", + "| n_updates | 3935 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6220 |\n", + "| fps | 145 |\n", + "| time_elapsed | 453 |\n", + "| total_timesteps | 65825 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0115 |\n", + "| n_updates | 3956 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6224 |\n", + "| fps | 145 |\n", + "| time_elapsed | 453 |\n", + "| total_timesteps | 65874 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000188 |\n", + "| n_updates | 3968 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6228 |\n", + "| fps | 145 |\n", + "| time_elapsed | 454 |\n", + "| total_timesteps | 65907 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 8.19e-05 |\n", + "| n_updates | 3976 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6232 |\n", + "| fps | 144 |\n", + "| time_elapsed | 455 |\n", + "| total_timesteps | 65956 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0165 |\n", + "| n_updates | 3988 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6236 |\n", + "| fps | 144 |\n", + "| time_elapsed | 455 |\n", + "| total_timesteps | 65979 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00377 |\n", + "| n_updates | 3994 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6240 |\n", + "| fps | 144 |\n", + "| time_elapsed | 456 |\n", + "| total_timesteps | 66005 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 6.05e-05 |\n", + "| n_updates | 4001 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6244 |\n", + "| fps | 144 |\n", + "| time_elapsed | 457 |\n", + "| total_timesteps | 66032 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00318 |\n", + "| n_updates | 4007 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6248 |\n", + "| fps | 144 |\n", + "| time_elapsed | 457 |\n", + "| total_timesteps | 66075 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000694 |\n", + "| n_updates | 4018 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6252 |\n", + "| fps | 144 |\n", + "| time_elapsed | 459 |\n", + "| total_timesteps | 66137 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00387 |\n", + "| n_updates | 4034 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6256 |\n", + "| fps | 143 |\n", + "| time_elapsed | 459 |\n", + "| total_timesteps | 66162 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00136 |\n", + "| n_updates | 4040 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6260 |\n", + "| fps | 143 |\n", + "| time_elapsed | 460 |\n", + "| total_timesteps | 66191 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00745 |\n", + "| n_updates | 4047 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6264 |\n", + "| fps | 143 |\n", + "| time_elapsed | 460 |\n", + "| total_timesteps | 66217 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000804 |\n", + "| n_updates | 4054 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6268 |\n", + "| fps | 143 |\n", + "| time_elapsed | 462 |\n", + "| total_timesteps | 66301 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00176 |\n", + "| n_updates | 4075 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6272 |\n", + "| fps | 143 |\n", + "| time_elapsed | 463 |\n", + "| total_timesteps | 66351 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000691 |\n", + "| n_updates | 4087 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6276 |\n", + "| fps | 143 |\n", + "| time_elapsed | 464 |\n", + "| total_timesteps | 66398 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0077 |\n", + "| n_updates | 4099 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6280 |\n", + "| fps | 142 |\n", + "| time_elapsed | 464 |\n", + "| total_timesteps | 66424 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0138 |\n", + "| n_updates | 4105 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6284 |\n", + "| fps | 142 |\n", + "| time_elapsed | 465 |\n", + "| total_timesteps | 66451 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0118 |\n", + "| n_updates | 4112 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6288 |\n", + "| fps | 142 |\n", + "| time_elapsed | 466 |\n", + "| total_timesteps | 66494 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00934 |\n", + "| n_updates | 4123 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6292 |\n", + "| fps | 142 |\n", + "| time_elapsed | 467 |\n", + "| total_timesteps | 66570 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000212 |\n", + "| n_updates | 4142 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6296 |\n", + "| fps | 142 |\n", + "| time_elapsed | 468 |\n", + "| total_timesteps | 66614 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00619 |\n", + "| n_updates | 4153 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6300 |\n", + "| fps | 142 |\n", + "| time_elapsed | 468 |\n", + "| total_timesteps | 66640 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00367 |\n", + "| n_updates | 4159 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6304 |\n", + "| fps | 141 |\n", + "| time_elapsed | 469 |\n", + "| total_timesteps | 66690 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00326 |\n", + "| n_updates | 4172 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6308 |\n", + "| fps | 141 |\n", + "| time_elapsed | 470 |\n", + "| total_timesteps | 66716 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000415 |\n", + "| n_updates | 4178 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6312 |\n", + "| fps | 141 |\n", + "| time_elapsed | 471 |\n", + "| total_timesteps | 66742 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00434 |\n", + "| n_updates | 4185 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6316 |\n", + "| fps | 141 |\n", + "| time_elapsed | 471 |\n", + "| total_timesteps | 66777 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00705 |\n", + "| n_updates | 4194 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6320 |\n", + "| fps | 141 |\n", + "| time_elapsed | 472 |\n", + "| total_timesteps | 66804 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0136 |\n", + "| n_updates | 4200 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6324 |\n", + "| fps | 141 |\n", + "| time_elapsed | 473 |\n", + "| total_timesteps | 66843 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000639 |\n", + "| n_updates | 4210 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6328 |\n", + "| fps | 141 |\n", + "| time_elapsed | 474 |\n", + "| total_timesteps | 66882 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00149 |\n", + "| n_updates | 4220 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6332 |\n", + "| fps | 140 |\n", + "| time_elapsed | 474 |\n", + "| total_timesteps | 66907 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00279 |\n", + "| n_updates | 4226 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6336 |\n", + "| fps | 140 |\n", + "| time_elapsed | 475 |\n", + "| total_timesteps | 66959 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00309 |\n", + "| n_updates | 4239 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6340 |\n", + "| fps | 140 |\n", + "| time_elapsed | 476 |\n", + "| total_timesteps | 66984 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00532 |\n", + "| n_updates | 4245 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6344 |\n", + "| fps | 140 |\n", + "| time_elapsed | 477 |\n", + "| total_timesteps | 67049 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 4.77e-05 |\n", + "| n_updates | 4262 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6348 |\n", + "| fps | 140 |\n", + "| time_elapsed | 478 |\n", + "| total_timesteps | 67091 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00695 |\n", + "| n_updates | 4272 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6352 |\n", + "| fps | 140 |\n", + "| time_elapsed | 479 |\n", + "| total_timesteps | 67115 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0119 |\n", + "| n_updates | 4278 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6356 |\n", + "| fps | 139 |\n", + "| time_elapsed | 480 |\n", + "| total_timesteps | 67177 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 8.99e-05 |\n", + "| n_updates | 4294 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6360 |\n", + "| fps | 139 |\n", + "| time_elapsed | 481 |\n", + "| total_timesteps | 67223 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00447 |\n", + "| n_updates | 4305 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6364 |\n", + "| fps | 139 |\n", + "| time_elapsed | 482 |\n", + "| total_timesteps | 67267 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00785 |\n", + "| n_updates | 4316 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6368 |\n", + "| fps | 139 |\n", + "| time_elapsed | 484 |\n", + "| total_timesteps | 67320 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 7.18e-05 |\n", + "| n_updates | 4329 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6372 |\n", + "| fps | 138 |\n", + "| time_elapsed | 485 |\n", + "| total_timesteps | 67387 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00011 |\n", + "| n_updates | 4346 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6376 |\n", + "| fps | 138 |\n", + "| time_elapsed | 486 |\n", + "| total_timesteps | 67415 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00324 |\n", + "| n_updates | 4353 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6380 |\n", + "| fps | 138 |\n", + "| time_elapsed | 487 |\n", + "| total_timesteps | 67442 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00596 |\n", + "| n_updates | 4360 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6384 |\n", + "| fps | 138 |\n", + "| time_elapsed | 488 |\n", + "| total_timesteps | 67510 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 8.65e-05 |\n", + "| n_updates | 4377 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6388 |\n", + "| fps | 137 |\n", + "| time_elapsed | 490 |\n", + "| total_timesteps | 67599 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00252 |\n", + "| n_updates | 4399 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6392 |\n", + "| fps | 137 |\n", + "| time_elapsed | 491 |\n", + "| total_timesteps | 67655 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000542 |\n", + "| n_updates | 4413 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6396 |\n", + "| fps | 137 |\n", + "| time_elapsed | 492 |\n", + "| total_timesteps | 67704 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000557 |\n", + "| n_updates | 4425 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6400 |\n", + "| fps | 137 |\n", + "| time_elapsed | 493 |\n", + "| total_timesteps | 67738 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00895 |\n", + "| n_updates | 4434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6404 |\n", + "| fps | 137 |\n", + "| time_elapsed | 494 |\n", + "| total_timesteps | 67771 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00778 |\n", + "| n_updates | 4442 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6408 |\n", + "| fps | 136 |\n", + "| time_elapsed | 495 |\n", + "| total_timesteps | 67811 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000716 |\n", + "| n_updates | 4452 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6412 |\n", + "| fps | 136 |\n", + "| time_elapsed | 496 |\n", + "| total_timesteps | 67853 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00856 |\n", + "| n_updates | 4463 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6416 |\n", + "| fps | 136 |\n", + "| time_elapsed | 497 |\n", + "| total_timesteps | 67905 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000319 |\n", + "| n_updates | 4476 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6420 |\n", + "| fps | 136 |\n", + "| time_elapsed | 497 |\n", + "| total_timesteps | 67931 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00796 |\n", + "| n_updates | 4482 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6424 |\n", + "| fps | 136 |\n", + "| time_elapsed | 498 |\n", + "| total_timesteps | 67966 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00258 |\n", + "| n_updates | 4491 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6428 |\n", + "| fps | 136 |\n", + "| time_elapsed | 499 |\n", + "| total_timesteps | 68002 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00327 |\n", + "| n_updates | 4500 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6432 |\n", + "| fps | 136 |\n", + "| time_elapsed | 499 |\n", + "| total_timesteps | 68029 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00113 |\n", + "| n_updates | 4507 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6436 |\n", + "| fps | 135 |\n", + "| time_elapsed | 500 |\n", + "| total_timesteps | 68077 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00029 |\n", + "| n_updates | 4519 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6440 |\n", + "| fps | 135 |\n", + "| time_elapsed | 501 |\n", + "| total_timesteps | 68104 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0163 |\n", + "| n_updates | 4525 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6444 |\n", + "| fps | 135 |\n", + "| time_elapsed | 502 |\n", + "| total_timesteps | 68154 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000143 |\n", + "| n_updates | 4538 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6448 |\n", + "| fps | 135 |\n", + "| time_elapsed | 503 |\n", + "| total_timesteps | 68206 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000797 |\n", + "| n_updates | 4551 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6452 |\n", + "| fps | 135 |\n", + "| time_elapsed | 504 |\n", + "| total_timesteps | 68232 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000388 |\n", + "| n_updates | 4557 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6456 |\n", + "| fps | 135 |\n", + "| time_elapsed | 505 |\n", + "| total_timesteps | 68298 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00107 |\n", + "| n_updates | 4574 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6460 |\n", + "| fps | 134 |\n", + "| time_elapsed | 506 |\n", + "| total_timesteps | 68359 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000204 |\n", + "| n_updates | 4589 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6464 |\n", + "| fps | 134 |\n", + "| time_elapsed | 507 |\n", + "| total_timesteps | 68384 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000824 |\n", + "| n_updates | 4595 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6468 |\n", + "| fps | 134 |\n", + "| time_elapsed | 508 |\n", + "| total_timesteps | 68446 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00749 |\n", + "| n_updates | 4611 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6472 |\n", + "| fps | 134 |\n", + "| time_elapsed | 509 |\n", + "| total_timesteps | 68508 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 7.78e-05 |\n", + "| n_updates | 4626 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6476 |\n", + "| fps | 134 |\n", + "| time_elapsed | 510 |\n", + "| total_timesteps | 68553 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00281 |\n", + "| n_updates | 4638 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6480 |\n", + "| fps | 134 |\n", + "| time_elapsed | 511 |\n", + "| total_timesteps | 68580 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000401 |\n", + "| n_updates | 4644 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6484 |\n", + "| fps | 134 |\n", + "| time_elapsed | 511 |\n", + "| total_timesteps | 68606 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0001 |\n", + "| n_updates | 4651 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6488 |\n", + "| fps | 133 |\n", + "| time_elapsed | 512 |\n", + "| total_timesteps | 68653 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00445 |\n", + "| n_updates | 4663 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6492 |\n", + "| fps | 133 |\n", + "| time_elapsed | 513 |\n", + "| total_timesteps | 68680 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 4.23e-05 |\n", + "| n_updates | 4669 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6496 |\n", + "| fps | 133 |\n", + "| time_elapsed | 514 |\n", + "| total_timesteps | 68733 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00201 |\n", + "| n_updates | 4683 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6500 |\n", + "| fps | 133 |\n", + "| time_elapsed | 515 |\n", + "| total_timesteps | 68758 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00329 |\n", + "| n_updates | 4689 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6504 |\n", + "| fps | 133 |\n", + "| time_elapsed | 516 |\n", + "| total_timesteps | 68797 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 6.43e-05 |\n", + "| n_updates | 4699 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6508 |\n", + "| fps | 133 |\n", + "| time_elapsed | 516 |\n", + "| total_timesteps | 68820 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000163 |\n", + "| n_updates | 4704 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6512 |\n", + "| fps | 133 |\n", + "| time_elapsed | 517 |\n", + "| total_timesteps | 68859 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000346 |\n", + "| n_updates | 4714 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6516 |\n", + "| fps | 132 |\n", + "| time_elapsed | 518 |\n", + "| total_timesteps | 68935 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0138 |\n", + "| n_updates | 4733 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6520 |\n", + "| fps | 132 |\n", + "| time_elapsed | 520 |\n", + "| total_timesteps | 68993 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00518 |\n", + "| n_updates | 4748 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6524 |\n", + "| fps | 132 |\n", + "| time_elapsed | 521 |\n", + "| total_timesteps | 69043 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0108 |\n", + "| n_updates | 4760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6528 |\n", + "| fps | 132 |\n", + "| time_elapsed | 522 |\n", + "| total_timesteps | 69093 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00652 |\n", + "| n_updates | 4773 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6532 |\n", + "| fps | 132 |\n", + "| time_elapsed | 523 |\n", + "| total_timesteps | 69169 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0133 |\n", + "| n_updates | 4792 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6536 |\n", + "| fps | 131 |\n", + "| time_elapsed | 524 |\n", + "| total_timesteps | 69208 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00131 |\n", + "| n_updates | 4801 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6540 |\n", + "| fps | 131 |\n", + "| time_elapsed | 525 |\n", + "| total_timesteps | 69244 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.014 |\n", + "| n_updates | 4810 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6544 |\n", + "| fps | 131 |\n", + "| time_elapsed | 526 |\n", + "| total_timesteps | 69288 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0167 |\n", + "| n_updates | 4821 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6548 |\n", + "| fps | 131 |\n", + "| time_elapsed | 527 |\n", + "| total_timesteps | 69362 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.01 |\n", + "| n_updates | 4840 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6552 |\n", + "| fps | 131 |\n", + "| time_elapsed | 528 |\n", + "| total_timesteps | 69386 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00958 |\n", + "| n_updates | 4846 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6556 |\n", + "| fps | 131 |\n", + "| time_elapsed | 529 |\n", + "| total_timesteps | 69436 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 5.51e-05 |\n", + "| n_updates | 4858 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6560 |\n", + "| fps | 131 |\n", + "| time_elapsed | 530 |\n", + "| total_timesteps | 69486 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00206 |\n", + "| n_updates | 4871 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6564 |\n", + "| fps | 130 |\n", + "| time_elapsed | 531 |\n", + "| total_timesteps | 69534 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00672 |\n", + "| n_updates | 4883 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6568 |\n", + "| fps | 130 |\n", + "| time_elapsed | 532 |\n", + "| total_timesteps | 69566 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00266 |\n", + "| n_updates | 4891 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6572 |\n", + "| fps | 130 |\n", + "| time_elapsed | 533 |\n", + "| total_timesteps | 69633 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00296 |\n", + "| n_updates | 4908 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6576 |\n", + "| fps | 130 |\n", + "| time_elapsed | 533 |\n", + "| total_timesteps | 69659 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000511 |\n", + "| n_updates | 4914 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6580 |\n", + "| fps | 130 |\n", + "| time_elapsed | 535 |\n", + "| total_timesteps | 69711 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00531 |\n", + "| n_updates | 4927 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6584 |\n", + "| fps | 130 |\n", + "| time_elapsed | 536 |\n", + "| total_timesteps | 69776 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0018 |\n", + "| n_updates | 4943 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6588 |\n", + "| fps | 129 |\n", + "| time_elapsed | 537 |\n", + "| total_timesteps | 69804 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00375 |\n", + "| n_updates | 4950 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6592 |\n", + "| fps | 129 |\n", + "| time_elapsed | 538 |\n", + "| total_timesteps | 69852 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00144 |\n", + "| n_updates | 4962 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6596 |\n", + "| fps | 129 |\n", + "| time_elapsed | 538 |\n", + "| total_timesteps | 69888 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000411 |\n", + "| n_updates | 4971 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6600 |\n", + "| fps | 129 |\n", + "| time_elapsed | 539 |\n", + "| total_timesteps | 69924 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0012 |\n", + "| n_updates | 4980 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6604 |\n", + "| fps | 129 |\n", + "| time_elapsed | 540 |\n", + "| total_timesteps | 69949 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 8e-05 |\n", + "| n_updates | 4987 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6608 |\n", + "| fps | 129 |\n", + "| time_elapsed | 541 |\n", + "| total_timesteps | 70026 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00902 |\n", + "| n_updates | 5006 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6612 |\n", + "| fps | 129 |\n", + "| time_elapsed | 543 |\n", + "| total_timesteps | 70101 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00493 |\n", + "| n_updates | 5025 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6616 |\n", + "| fps | 128 |\n", + "| time_elapsed | 544 |\n", + "| total_timesteps | 70141 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00365 |\n", + "| n_updates | 5035 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6620 |\n", + "| fps | 128 |\n", + "| time_elapsed | 544 |\n", + "| total_timesteps | 70166 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0149 |\n", + "| n_updates | 5041 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6624 |\n", + "| fps | 128 |\n", + "| time_elapsed | 545 |\n", + "| total_timesteps | 70189 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00788 |\n", + "| n_updates | 5047 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6628 |\n", + "| fps | 128 |\n", + "| time_elapsed | 545 |\n", + "| total_timesteps | 70216 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0113 |\n", + "| n_updates | 5053 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6632 |\n", + "| fps | 128 |\n", + "| time_elapsed | 546 |\n", + "| total_timesteps | 70250 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0217 |\n", + "| n_updates | 5062 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6636 |\n", + "| fps | 128 |\n", + "| time_elapsed | 547 |\n", + "| total_timesteps | 70304 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.02 |\n", + "| n_updates | 5075 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6640 |\n", + "| fps | 128 |\n", + "| time_elapsed | 548 |\n", + "| total_timesteps | 70344 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00189 |\n", + "| n_updates | 5085 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6644 |\n", + "| fps | 128 |\n", + "| time_elapsed | 549 |\n", + "| total_timesteps | 70395 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00457 |\n", + "| n_updates | 5098 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6648 |\n", + "| fps | 127 |\n", + "| time_elapsed | 550 |\n", + "| total_timesteps | 70447 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00371 |\n", + "| n_updates | 5111 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6652 |\n", + "| fps | 127 |\n", + "| time_elapsed | 551 |\n", + "| total_timesteps | 70474 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0178 |\n", + "| n_updates | 5118 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6656 |\n", + "| fps | 127 |\n", + "| time_elapsed | 552 |\n", + "| total_timesteps | 70535 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00235 |\n", + "| n_updates | 5133 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6660 |\n", + "| fps | 127 |\n", + "| time_elapsed | 553 |\n", + "| total_timesteps | 70563 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00622 |\n", + "| n_updates | 5140 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6664 |\n", + "| fps | 127 |\n", + "| time_elapsed | 553 |\n", + "| total_timesteps | 70588 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00603 |\n", + "| n_updates | 5146 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6668 |\n", + "| fps | 127 |\n", + "| time_elapsed | 554 |\n", + "| total_timesteps | 70628 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00368 |\n", + "| n_updates | 5156 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6672 |\n", + "| fps | 127 |\n", + "| time_elapsed | 555 |\n", + "| total_timesteps | 70655 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00265 |\n", + "| n_updates | 5163 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6676 |\n", + "| fps | 127 |\n", + "| time_elapsed | 555 |\n", + "| total_timesteps | 70700 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00351 |\n", + "| n_updates | 5174 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6680 |\n", + "| fps | 127 |\n", + "| time_elapsed | 556 |\n", + "| total_timesteps | 70736 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000343 |\n", + "| n_updates | 5183 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6684 |\n", + "| fps | 126 |\n", + "| time_elapsed | 557 |\n", + "| total_timesteps | 70762 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0072 |\n", + "| n_updates | 5190 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6688 |\n", + "| fps | 126 |\n", + "| time_elapsed | 559 |\n", + "| total_timesteps | 70845 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00844 |\n", + "| n_updates | 5211 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6692 |\n", + "| fps | 126 |\n", + "| time_elapsed | 559 |\n", + "| total_timesteps | 70872 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00588 |\n", + "| n_updates | 5217 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6696 |\n", + "| fps | 126 |\n", + "| time_elapsed | 560 |\n", + "| total_timesteps | 70913 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0133 |\n", + "| n_updates | 5228 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6700 |\n", + "| fps | 126 |\n", + "| time_elapsed | 561 |\n", + "| total_timesteps | 70959 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0043 |\n", + "| n_updates | 5239 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6704 |\n", + "| fps | 126 |\n", + "| time_elapsed | 562 |\n", + "| total_timesteps | 71011 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00618 |\n", + "| n_updates | 5252 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6708 |\n", + "| fps | 126 |\n", + "| time_elapsed | 563 |\n", + "| total_timesteps | 71048 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00266 |\n", + "| n_updates | 5261 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6712 |\n", + "| fps | 126 |\n", + "| time_elapsed | 563 |\n", + "| total_timesteps | 71075 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00128 |\n", + "| n_updates | 5268 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6716 |\n", + "| fps | 126 |\n", + "| time_elapsed | 564 |\n", + "| total_timesteps | 71103 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00296 |\n", + "| n_updates | 5275 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6720 |\n", + "| fps | 125 |\n", + "| time_elapsed | 565 |\n", + "| total_timesteps | 71155 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00601 |\n", + "| n_updates | 5288 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6724 |\n", + "| fps | 125 |\n", + "| time_elapsed | 565 |\n", + "| total_timesteps | 71181 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00615 |\n", + "| n_updates | 5295 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6728 |\n", + "| fps | 125 |\n", + "| time_elapsed | 566 |\n", + "| total_timesteps | 71208 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00767 |\n", + "| n_updates | 5301 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6732 |\n", + "| fps | 125 |\n", + "| time_elapsed | 567 |\n", + "| total_timesteps | 71258 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00107 |\n", + "| n_updates | 5314 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6736 |\n", + "| fps | 125 |\n", + "| time_elapsed | 568 |\n", + "| total_timesteps | 71308 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0172 |\n", + "| n_updates | 5326 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6740 |\n", + "| fps | 125 |\n", + "| time_elapsed | 569 |\n", + "| total_timesteps | 71361 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0024 |\n", + "| n_updates | 5340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6744 |\n", + "| fps | 125 |\n", + "| time_elapsed | 570 |\n", + "| total_timesteps | 71428 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000107 |\n", + "| n_updates | 5356 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6748 |\n", + "| fps | 124 |\n", + "| time_elapsed | 572 |\n", + "| total_timesteps | 71483 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0153 |\n", + "| n_updates | 5370 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6752 |\n", + "| fps | 124 |\n", + "| time_elapsed | 572 |\n", + "| total_timesteps | 71504 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00319 |\n", + "| n_updates | 5375 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6756 |\n", + "| fps | 124 |\n", + "| time_elapsed | 573 |\n", + "| total_timesteps | 71559 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000103 |\n", + "| n_updates | 5389 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6760 |\n", + "| fps | 124 |\n", + "| time_elapsed | 574 |\n", + "| total_timesteps | 71584 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00718 |\n", + "| n_updates | 5395 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6764 |\n", + "| fps | 124 |\n", + "| time_elapsed | 574 |\n", + "| total_timesteps | 71607 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00358 |\n", + "| n_updates | 5401 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6768 |\n", + "| fps | 124 |\n", + "| time_elapsed | 575 |\n", + "| total_timesteps | 71658 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00186 |\n", + "| n_updates | 5414 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6772 |\n", + "| fps | 124 |\n", + "| time_elapsed | 577 |\n", + "| total_timesteps | 71737 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000623 |\n", + "| n_updates | 5434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6776 |\n", + "| fps | 124 |\n", + "| time_elapsed | 578 |\n", + "| total_timesteps | 71823 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000273 |\n", + "| n_updates | 5455 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6780 |\n", + "| fps | 123 |\n", + "| time_elapsed | 579 |\n", + "| total_timesteps | 71875 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000925 |\n", + "| n_updates | 5468 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6784 |\n", + "| fps | 123 |\n", + "| time_elapsed | 580 |\n", + "| total_timesteps | 71902 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.012 |\n", + "| n_updates | 5475 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6788 |\n", + "| fps | 123 |\n", + "| time_elapsed | 581 |\n", + "| total_timesteps | 71953 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00155 |\n", + "| n_updates | 5488 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6792 |\n", + "| fps | 123 |\n", + "| time_elapsed | 582 |\n", + "| total_timesteps | 71981 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00694 |\n", + "| n_updates | 5495 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6796 |\n", + "| fps | 123 |\n", + "| time_elapsed | 583 |\n", + "| total_timesteps | 72043 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00209 |\n", + "| n_updates | 5510 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6800 |\n", + "| fps | 123 |\n", + "| time_elapsed | 584 |\n", + "| total_timesteps | 72069 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000798 |\n", + "| n_updates | 5517 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6804 |\n", + "| fps | 123 |\n", + "| time_elapsed | 584 |\n", + "| total_timesteps | 72105 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00157 |\n", + "| n_updates | 5526 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6808 |\n", + "| fps | 123 |\n", + "| time_elapsed | 585 |\n", + "| total_timesteps | 72142 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000106 |\n", + "| n_updates | 5535 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6812 |\n", + "| fps | 123 |\n", + "| time_elapsed | 586 |\n", + "| total_timesteps | 72185 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00255 |\n", + "| n_updates | 5546 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6816 |\n", + "| fps | 122 |\n", + "| time_elapsed | 587 |\n", + "| total_timesteps | 72252 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00852 |\n", + "| n_updates | 5562 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6820 |\n", + "| fps | 122 |\n", + "| time_elapsed | 588 |\n", + "| total_timesteps | 72277 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000616 |\n", + "| n_updates | 5569 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6824 |\n", + "| fps | 122 |\n", + "| time_elapsed | 589 |\n", + "| total_timesteps | 72319 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000148 |\n", + "| n_updates | 5579 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6828 |\n", + "| fps | 122 |\n", + "| time_elapsed | 589 |\n", + "| total_timesteps | 72346 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00289 |\n", + "| n_updates | 5586 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6832 |\n", + "| fps | 122 |\n", + "| time_elapsed | 590 |\n", + "| total_timesteps | 72388 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000418 |\n", + "| n_updates | 5596 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6836 |\n", + "| fps | 122 |\n", + "| time_elapsed | 591 |\n", + "| total_timesteps | 72424 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00205 |\n", + "| n_updates | 5605 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6840 |\n", + "| fps | 122 |\n", + "| time_elapsed | 592 |\n", + "| total_timesteps | 72459 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000606 |\n", + "| n_updates | 5614 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6844 |\n", + "| fps | 122 |\n", + "| time_elapsed | 593 |\n", + "| total_timesteps | 72513 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00196 |\n", + "| n_updates | 5628 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6848 |\n", + "| fps | 122 |\n", + "| time_elapsed | 594 |\n", + "| total_timesteps | 72570 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000398 |\n", + "| n_updates | 5642 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6852 |\n", + "| fps | 121 |\n", + "| time_elapsed | 595 |\n", + "| total_timesteps | 72636 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00131 |\n", + "| n_updates | 5658 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6856 |\n", + "| fps | 121 |\n", + "| time_elapsed | 596 |\n", + "| total_timesteps | 72662 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00134 |\n", + "| n_updates | 5665 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6860 |\n", + "| fps | 121 |\n", + "| time_elapsed | 596 |\n", + "| total_timesteps | 72689 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00152 |\n", + "| n_updates | 5672 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6864 |\n", + "| fps | 121 |\n", + "| time_elapsed | 598 |\n", + "| total_timesteps | 72749 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00127 |\n", + "| n_updates | 5687 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6868 |\n", + "| fps | 121 |\n", + "| time_elapsed | 599 |\n", + "| total_timesteps | 72808 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000166 |\n", + "| n_updates | 5701 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6872 |\n", + "| fps | 121 |\n", + "| time_elapsed | 600 |\n", + "| total_timesteps | 72848 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00196 |\n", + "| n_updates | 5711 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6876 |\n", + "| fps | 121 |\n", + "| time_elapsed | 600 |\n", + "| total_timesteps | 72875 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000184 |\n", + "| n_updates | 5718 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6880 |\n", + "| fps | 121 |\n", + "| time_elapsed | 601 |\n", + "| total_timesteps | 72899 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000105 |\n", + "| n_updates | 5724 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6884 |\n", + "| fps | 121 |\n", + "| time_elapsed | 602 |\n", + "| total_timesteps | 72962 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00168 |\n", + "| n_updates | 5740 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6888 |\n", + "| fps | 121 |\n", + "| time_elapsed | 603 |\n", + "| total_timesteps | 72989 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00161 |\n", + "| n_updates | 5747 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6892 |\n", + "| fps | 120 |\n", + "| time_elapsed | 603 |\n", + "| total_timesteps | 73032 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00385 |\n", + "| n_updates | 5757 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6896 |\n", + "| fps | 120 |\n", + "| time_elapsed | 605 |\n", + "| total_timesteps | 73090 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00101 |\n", + "| n_updates | 5772 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6900 |\n", + "| fps | 120 |\n", + "| time_elapsed | 605 |\n", + "| total_timesteps | 73116 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0125 |\n", + "| n_updates | 5778 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6904 |\n", + "| fps | 120 |\n", + "| time_elapsed | 606 |\n", + "| total_timesteps | 73158 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000937 |\n", + "| n_updates | 5789 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6908 |\n", + "| fps | 120 |\n", + "| time_elapsed | 607 |\n", + "| total_timesteps | 73199 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.01 |\n", + "| n_updates | 5799 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6912 |\n", + "| fps | 120 |\n", + "| time_elapsed | 608 |\n", + "| total_timesteps | 73249 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00145 |\n", + "| n_updates | 5812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6916 |\n", + "| fps | 120 |\n", + "| time_elapsed | 609 |\n", + "| total_timesteps | 73277 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000755 |\n", + "| n_updates | 5819 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6920 |\n", + "| fps | 120 |\n", + "| time_elapsed | 609 |\n", + "| total_timesteps | 73311 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00143 |\n", + "| n_updates | 5827 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6924 |\n", + "| fps | 120 |\n", + "| time_elapsed | 610 |\n", + "| total_timesteps | 73346 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 8.07e-05 |\n", + "| n_updates | 5836 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6928 |\n", + "| fps | 119 |\n", + "| time_elapsed | 611 |\n", + "| total_timesteps | 73387 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00113 |\n", + "| n_updates | 5846 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6932 |\n", + "| fps | 119 |\n", + "| time_elapsed | 612 |\n", + "| total_timesteps | 73432 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0017 |\n", + "| n_updates | 5857 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6936 |\n", + "| fps | 119 |\n", + "| time_elapsed | 613 |\n", + "| total_timesteps | 73483 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00076 |\n", + "| n_updates | 5870 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6940 |\n", + "| fps | 119 |\n", + "| time_elapsed | 614 |\n", + "| total_timesteps | 73541 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00311 |\n", + "| n_updates | 5885 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6944 |\n", + "| fps | 119 |\n", + "| time_elapsed | 615 |\n", + "| total_timesteps | 73593 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00152 |\n", + "| n_updates | 5898 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6948 |\n", + "| fps | 119 |\n", + "| time_elapsed | 617 |\n", + "| total_timesteps | 73646 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000873 |\n", + "| n_updates | 5911 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6952 |\n", + "| fps | 119 |\n", + "| time_elapsed | 618 |\n", + "| total_timesteps | 73699 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00168 |\n", + "| n_updates | 5924 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6956 |\n", + "| fps | 119 |\n", + "| time_elapsed | 618 |\n", + "| total_timesteps | 73724 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0013 |\n", + "| n_updates | 5930 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6960 |\n", + "| fps | 119 |\n", + "| time_elapsed | 619 |\n", + "| total_timesteps | 73761 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0106 |\n", + "| n_updates | 5940 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6964 |\n", + "| fps | 118 |\n", + "| time_elapsed | 620 |\n", + "| total_timesteps | 73796 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00293 |\n", + "| n_updates | 5948 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6968 |\n", + "| fps | 118 |\n", + "| time_elapsed | 620 |\n", + "| total_timesteps | 73818 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00618 |\n", + "| n_updates | 5954 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6972 |\n", + "| fps | 118 |\n", + "| time_elapsed | 621 |\n", + "| total_timesteps | 73879 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00194 |\n", + "| n_updates | 5969 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6976 |\n", + "| fps | 118 |\n", + "| time_elapsed | 622 |\n", + "| total_timesteps | 73927 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000228 |\n", + "| n_updates | 5981 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6980 |\n", + "| fps | 118 |\n", + "| time_elapsed | 623 |\n", + "| total_timesteps | 73963 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0135 |\n", + "| n_updates | 5990 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6984 |\n", + "| fps | 118 |\n", + "| time_elapsed | 625 |\n", + "| total_timesteps | 74025 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000325 |\n", + "| n_updates | 6006 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6988 |\n", + "| fps | 118 |\n", + "| time_elapsed | 625 |\n", + "| total_timesteps | 74047 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00104 |\n", + "| n_updates | 6011 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6992 |\n", + "| fps | 118 |\n", + "| time_elapsed | 626 |\n", + "| total_timesteps | 74069 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00612 |\n", + "| n_updates | 6017 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 6996 |\n", + "| fps | 118 |\n", + "| time_elapsed | 626 |\n", + "| total_timesteps | 74108 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000919 |\n", + "| n_updates | 6026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7000 |\n", + "| fps | 118 |\n", + "| time_elapsed | 627 |\n", + "| total_timesteps | 74131 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00232 |\n", + "| n_updates | 6032 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7004 |\n", + "| fps | 118 |\n", + "| time_elapsed | 628 |\n", + "| total_timesteps | 74195 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0067 |\n", + "| n_updates | 6048 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7008 |\n", + "| fps | 117 |\n", + "| time_elapsed | 629 |\n", + "| total_timesteps | 74229 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00229 |\n", + "| n_updates | 6057 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7012 |\n", + "| fps | 117 |\n", + "| time_elapsed | 630 |\n", + "| total_timesteps | 74306 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0122 |\n", + "| n_updates | 6076 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7016 |\n", + "| fps | 117 |\n", + "| time_elapsed | 631 |\n", + "| total_timesteps | 74347 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0237 |\n", + "| n_updates | 6086 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7020 |\n", + "| fps | 117 |\n", + "| time_elapsed | 632 |\n", + "| total_timesteps | 74385 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0122 |\n", + "| n_updates | 6096 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7024 |\n", + "| fps | 117 |\n", + "| time_elapsed | 633 |\n", + "| total_timesteps | 74422 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00142 |\n", + "| n_updates | 6105 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7028 |\n", + "| fps | 117 |\n", + "| time_elapsed | 634 |\n", + "| total_timesteps | 74472 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000135 |\n", + "| n_updates | 6117 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7032 |\n", + "| fps | 117 |\n", + "| time_elapsed | 635 |\n", + "| total_timesteps | 74514 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00652 |\n", + "| n_updates | 6128 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7036 |\n", + "| fps | 117 |\n", + "| time_elapsed | 635 |\n", + "| total_timesteps | 74554 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00356 |\n", + "| n_updates | 6138 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7040 |\n", + "| fps | 117 |\n", + "| time_elapsed | 636 |\n", + "| total_timesteps | 74579 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00391 |\n", + "| n_updates | 6144 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7044 |\n", + "| fps | 116 |\n", + "| time_elapsed | 638 |\n", + "| total_timesteps | 74646 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00661 |\n", + "| n_updates | 6161 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7048 |\n", + "| fps | 116 |\n", + "| time_elapsed | 638 |\n", + "| total_timesteps | 74681 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000431 |\n", + "| n_updates | 6170 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7052 |\n", + "| fps | 116 |\n", + "| time_elapsed | 639 |\n", + "| total_timesteps | 74727 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000167 |\n", + "| n_updates | 6181 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7056 |\n", + "| fps | 116 |\n", + "| time_elapsed | 640 |\n", + "| total_timesteps | 74777 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00328 |\n", + "| n_updates | 6194 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7060 |\n", + "| fps | 116 |\n", + "| time_elapsed | 641 |\n", + "| total_timesteps | 74824 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00324 |\n", + "| n_updates | 6205 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7064 |\n", + "| fps | 116 |\n", + "| time_elapsed | 642 |\n", + "| total_timesteps | 74846 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00505 |\n", + "| n_updates | 6211 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7068 |\n", + "| fps | 116 |\n", + "| time_elapsed | 642 |\n", + "| total_timesteps | 74872 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00736 |\n", + "| n_updates | 6217 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7072 |\n", + "| fps | 116 |\n", + "| time_elapsed | 643 |\n", + "| total_timesteps | 74898 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000761 |\n", + "| n_updates | 6224 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7076 |\n", + "| fps | 116 |\n", + "| time_elapsed | 644 |\n", + "| total_timesteps | 74933 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000977 |\n", + "| n_updates | 6233 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7080 |\n", + "| fps | 116 |\n", + "| time_elapsed | 645 |\n", + "| total_timesteps | 74974 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00149 |\n", + "| n_updates | 6243 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7084 |\n", + "| fps | 116 |\n", + "| time_elapsed | 646 |\n", + "| total_timesteps | 75040 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00111 |\n", + "| n_updates | 6259 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7088 |\n", + "| fps | 116 |\n", + "| time_elapsed | 646 |\n", + "| total_timesteps | 75065 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00145 |\n", + "| n_updates | 6266 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7092 |\n", + "| fps | 115 |\n", + "| time_elapsed | 647 |\n", + "| total_timesteps | 75107 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00125 |\n", + "| n_updates | 6276 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7096 |\n", + "| fps | 115 |\n", + "| time_elapsed | 648 |\n", + "| total_timesteps | 75133 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00138 |\n", + "| n_updates | 6283 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7100 |\n", + "| fps | 115 |\n", + "| time_elapsed | 648 |\n", + "| total_timesteps | 75160 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000793 |\n", + "| n_updates | 6289 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7104 |\n", + "| fps | 115 |\n", + "| time_elapsed | 649 |\n", + "| total_timesteps | 75186 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000722 |\n", + "| n_updates | 6296 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7108 |\n", + "| fps | 115 |\n", + "| time_elapsed | 650 |\n", + "| total_timesteps | 75211 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000491 |\n", + "| n_updates | 6302 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7112 |\n", + "| fps | 115 |\n", + "| time_elapsed | 650 |\n", + "| total_timesteps | 75237 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00303 |\n", + "| n_updates | 6309 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7116 |\n", + "| fps | 115 |\n", + "| time_elapsed | 651 |\n", + "| total_timesteps | 75279 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0106 |\n", + "| n_updates | 6319 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7120 |\n", + "| fps | 115 |\n", + "| time_elapsed | 652 |\n", + "| total_timesteps | 75306 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000588 |\n", + "| n_updates | 6326 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7124 |\n", + "| fps | 115 |\n", + "| time_elapsed | 653 |\n", + "| total_timesteps | 75347 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000974 |\n", + "| n_updates | 6336 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7128 |\n", + "| fps | 115 |\n", + "| time_elapsed | 654 |\n", + "| total_timesteps | 75398 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0111 |\n", + "| n_updates | 6349 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7132 |\n", + "| fps | 115 |\n", + "| time_elapsed | 654 |\n", + "| total_timesteps | 75425 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00183 |\n", + "| n_updates | 6356 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7136 |\n", + "| fps | 115 |\n", + "| time_elapsed | 656 |\n", + "| total_timesteps | 75482 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0143 |\n", + "| n_updates | 6370 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7140 |\n", + "| fps | 114 |\n", + "| time_elapsed | 656 |\n", + "| total_timesteps | 75507 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000283 |\n", + "| n_updates | 6376 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7144 |\n", + "| fps | 114 |\n", + "| time_elapsed | 657 |\n", + "| total_timesteps | 75532 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00585 |\n", + "| n_updates | 6382 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7148 |\n", + "| fps | 114 |\n", + "| time_elapsed | 658 |\n", + "| total_timesteps | 75573 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00224 |\n", + "| n_updates | 6393 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7152 |\n", + "| fps | 114 |\n", + "| time_elapsed | 658 |\n", + "| total_timesteps | 75596 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00629 |\n", + "| n_updates | 6398 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7156 |\n", + "| fps | 114 |\n", + "| time_elapsed | 659 |\n", + "| total_timesteps | 75617 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00129 |\n", + "| n_updates | 6404 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7160 |\n", + "| fps | 114 |\n", + "| time_elapsed | 659 |\n", + "| total_timesteps | 75648 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000734 |\n", + "| n_updates | 6411 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7164 |\n", + "| fps | 114 |\n", + "| time_elapsed | 660 |\n", + "| total_timesteps | 75674 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00114 |\n", + "| n_updates | 6418 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7168 |\n", + "| fps | 114 |\n", + "| time_elapsed | 661 |\n", + "| total_timesteps | 75725 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00219 |\n", + "| n_updates | 6431 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7172 |\n", + "| fps | 114 |\n", + "| time_elapsed | 662 |\n", + "| total_timesteps | 75766 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00246 |\n", + "| n_updates | 6441 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7176 |\n", + "| fps | 114 |\n", + "| time_elapsed | 663 |\n", + "| total_timesteps | 75812 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00156 |\n", + "| n_updates | 6452 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7180 |\n", + "| fps | 114 |\n", + "| time_elapsed | 665 |\n", + "| total_timesteps | 75894 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00132 |\n", + "| n_updates | 6473 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7184 |\n", + "| fps | 113 |\n", + "| time_elapsed | 666 |\n", + "| total_timesteps | 75928 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00109 |\n", + "| n_updates | 6481 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7188 |\n", + "| fps | 113 |\n", + "| time_elapsed | 667 |\n", + "| total_timesteps | 75965 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00155 |\n", + "| n_updates | 6491 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7192 |\n", + "| fps | 113 |\n", + "| time_elapsed | 668 |\n", + "| total_timesteps | 76011 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000912 |\n", + "| n_updates | 6502 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7196 |\n", + "| fps | 113 |\n", + "| time_elapsed | 668 |\n", + "| total_timesteps | 76039 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000831 |\n", + "| n_updates | 6509 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7200 |\n", + "| fps | 113 |\n", + "| time_elapsed | 669 |\n", + "| total_timesteps | 76088 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0101 |\n", + "| n_updates | 6521 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7204 |\n", + "| fps | 113 |\n", + "| time_elapsed | 670 |\n", + "| total_timesteps | 76126 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000465 |\n", + "| n_updates | 6531 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7208 |\n", + "| fps | 113 |\n", + "| time_elapsed | 671 |\n", + "| total_timesteps | 76162 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00641 |\n", + "| n_updates | 6540 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7212 |\n", + "| fps | 113 |\n", + "| time_elapsed | 672 |\n", + "| total_timesteps | 76211 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00494 |\n", + "| n_updates | 6552 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7216 |\n", + "| fps | 113 |\n", + "| time_elapsed | 673 |\n", + "| total_timesteps | 76238 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00113 |\n", + "| n_updates | 6559 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7220 |\n", + "| fps | 113 |\n", + "| time_elapsed | 674 |\n", + "| total_timesteps | 76281 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0012 |\n", + "| n_updates | 6570 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7224 |\n", + "| fps | 112 |\n", + "| time_elapsed | 675 |\n", + "| total_timesteps | 76349 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00499 |\n", + "| n_updates | 6587 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7228 |\n", + "| fps | 112 |\n", + "| time_elapsed | 676 |\n", + "| total_timesteps | 76375 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00162 |\n", + "| n_updates | 6593 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7232 |\n", + "| fps | 112 |\n", + "| time_elapsed | 677 |\n", + "| total_timesteps | 76436 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00196 |\n", + "| n_updates | 6608 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7236 |\n", + "| fps | 112 |\n", + "| time_elapsed | 678 |\n", + "| total_timesteps | 76472 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00588 |\n", + "| n_updates | 6617 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7240 |\n", + "| fps | 112 |\n", + "| time_elapsed | 679 |\n", + "| total_timesteps | 76524 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000281 |\n", + "| n_updates | 6630 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7244 |\n", + "| fps | 112 |\n", + "| time_elapsed | 681 |\n", + "| total_timesteps | 76577 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000892 |\n", + "| n_updates | 6644 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7248 |\n", + "| fps | 112 |\n", + "| time_elapsed | 681 |\n", + "| total_timesteps | 76602 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00161 |\n", + "| n_updates | 6650 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7252 |\n", + "| fps | 112 |\n", + "| time_elapsed | 682 |\n", + "| total_timesteps | 76655 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00461 |\n", + "| n_updates | 6663 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7256 |\n", + "| fps | 112 |\n", + "| time_elapsed | 684 |\n", + "| total_timesteps | 76750 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00853 |\n", + "| n_updates | 6687 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7260 |\n", + "| fps | 111 |\n", + "| time_elapsed | 686 |\n", + "| total_timesteps | 76825 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000117 |\n", + "| n_updates | 6706 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7264 |\n", + "| fps | 111 |\n", + "| time_elapsed | 688 |\n", + "| total_timesteps | 76873 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0143 |\n", + "| n_updates | 6718 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7268 |\n", + "| fps | 111 |\n", + "| time_elapsed | 689 |\n", + "| total_timesteps | 76928 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00299 |\n", + "| n_updates | 6731 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7272 |\n", + "| fps | 111 |\n", + "| time_elapsed | 690 |\n", + "| total_timesteps | 76953 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000283 |\n", + "| n_updates | 6738 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7276 |\n", + "| fps | 111 |\n", + "| time_elapsed | 691 |\n", + "| total_timesteps | 77014 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0011 |\n", + "| n_updates | 6753 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7280 |\n", + "| fps | 111 |\n", + "| time_elapsed | 692 |\n", + "| total_timesteps | 77076 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00827 |\n", + "| n_updates | 6768 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7284 |\n", + "| fps | 111 |\n", + "| time_elapsed | 693 |\n", + "| total_timesteps | 77126 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00267 |\n", + "| n_updates | 6781 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7288 |\n", + "| fps | 111 |\n", + "| time_elapsed | 695 |\n", + "| total_timesteps | 77196 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00746 |\n", + "| n_updates | 6798 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7292 |\n", + "| fps | 110 |\n", + "| time_elapsed | 696 |\n", + "| total_timesteps | 77255 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00109 |\n", + "| n_updates | 6813 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7296 |\n", + "| fps | 110 |\n", + "| time_elapsed | 697 |\n", + "| total_timesteps | 77289 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 6822 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7300 |\n", + "| fps | 110 |\n", + "| time_elapsed | 698 |\n", + "| total_timesteps | 77323 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0072 |\n", + "| n_updates | 6830 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7304 |\n", + "| fps | 110 |\n", + "| time_elapsed | 699 |\n", + "| total_timesteps | 77396 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00568 |\n", + "| n_updates | 6848 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7308 |\n", + "| fps | 110 |\n", + "| time_elapsed | 700 |\n", + "| total_timesteps | 77419 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 8.75e-05 |\n", + "| n_updates | 6854 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7312 |\n", + "| fps | 110 |\n", + "| time_elapsed | 701 |\n", + "| total_timesteps | 77473 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 6.35e-05 |\n", + "| n_updates | 6868 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7316 |\n", + "| fps | 110 |\n", + "| time_elapsed | 703 |\n", + "| total_timesteps | 77540 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00506 |\n", + "| n_updates | 6884 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7320 |\n", + "| fps | 110 |\n", + "| time_elapsed | 704 |\n", + "| total_timesteps | 77596 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000309 |\n", + "| n_updates | 6898 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7324 |\n", + "| fps | 110 |\n", + "| time_elapsed | 705 |\n", + "| total_timesteps | 77622 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00435 |\n", + "| n_updates | 6905 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7328 |\n", + "| fps | 109 |\n", + "| time_elapsed | 706 |\n", + "| total_timesteps | 77649 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00166 |\n", + "| n_updates | 6912 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7332 |\n", + "| fps | 109 |\n", + "| time_elapsed | 707 |\n", + "| total_timesteps | 77692 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00451 |\n", + "| n_updates | 6922 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7336 |\n", + "| fps | 109 |\n", + "| time_elapsed | 708 |\n", + "| total_timesteps | 77735 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000195 |\n", + "| n_updates | 6933 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7340 |\n", + "| fps | 109 |\n", + "| time_elapsed | 709 |\n", + "| total_timesteps | 77776 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00408 |\n", + "| n_updates | 6943 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7344 |\n", + "| fps | 109 |\n", + "| time_elapsed | 710 |\n", + "| total_timesteps | 77828 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000899 |\n", + "| n_updates | 6956 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7348 |\n", + "| fps | 109 |\n", + "| time_elapsed | 711 |\n", + "| total_timesteps | 77887 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00679 |\n", + "| n_updates | 6971 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7352 |\n", + "| fps | 109 |\n", + "| time_elapsed | 712 |\n", + "| total_timesteps | 77933 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000268 |\n", + "| n_updates | 6983 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7356 |\n", + "| fps | 109 |\n", + "| time_elapsed | 712 |\n", + "| total_timesteps | 77958 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000829 |\n", + "| n_updates | 6989 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7360 |\n", + "| fps | 109 |\n", + "| time_elapsed | 713 |\n", + "| total_timesteps | 77985 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000708 |\n", + "| n_updates | 6996 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7364 |\n", + "| fps | 109 |\n", + "| time_elapsed | 714 |\n", + "| total_timesteps | 78018 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000707 |\n", + "| n_updates | 7004 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7368 |\n", + "| fps | 109 |\n", + "| time_elapsed | 714 |\n", + "| total_timesteps | 78043 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 4.5e-05 |\n", + "| n_updates | 7010 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7372 |\n", + "| fps | 109 |\n", + "| time_elapsed | 716 |\n", + "| total_timesteps | 78140 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00134 |\n", + "| n_updates | 7034 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7376 |\n", + "| fps | 108 |\n", + "| time_elapsed | 717 |\n", + "| total_timesteps | 78182 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00107 |\n", + "| n_updates | 7045 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7380 |\n", + "| fps | 108 |\n", + "| time_elapsed | 718 |\n", + "| total_timesteps | 78220 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000923 |\n", + "| n_updates | 7054 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7384 |\n", + "| fps | 108 |\n", + "| time_elapsed | 719 |\n", + "| total_timesteps | 78254 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000221 |\n", + "| n_updates | 7063 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7388 |\n", + "| fps | 108 |\n", + "| time_elapsed | 720 |\n", + "| total_timesteps | 78315 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0206 |\n", + "| n_updates | 7078 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7392 |\n", + "| fps | 108 |\n", + "| time_elapsed | 721 |\n", + "| total_timesteps | 78351 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00328 |\n", + "| n_updates | 7087 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7396 |\n", + "| fps | 108 |\n", + "| time_elapsed | 722 |\n", + "| total_timesteps | 78412 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00157 |\n", + "| n_updates | 7102 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7400 |\n", + "| fps | 108 |\n", + "| time_elapsed | 723 |\n", + "| total_timesteps | 78449 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00915 |\n", + "| n_updates | 7112 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7404 |\n", + "| fps | 108 |\n", + "| time_elapsed | 724 |\n", + "| total_timesteps | 78501 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000126 |\n", + "| n_updates | 7125 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7408 |\n", + "| fps | 108 |\n", + "| time_elapsed | 724 |\n", + "| total_timesteps | 78528 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 8.66e-05 |\n", + "| n_updates | 7131 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7412 |\n", + "| fps | 108 |\n", + "| time_elapsed | 725 |\n", + "| total_timesteps | 78577 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00151 |\n", + "| n_updates | 7144 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7416 |\n", + "| fps | 108 |\n", + "| time_elapsed | 727 |\n", + "| total_timesteps | 78628 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0106 |\n", + "| n_updates | 7156 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7420 |\n", + "| fps | 108 |\n", + "| time_elapsed | 727 |\n", + "| total_timesteps | 78664 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.016 |\n", + "| n_updates | 7165 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7424 |\n", + "| fps | 107 |\n", + "| time_elapsed | 728 |\n", + "| total_timesteps | 78724 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00833 |\n", + "| n_updates | 7180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7428 |\n", + "| fps | 107 |\n", + "| time_elapsed | 729 |\n", + "| total_timesteps | 78750 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00909 |\n", + "| n_updates | 7187 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7432 |\n", + "| fps | 107 |\n", + "| time_elapsed | 730 |\n", + "| total_timesteps | 78796 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 7.39e-05 |\n", + "| n_updates | 7198 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7436 |\n", + "| fps | 107 |\n", + "| time_elapsed | 732 |\n", + "| total_timesteps | 78898 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00462 |\n", + "| n_updates | 7224 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7440 |\n", + "| fps | 107 |\n", + "| time_elapsed | 733 |\n", + "| total_timesteps | 78949 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0277 |\n", + "| n_updates | 7237 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7444 |\n", + "| fps | 107 |\n", + "| time_elapsed | 734 |\n", + "| total_timesteps | 79014 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000972 |\n", + "| n_updates | 7253 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7448 |\n", + "| fps | 107 |\n", + "| time_elapsed | 735 |\n", + "| total_timesteps | 79053 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0117 |\n", + "| n_updates | 7263 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7452 |\n", + "| fps | 107 |\n", + "| time_elapsed | 736 |\n", + "| total_timesteps | 79080 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00808 |\n", + "| n_updates | 7269 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7456 |\n", + "| fps | 107 |\n", + "| time_elapsed | 736 |\n", + "| total_timesteps | 79107 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000795 |\n", + "| n_updates | 7276 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7460 |\n", + "| fps | 107 |\n", + "| time_elapsed | 737 |\n", + "| total_timesteps | 79136 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00844 |\n", + "| n_updates | 7283 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7464 |\n", + "| fps | 107 |\n", + "| time_elapsed | 738 |\n", + "| total_timesteps | 79185 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000864 |\n", + "| n_updates | 7296 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7468 |\n", + "| fps | 107 |\n", + "| time_elapsed | 739 |\n", + "| total_timesteps | 79254 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000706 |\n", + "| n_updates | 7313 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7472 |\n", + "| fps | 107 |\n", + "| time_elapsed | 740 |\n", + "| total_timesteps | 79287 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00157 |\n", + "| n_updates | 7321 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7476 |\n", + "| fps | 106 |\n", + "| time_elapsed | 741 |\n", + "| total_timesteps | 79325 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000501 |\n", + "| n_updates | 7331 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7480 |\n", + "| fps | 106 |\n", + "| time_elapsed | 742 |\n", + "| total_timesteps | 79360 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 9.34e-05 |\n", + "| n_updates | 7339 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7484 |\n", + "| fps | 106 |\n", + "| time_elapsed | 742 |\n", + "| total_timesteps | 79386 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000505 |\n", + "| n_updates | 7346 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7488 |\n", + "| fps | 106 |\n", + "| time_elapsed | 743 |\n", + "| total_timesteps | 79423 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000727 |\n", + "| n_updates | 7355 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7492 |\n", + "| fps | 106 |\n", + "| time_elapsed | 744 |\n", + "| total_timesteps | 79450 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00153 |\n", + "| n_updates | 7362 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7496 |\n", + "| fps | 106 |\n", + "| time_elapsed | 744 |\n", + "| total_timesteps | 79476 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000583 |\n", + "| n_updates | 7368 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7500 |\n", + "| fps | 106 |\n", + "| time_elapsed | 746 |\n", + "| total_timesteps | 79546 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00191 |\n", + "| n_updates | 7386 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7504 |\n", + "| fps | 106 |\n", + "| time_elapsed | 746 |\n", + "| total_timesteps | 79573 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000396 |\n", + "| n_updates | 7393 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7508 |\n", + "| fps | 106 |\n", + "| time_elapsed | 747 |\n", + "| total_timesteps | 79625 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00673 |\n", + "| n_updates | 7406 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7512 |\n", + "| fps | 106 |\n", + "| time_elapsed | 748 |\n", + "| total_timesteps | 79651 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000845 |\n", + "| n_updates | 7412 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7516 |\n", + "| fps | 106 |\n", + "| time_elapsed | 749 |\n", + "| total_timesteps | 79676 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00239 |\n", + "| n_updates | 7418 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7520 |\n", + "| fps | 106 |\n", + "| time_elapsed | 750 |\n", + "| total_timesteps | 79742 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00219 |\n", + "| n_updates | 7435 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7524 |\n", + "| fps | 106 |\n", + "| time_elapsed | 751 |\n", + "| total_timesteps | 79793 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000597 |\n", + "| n_updates | 7448 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7528 |\n", + "| fps | 106 |\n", + "| time_elapsed | 752 |\n", + "| total_timesteps | 79836 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0026 |\n", + "| n_updates | 7458 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7532 |\n", + "| fps | 106 |\n", + "| time_elapsed | 752 |\n", + "| total_timesteps | 79861 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00188 |\n", + "| n_updates | 7465 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7536 |\n", + "| fps | 105 |\n", + "| time_elapsed | 754 |\n", + "| total_timesteps | 79935 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000856 |\n", + "| n_updates | 7483 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7540 |\n", + "| fps | 105 |\n", + "| time_elapsed | 755 |\n", + "| total_timesteps | 79962 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00376 |\n", + "| n_updates | 7490 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7544 |\n", + "| fps | 105 |\n", + "| time_elapsed | 756 |\n", + "| total_timesteps | 80014 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0114 |\n", + "| n_updates | 7503 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7548 |\n", + "| fps | 105 |\n", + "| time_elapsed | 756 |\n", + "| total_timesteps | 80041 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0139 |\n", + "| n_updates | 7510 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7552 |\n", + "| fps | 105 |\n", + "| time_elapsed | 758 |\n", + "| total_timesteps | 80094 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00371 |\n", + "| n_updates | 7523 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7556 |\n", + "| fps | 105 |\n", + "| time_elapsed | 758 |\n", + "| total_timesteps | 80117 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00256 |\n", + "| n_updates | 7529 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7560 |\n", + "| fps | 105 |\n", + "| time_elapsed | 759 |\n", + "| total_timesteps | 80168 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00282 |\n", + "| n_updates | 7541 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7564 |\n", + "| fps | 105 |\n", + "| time_elapsed | 760 |\n", + "| total_timesteps | 80193 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00481 |\n", + "| n_updates | 7548 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7568 |\n", + "| fps | 105 |\n", + "| time_elapsed | 761 |\n", + "| total_timesteps | 80249 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00524 |\n", + "| n_updates | 7562 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7572 |\n", + "| fps | 105 |\n", + "| time_elapsed | 762 |\n", + "| total_timesteps | 80291 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00673 |\n", + "| n_updates | 7572 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7576 |\n", + "| fps | 105 |\n", + "| time_elapsed | 763 |\n", + "| total_timesteps | 80343 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00226 |\n", + "| n_updates | 7585 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7580 |\n", + "| fps | 105 |\n", + "| time_elapsed | 765 |\n", + "| total_timesteps | 80420 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00462 |\n", + "| n_updates | 7604 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7584 |\n", + "| fps | 104 |\n", + "| time_elapsed | 766 |\n", + "| total_timesteps | 80485 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000713 |\n", + "| n_updates | 7621 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7588 |\n", + "| fps | 104 |\n", + "| time_elapsed | 767 |\n", + "| total_timesteps | 80535 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00308 |\n", + "| n_updates | 7633 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7592 |\n", + "| fps | 104 |\n", + "| time_elapsed | 769 |\n", + "| total_timesteps | 80613 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00027 |\n", + "| n_updates | 7653 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7596 |\n", + "| fps | 104 |\n", + "| time_elapsed | 771 |\n", + "| total_timesteps | 80673 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00262 |\n", + "| n_updates | 7668 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7600 |\n", + "| fps | 104 |\n", + "| time_elapsed | 771 |\n", + "| total_timesteps | 80697 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0109 |\n", + "| n_updates | 7674 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7604 |\n", + "| fps | 104 |\n", + "| time_elapsed | 772 |\n", + "| total_timesteps | 80733 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00687 |\n", + "| n_updates | 7683 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7608 |\n", + "| fps | 104 |\n", + "| time_elapsed | 773 |\n", + "| total_timesteps | 80785 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0038 |\n", + "| n_updates | 7696 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7612 |\n", + "| fps | 104 |\n", + "| time_elapsed | 774 |\n", + "| total_timesteps | 80835 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00341 |\n", + "| n_updates | 7708 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7616 |\n", + "| fps | 104 |\n", + "| time_elapsed | 776 |\n", + "| total_timesteps | 80897 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00286 |\n", + "| n_updates | 7724 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7620 |\n", + "| fps | 104 |\n", + "| time_elapsed | 776 |\n", + "| total_timesteps | 80933 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00148 |\n", + "| n_updates | 7733 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7624 |\n", + "| fps | 104 |\n", + "| time_elapsed | 777 |\n", + "| total_timesteps | 80957 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00968 |\n", + "| n_updates | 7739 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7628 |\n", + "| fps | 104 |\n", + "| time_elapsed | 778 |\n", + "| total_timesteps | 80982 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0119 |\n", + "| n_updates | 7745 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7632 |\n", + "| fps | 103 |\n", + "| time_elapsed | 779 |\n", + "| total_timesteps | 81038 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00191 |\n", + "| n_updates | 7759 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7636 |\n", + "| fps | 103 |\n", + "| time_elapsed | 780 |\n", + "| total_timesteps | 81097 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00338 |\n", + "| n_updates | 7774 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7640 |\n", + "| fps | 103 |\n", + "| time_elapsed | 781 |\n", + "| total_timesteps | 81149 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00757 |\n", + "| n_updates | 7787 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7644 |\n", + "| fps | 103 |\n", + "| time_elapsed | 782 |\n", + "| total_timesteps | 81174 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.006 |\n", + "| n_updates | 7793 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7648 |\n", + "| fps | 103 |\n", + "| time_elapsed | 783 |\n", + "| total_timesteps | 81223 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00395 |\n", + "| n_updates | 7805 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7652 |\n", + "| fps | 103 |\n", + "| time_elapsed | 784 |\n", + "| total_timesteps | 81264 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00678 |\n", + "| n_updates | 7815 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7656 |\n", + "| fps | 103 |\n", + "| time_elapsed | 785 |\n", + "| total_timesteps | 81316 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00745 |\n", + "| n_updates | 7828 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7660 |\n", + "| fps | 103 |\n", + "| time_elapsed | 785 |\n", + "| total_timesteps | 81341 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00278 |\n", + "| n_updates | 7835 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7664 |\n", + "| fps | 103 |\n", + "| time_elapsed | 786 |\n", + "| total_timesteps | 81391 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00288 |\n", + "| n_updates | 7847 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7668 |\n", + "| fps | 103 |\n", + "| time_elapsed | 787 |\n", + "| total_timesteps | 81430 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00293 |\n", + "| n_updates | 7857 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7672 |\n", + "| fps | 103 |\n", + "| time_elapsed | 788 |\n", + "| total_timesteps | 81478 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00612 |\n", + "| n_updates | 7869 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7676 |\n", + "| fps | 103 |\n", + "| time_elapsed | 789 |\n", + "| total_timesteps | 81533 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00902 |\n", + "| n_updates | 7883 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7680 |\n", + "| fps | 103 |\n", + "| time_elapsed | 791 |\n", + "| total_timesteps | 81603 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000589 |\n", + "| n_updates | 7900 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7684 |\n", + "| fps | 103 |\n", + "| time_elapsed | 792 |\n", + "| total_timesteps | 81654 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0065 |\n", + "| n_updates | 7913 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7688 |\n", + "| fps | 102 |\n", + "| time_elapsed | 793 |\n", + "| total_timesteps | 81682 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0013 |\n", + "| n_updates | 7920 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7692 |\n", + "| fps | 102 |\n", + "| time_elapsed | 793 |\n", + "| total_timesteps | 81709 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00508 |\n", + "| n_updates | 7927 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7696 |\n", + "| fps | 102 |\n", + "| time_elapsed | 794 |\n", + "| total_timesteps | 81758 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00131 |\n", + "| n_updates | 7939 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7700 |\n", + "| fps | 102 |\n", + "| time_elapsed | 795 |\n", + "| total_timesteps | 81782 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00952 |\n", + "| n_updates | 7945 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7704 |\n", + "| fps | 102 |\n", + "| time_elapsed | 796 |\n", + "| total_timesteps | 81808 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00089 |\n", + "| n_updates | 7951 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7708 |\n", + "| fps | 102 |\n", + "| time_elapsed | 796 |\n", + "| total_timesteps | 81831 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00155 |\n", + "| n_updates | 7957 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7712 |\n", + "| fps | 102 |\n", + "| time_elapsed | 797 |\n", + "| total_timesteps | 81875 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0054 |\n", + "| n_updates | 7968 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7716 |\n", + "| fps | 102 |\n", + "| time_elapsed | 798 |\n", + "| total_timesteps | 81900 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000512 |\n", + "| n_updates | 7974 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7720 |\n", + "| fps | 102 |\n", + "| time_elapsed | 799 |\n", + "| total_timesteps | 81950 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00259 |\n", + "| n_updates | 7987 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7724 |\n", + "| fps | 102 |\n", + "| time_elapsed | 799 |\n", + "| total_timesteps | 81974 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00585 |\n", + "| n_updates | 7993 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7728 |\n", + "| fps | 102 |\n", + "| time_elapsed | 800 |\n", + "| total_timesteps | 82000 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000935 |\n", + "| n_updates | 7999 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7732 |\n", + "| fps | 102 |\n", + "| time_elapsed | 802 |\n", + "| total_timesteps | 82078 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00253 |\n", + "| n_updates | 8019 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7736 |\n", + "| fps | 102 |\n", + "| time_elapsed | 802 |\n", + "| total_timesteps | 82121 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00556 |\n", + "| n_updates | 8030 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7740 |\n", + "| fps | 102 |\n", + "| time_elapsed | 803 |\n", + "| total_timesteps | 82162 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00493 |\n", + "| n_updates | 8040 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7744 |\n", + "| fps | 102 |\n", + "| time_elapsed | 804 |\n", + "| total_timesteps | 82189 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000109 |\n", + "| n_updates | 8047 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7748 |\n", + "| fps | 102 |\n", + "| time_elapsed | 805 |\n", + "| total_timesteps | 82230 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00148 |\n", + "| n_updates | 8057 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7752 |\n", + "| fps | 102 |\n", + "| time_elapsed | 806 |\n", + "| total_timesteps | 82272 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00179 |\n", + "| n_updates | 8067 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7756 |\n", + "| fps | 101 |\n", + "| time_elapsed | 807 |\n", + "| total_timesteps | 82315 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00139 |\n", + "| n_updates | 8078 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7760 |\n", + "| fps | 101 |\n", + "| time_elapsed | 807 |\n", + "| total_timesteps | 82342 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00395 |\n", + "| n_updates | 8085 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7764 |\n", + "| fps | 101 |\n", + "| time_elapsed | 808 |\n", + "| total_timesteps | 82368 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00275 |\n", + "| n_updates | 8091 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7768 |\n", + "| fps | 101 |\n", + "| time_elapsed | 808 |\n", + "| total_timesteps | 82396 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00274 |\n", + "| n_updates | 8098 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7772 |\n", + "| fps | 101 |\n", + "| time_elapsed | 810 |\n", + "| total_timesteps | 82462 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00115 |\n", + "| n_updates | 8115 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7776 |\n", + "| fps | 101 |\n", + "| time_elapsed | 811 |\n", + "| total_timesteps | 82528 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00402 |\n", + "| n_updates | 8131 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7780 |\n", + "| fps | 101 |\n", + "| time_elapsed | 812 |\n", + "| total_timesteps | 82570 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00353 |\n", + "| n_updates | 8142 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7784 |\n", + "| fps | 101 |\n", + "| time_elapsed | 813 |\n", + "| total_timesteps | 82609 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00327 |\n", + "| n_updates | 8152 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7788 |\n", + "| fps | 101 |\n", + "| time_elapsed | 814 |\n", + "| total_timesteps | 82664 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00121 |\n", + "| n_updates | 8165 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7792 |\n", + "| fps | 101 |\n", + "| time_elapsed | 815 |\n", + "| total_timesteps | 82691 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000523 |\n", + "| n_updates | 8172 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7796 |\n", + "| fps | 101 |\n", + "| time_elapsed | 816 |\n", + "| total_timesteps | 82741 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000565 |\n", + "| n_updates | 8185 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7800 |\n", + "| fps | 101 |\n", + "| time_elapsed | 817 |\n", + "| total_timesteps | 82795 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00297 |\n", + "| n_updates | 8198 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7804 |\n", + "| fps | 101 |\n", + "| time_elapsed | 817 |\n", + "| total_timesteps | 82822 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0033 |\n", + "| n_updates | 8205 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7808 |\n", + "| fps | 101 |\n", + "| time_elapsed | 818 |\n", + "| total_timesteps | 82848 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000205 |\n", + "| n_updates | 8211 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7812 |\n", + "| fps | 101 |\n", + "| time_elapsed | 819 |\n", + "| total_timesteps | 82876 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000644 |\n", + "| n_updates | 8218 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7816 |\n", + "| fps | 101 |\n", + "| time_elapsed | 819 |\n", + "| total_timesteps | 82902 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00392 |\n", + "| n_updates | 8225 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7820 |\n", + "| fps | 101 |\n", + "| time_elapsed | 820 |\n", + "| total_timesteps | 82928 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00275 |\n", + "| n_updates | 8231 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7824 |\n", + "| fps | 101 |\n", + "| time_elapsed | 821 |\n", + "| total_timesteps | 82955 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0101 |\n", + "| n_updates | 8238 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7828 |\n", + "| fps | 100 |\n", + "| time_elapsed | 822 |\n", + "| total_timesteps | 83032 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0132 |\n", + "| n_updates | 8257 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7832 |\n", + "| fps | 100 |\n", + "| time_elapsed | 823 |\n", + "| total_timesteps | 83059 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00055 |\n", + "| n_updates | 8264 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7836 |\n", + "| fps | 100 |\n", + "| time_elapsed | 824 |\n", + "| total_timesteps | 83109 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0125 |\n", + "| n_updates | 8277 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7840 |\n", + "| fps | 100 |\n", + "| time_elapsed | 825 |\n", + "| total_timesteps | 83132 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00818 |\n", + "| n_updates | 8282 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7844 |\n", + "| fps | 100 |\n", + "| time_elapsed | 825 |\n", + "| total_timesteps | 83171 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00842 |\n", + "| n_updates | 8292 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7848 |\n", + "| fps | 100 |\n", + "| time_elapsed | 826 |\n", + "| total_timesteps | 83210 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00642 |\n", + "| n_updates | 8302 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7852 |\n", + "| fps | 100 |\n", + "| time_elapsed | 827 |\n", + "| total_timesteps | 83245 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000832 |\n", + "| n_updates | 8311 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7856 |\n", + "| fps | 100 |\n", + "| time_elapsed | 828 |\n", + "| total_timesteps | 83269 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00172 |\n", + "| n_updates | 8317 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7860 |\n", + "| fps | 100 |\n", + "| time_elapsed | 829 |\n", + "| total_timesteps | 83321 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0106 |\n", + "| n_updates | 8330 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7864 |\n", + "| fps | 100 |\n", + "| time_elapsed | 830 |\n", + "| total_timesteps | 83388 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00146 |\n", + "| n_updates | 8346 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7868 |\n", + "| fps | 100 |\n", + "| time_elapsed | 831 |\n", + "| total_timesteps | 83415 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0152 |\n", + "| n_updates | 8353 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7872 |\n", + "| fps | 100 |\n", + "| time_elapsed | 832 |\n", + "| total_timesteps | 83456 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000803 |\n", + "| n_updates | 8363 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7876 |\n", + "| fps | 100 |\n", + "| time_elapsed | 833 |\n", + "| total_timesteps | 83499 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000549 |\n", + "| n_updates | 8374 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7880 |\n", + "| fps | 100 |\n", + "| time_elapsed | 833 |\n", + "| total_timesteps | 83526 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00451 |\n", + "| n_updates | 8381 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7884 |\n", + "| fps | 100 |\n", + "| time_elapsed | 834 |\n", + "| total_timesteps | 83567 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000367 |\n", + "| n_updates | 8391 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7888 |\n", + "| fps | 100 |\n", + "| time_elapsed | 835 |\n", + "| total_timesteps | 83625 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000712 |\n", + "| n_updates | 8406 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7892 |\n", + "| fps | 99 |\n", + "| time_elapsed | 836 |\n", + "| total_timesteps | 83682 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000999 |\n", + "| n_updates | 8420 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7896 |\n", + "| fps | 99 |\n", + "| time_elapsed | 837 |\n", + "| total_timesteps | 83705 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00296 |\n", + "| n_updates | 8426 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7900 |\n", + "| fps | 99 |\n", + "| time_elapsed | 838 |\n", + "| total_timesteps | 83762 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00044 |\n", + "| n_updates | 8440 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7904 |\n", + "| fps | 99 |\n", + "| time_elapsed | 839 |\n", + "| total_timesteps | 83787 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00957 |\n", + "| n_updates | 8446 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7908 |\n", + "| fps | 99 |\n", + "| time_elapsed | 840 |\n", + "| total_timesteps | 83867 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00024 |\n", + "| n_updates | 8466 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7912 |\n", + "| fps | 99 |\n", + "| time_elapsed | 842 |\n", + "| total_timesteps | 83939 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00559 |\n", + "| n_updates | 8484 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7916 |\n", + "| fps | 99 |\n", + "| time_elapsed | 843 |\n", + "| total_timesteps | 83981 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00846 |\n", + "| n_updates | 8495 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7920 |\n", + "| fps | 99 |\n", + "| time_elapsed | 843 |\n", + "| total_timesteps | 84009 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00385 |\n", + "| n_updates | 8502 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7924 |\n", + "| fps | 99 |\n", + "| time_elapsed | 844 |\n", + "| total_timesteps | 84037 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00391 |\n", + "| n_updates | 8509 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7928 |\n", + "| fps | 99 |\n", + "| time_elapsed | 844 |\n", + "| total_timesteps | 84063 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00349 |\n", + "| n_updates | 8515 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7932 |\n", + "| fps | 99 |\n", + "| time_elapsed | 845 |\n", + "| total_timesteps | 84114 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00579 |\n", + "| n_updates | 8528 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7936 |\n", + "| fps | 99 |\n", + "| time_elapsed | 846 |\n", + "| total_timesteps | 84165 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00605 |\n", + "| n_updates | 8541 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7940 |\n", + "| fps | 99 |\n", + "| time_elapsed | 849 |\n", + "| total_timesteps | 84265 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00922 |\n", + "| n_updates | 8566 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7944 |\n", + "| fps | 99 |\n", + "| time_elapsed | 850 |\n", + "| total_timesteps | 84315 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00706 |\n", + "| n_updates | 8578 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7948 |\n", + "| fps | 99 |\n", + "| time_elapsed | 850 |\n", + "| total_timesteps | 84342 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00122 |\n", + "| n_updates | 8585 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7952 |\n", + "| fps | 99 |\n", + "| time_elapsed | 851 |\n", + "| total_timesteps | 84369 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00169 |\n", + "| n_updates | 8592 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7956 |\n", + "| fps | 98 |\n", + "| time_elapsed | 853 |\n", + "| total_timesteps | 84447 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00171 |\n", + "| n_updates | 8611 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7960 |\n", + "| fps | 98 |\n", + "| time_elapsed | 853 |\n", + "| total_timesteps | 84474 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000991 |\n", + "| n_updates | 8618 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7964 |\n", + "| fps | 98 |\n", + "| time_elapsed | 854 |\n", + "| total_timesteps | 84510 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000419 |\n", + "| n_updates | 8627 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7968 |\n", + "| fps | 98 |\n", + "| time_elapsed | 854 |\n", + "| total_timesteps | 84535 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0041 |\n", + "| n_updates | 8633 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7972 |\n", + "| fps | 98 |\n", + "| time_elapsed | 855 |\n", + "| total_timesteps | 84562 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00196 |\n", + "| n_updates | 8640 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7976 |\n", + "| fps | 98 |\n", + "| time_elapsed | 856 |\n", + "| total_timesteps | 84601 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00505 |\n", + "| n_updates | 8650 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7980 |\n", + "| fps | 98 |\n", + "| time_elapsed | 857 |\n", + "| total_timesteps | 84640 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00095 |\n", + "| n_updates | 8659 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7984 |\n", + "| fps | 98 |\n", + "| time_elapsed | 857 |\n", + "| total_timesteps | 84665 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000534 |\n", + "| n_updates | 8666 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7988 |\n", + "| fps | 98 |\n", + "| time_elapsed | 859 |\n", + "| total_timesteps | 84748 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00274 |\n", + "| n_updates | 8686 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7992 |\n", + "| fps | 98 |\n", + "| time_elapsed | 860 |\n", + "| total_timesteps | 84804 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00296 |\n", + "| n_updates | 8700 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 7996 |\n", + "| fps | 98 |\n", + "| time_elapsed | 861 |\n", + "| total_timesteps | 84827 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00131 |\n", + "| n_updates | 8706 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8000 |\n", + "| fps | 98 |\n", + "| time_elapsed | 862 |\n", + "| total_timesteps | 84873 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000326 |\n", + "| n_updates | 8718 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8004 |\n", + "| fps | 98 |\n", + "| time_elapsed | 862 |\n", + "| total_timesteps | 84912 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00548 |\n", + "| n_updates | 8727 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8008 |\n", + "| fps | 98 |\n", + "| time_elapsed | 864 |\n", + "| total_timesteps | 84963 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000442 |\n", + "| n_updates | 8740 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8012 |\n", + "| fps | 98 |\n", + "| time_elapsed | 864 |\n", + "| total_timesteps | 84987 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00117 |\n", + "| n_updates | 8746 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8016 |\n", + "| fps | 98 |\n", + "| time_elapsed | 865 |\n", + "| total_timesteps | 85038 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000847 |\n", + "| n_updates | 8759 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8020 |\n", + "| fps | 98 |\n", + "| time_elapsed | 866 |\n", + "| total_timesteps | 85080 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000221 |\n", + "| n_updates | 8769 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8024 |\n", + "| fps | 98 |\n", + "| time_elapsed | 867 |\n", + "| total_timesteps | 85123 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00934 |\n", + "| n_updates | 8780 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8028 |\n", + "| fps | 98 |\n", + "| time_elapsed | 868 |\n", + "| total_timesteps | 85164 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000545 |\n", + "| n_updates | 8790 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8032 |\n", + "| fps | 98 |\n", + "| time_elapsed | 869 |\n", + "| total_timesteps | 85214 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0084 |\n", + "| n_updates | 8803 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8036 |\n", + "| fps | 97 |\n", + "| time_elapsed | 871 |\n", + "| total_timesteps | 85320 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00873 |\n", + "| n_updates | 8829 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8040 |\n", + "| fps | 97 |\n", + "| time_elapsed | 872 |\n", + "| total_timesteps | 85386 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00128 |\n", + "| n_updates | 8846 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8044 |\n", + "| fps | 97 |\n", + "| time_elapsed | 873 |\n", + "| total_timesteps | 85436 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00317 |\n", + "| n_updates | 8858 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8048 |\n", + "| fps | 97 |\n", + "| time_elapsed | 874 |\n", + "| total_timesteps | 85461 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00564 |\n", + "| n_updates | 8865 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8052 |\n", + "| fps | 97 |\n", + "| time_elapsed | 874 |\n", + "| total_timesteps | 85487 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00163 |\n", + "| n_updates | 8871 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8056 |\n", + "| fps | 97 |\n", + "| time_elapsed | 875 |\n", + "| total_timesteps | 85527 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00174 |\n", + "| n_updates | 8881 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8060 |\n", + "| fps | 97 |\n", + "| time_elapsed | 877 |\n", + "| total_timesteps | 85584 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00334 |\n", + "| n_updates | 8895 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8064 |\n", + "| fps | 97 |\n", + "| time_elapsed | 877 |\n", + "| total_timesteps | 85610 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0182 |\n", + "| n_updates | 8902 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8068 |\n", + "| fps | 97 |\n", + "| time_elapsed | 878 |\n", + "| total_timesteps | 85642 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0154 |\n", + "| n_updates | 8910 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8072 |\n", + "| fps | 97 |\n", + "| time_elapsed | 880 |\n", + "| total_timesteps | 85714 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00018 |\n", + "| n_updates | 8928 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8076 |\n", + "| fps | 97 |\n", + "| time_elapsed | 880 |\n", + "| total_timesteps | 85753 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00238 |\n", + "| n_updates | 8938 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8080 |\n", + "| fps | 97 |\n", + "| time_elapsed | 881 |\n", + "| total_timesteps | 85790 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00428 |\n", + "| n_updates | 8947 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8084 |\n", + "| fps | 97 |\n", + "| time_elapsed | 882 |\n", + "| total_timesteps | 85816 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00134 |\n", + "| n_updates | 8953 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8088 |\n", + "| fps | 97 |\n", + "| time_elapsed | 883 |\n", + "| total_timesteps | 85864 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00043 |\n", + "| n_updates | 8965 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8092 |\n", + "| fps | 97 |\n", + "| time_elapsed | 883 |\n", + "| total_timesteps | 85890 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00237 |\n", + "| n_updates | 8972 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8096 |\n", + "| fps | 97 |\n", + "| time_elapsed | 884 |\n", + "| total_timesteps | 85917 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 7.34e-05 |\n", + "| n_updates | 8979 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8100 |\n", + "| fps | 97 |\n", + "| time_elapsed | 885 |\n", + "| total_timesteps | 85968 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00195 |\n", + "| n_updates | 8991 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8104 |\n", + "| fps | 97 |\n", + "| time_elapsed | 886 |\n", + "| total_timesteps | 85995 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000181 |\n", + "| n_updates | 8998 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8108 |\n", + "| fps | 96 |\n", + "| time_elapsed | 887 |\n", + "| total_timesteps | 86037 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00123 |\n", + "| n_updates | 9009 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8112 |\n", + "| fps | 96 |\n", + "| time_elapsed | 888 |\n", + "| total_timesteps | 86092 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00232 |\n", + "| n_updates | 9022 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8116 |\n", + "| fps | 96 |\n", + "| time_elapsed | 889 |\n", + "| total_timesteps | 86159 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0125 |\n", + "| n_updates | 9039 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8120 |\n", + "| fps | 96 |\n", + "| time_elapsed | 890 |\n", + "| total_timesteps | 86185 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00128 |\n", + "| n_updates | 9046 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8124 |\n", + "| fps | 96 |\n", + "| time_elapsed | 890 |\n", + "| total_timesteps | 86211 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00906 |\n", + "| n_updates | 9052 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8128 |\n", + "| fps | 96 |\n", + "| time_elapsed | 891 |\n", + "| total_timesteps | 86237 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000959 |\n", + "| n_updates | 9059 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8132 |\n", + "| fps | 96 |\n", + "| time_elapsed | 891 |\n", + "| total_timesteps | 86261 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0062 |\n", + "| n_updates | 9065 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8136 |\n", + "| fps | 96 |\n", + "| time_elapsed | 892 |\n", + "| total_timesteps | 86284 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00633 |\n", + "| n_updates | 9070 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8140 |\n", + "| fps | 96 |\n", + "| time_elapsed | 893 |\n", + "| total_timesteps | 86358 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000937 |\n", + "| n_updates | 9089 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8144 |\n", + "| fps | 96 |\n", + "| time_elapsed | 894 |\n", + "| total_timesteps | 86398 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000959 |\n", + "| n_updates | 9099 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8148 |\n", + "| fps | 96 |\n", + "| time_elapsed | 895 |\n", + "| total_timesteps | 86462 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00869 |\n", + "| n_updates | 9115 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8152 |\n", + "| fps | 96 |\n", + "| time_elapsed | 896 |\n", + "| total_timesteps | 86489 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00288 |\n", + "| n_updates | 9122 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8156 |\n", + "| fps | 96 |\n", + "| time_elapsed | 896 |\n", + "| total_timesteps | 86515 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000891 |\n", + "| n_updates | 9128 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8160 |\n", + "| fps | 96 |\n", + "| time_elapsed | 897 |\n", + "| total_timesteps | 86557 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0051 |\n", + "| n_updates | 9139 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8164 |\n", + "| fps | 96 |\n", + "| time_elapsed | 898 |\n", + "| total_timesteps | 86583 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00161 |\n", + "| n_updates | 9145 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8168 |\n", + "| fps | 96 |\n", + "| time_elapsed | 898 |\n", + "| total_timesteps | 86608 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0064 |\n", + "| n_updates | 9151 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8172 |\n", + "| fps | 96 |\n", + "| time_elapsed | 900 |\n", + "| total_timesteps | 86681 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000539 |\n", + "| n_updates | 9170 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8176 |\n", + "| fps | 96 |\n", + "| time_elapsed | 900 |\n", + "| total_timesteps | 86708 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0026 |\n", + "| n_updates | 9176 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8180 |\n", + "| fps | 96 |\n", + "| time_elapsed | 902 |\n", + "| total_timesteps | 86757 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00313 |\n", + "| n_updates | 9189 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8184 |\n", + "| fps | 96 |\n", + "| time_elapsed | 902 |\n", + "| total_timesteps | 86798 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00107 |\n", + "| n_updates | 9199 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8188 |\n", + "| fps | 96 |\n", + "| time_elapsed | 903 |\n", + "| total_timesteps | 86825 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00446 |\n", + "| n_updates | 9206 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8192 |\n", + "| fps | 96 |\n", + "| time_elapsed | 904 |\n", + "| total_timesteps | 86885 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00321 |\n", + "| n_updates | 9221 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8196 |\n", + "| fps | 95 |\n", + "| time_elapsed | 905 |\n", + "| total_timesteps | 86929 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00806 |\n", + "| n_updates | 9232 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8200 |\n", + "| fps | 95 |\n", + "| time_elapsed | 906 |\n", + "| total_timesteps | 86955 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000439 |\n", + "| n_updates | 9238 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8204 |\n", + "| fps | 95 |\n", + "| time_elapsed | 907 |\n", + "| total_timesteps | 87020 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0126 |\n", + "| n_updates | 9254 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8208 |\n", + "| fps | 95 |\n", + "| time_elapsed | 908 |\n", + "| total_timesteps | 87060 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0038 |\n", + "| n_updates | 9264 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8212 |\n", + "| fps | 95 |\n", + "| time_elapsed | 909 |\n", + "| total_timesteps | 87084 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000273 |\n", + "| n_updates | 9270 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8216 |\n", + "| fps | 95 |\n", + "| time_elapsed | 910 |\n", + "| total_timesteps | 87124 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000641 |\n", + "| n_updates | 9280 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8220 |\n", + "| fps | 95 |\n", + "| time_elapsed | 910 |\n", + "| total_timesteps | 87150 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00378 |\n", + "| n_updates | 9287 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8224 |\n", + "| fps | 95 |\n", + "| time_elapsed | 911 |\n", + "| total_timesteps | 87175 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00935 |\n", + "| n_updates | 9293 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8228 |\n", + "| fps | 95 |\n", + "| time_elapsed | 911 |\n", + "| total_timesteps | 87203 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000431 |\n", + "| n_updates | 9300 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8232 |\n", + "| fps | 95 |\n", + "| time_elapsed | 912 |\n", + "| total_timesteps | 87231 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00229 |\n", + "| n_updates | 9307 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8236 |\n", + "| fps | 95 |\n", + "| time_elapsed | 912 |\n", + "| total_timesteps | 87257 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00481 |\n", + "| n_updates | 9314 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8240 |\n", + "| fps | 95 |\n", + "| time_elapsed | 913 |\n", + "| total_timesteps | 87294 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000106 |\n", + "| n_updates | 9323 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8244 |\n", + "| fps | 95 |\n", + "| time_elapsed | 914 |\n", + "| total_timesteps | 87344 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00147 |\n", + "| n_updates | 9335 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8248 |\n", + "| fps | 95 |\n", + "| time_elapsed | 915 |\n", + "| total_timesteps | 87366 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00068 |\n", + "| n_updates | 9341 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8252 |\n", + "| fps | 95 |\n", + "| time_elapsed | 916 |\n", + "| total_timesteps | 87441 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0074 |\n", + "| n_updates | 9360 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8256 |\n", + "| fps | 95 |\n", + "| time_elapsed | 918 |\n", + "| total_timesteps | 87510 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000672 |\n", + "| n_updates | 9377 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8260 |\n", + "| fps | 95 |\n", + "| time_elapsed | 918 |\n", + "| total_timesteps | 87536 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000695 |\n", + "| n_updates | 9383 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8264 |\n", + "| fps | 95 |\n", + "| time_elapsed | 919 |\n", + "| total_timesteps | 87561 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00497 |\n", + "| n_updates | 9390 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8268 |\n", + "| fps | 95 |\n", + "| time_elapsed | 919 |\n", + "| total_timesteps | 87587 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00121 |\n", + "| n_updates | 9396 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8272 |\n", + "| fps | 95 |\n", + "| time_elapsed | 920 |\n", + "| total_timesteps | 87637 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0144 |\n", + "| n_updates | 9409 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8276 |\n", + "| fps | 95 |\n", + "| time_elapsed | 921 |\n", + "| total_timesteps | 87662 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00966 |\n", + "| n_updates | 9415 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8280 |\n", + "| fps | 95 |\n", + "| time_elapsed | 922 |\n", + "| total_timesteps | 87686 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0139 |\n", + "| n_updates | 9421 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8284 |\n", + "| fps | 95 |\n", + "| time_elapsed | 922 |\n", + "| total_timesteps | 87710 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000752 |\n", + "| n_updates | 9427 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8288 |\n", + "| fps | 95 |\n", + "| time_elapsed | 923 |\n", + "| total_timesteps | 87732 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00172 |\n", + "| n_updates | 9432 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8292 |\n", + "| fps | 94 |\n", + "| time_elapsed | 924 |\n", + "| total_timesteps | 87793 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000858 |\n", + "| n_updates | 9448 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8296 |\n", + "| fps | 94 |\n", + "| time_elapsed | 925 |\n", + "| total_timesteps | 87848 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00157 |\n", + "| n_updates | 9461 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8300 |\n", + "| fps | 94 |\n", + "| time_elapsed | 926 |\n", + "| total_timesteps | 87885 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00122 |\n", + "| n_updates | 9471 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8304 |\n", + "| fps | 94 |\n", + "| time_elapsed | 927 |\n", + "| total_timesteps | 87958 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00428 |\n", + "| n_updates | 9489 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8308 |\n", + "| fps | 94 |\n", + "| time_elapsed | 928 |\n", + "| total_timesteps | 88004 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00885 |\n", + "| n_updates | 9500 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8312 |\n", + "| fps | 94 |\n", + "| time_elapsed | 929 |\n", + "| total_timesteps | 88045 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000272 |\n", + "| n_updates | 9511 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8316 |\n", + "| fps | 94 |\n", + "| time_elapsed | 930 |\n", + "| total_timesteps | 88071 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000798 |\n", + "| n_updates | 9517 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8320 |\n", + "| fps | 94 |\n", + "| time_elapsed | 930 |\n", + "| total_timesteps | 88103 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000181 |\n", + "| n_updates | 9525 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8324 |\n", + "| fps | 94 |\n", + "| time_elapsed | 931 |\n", + "| total_timesteps | 88129 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00166 |\n", + "| n_updates | 9532 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8328 |\n", + "| fps | 94 |\n", + "| time_elapsed | 932 |\n", + "| total_timesteps | 88179 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0019 |\n", + "| n_updates | 9544 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8332 |\n", + "| fps | 94 |\n", + "| time_elapsed | 933 |\n", + "| total_timesteps | 88231 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00282 |\n", + "| n_updates | 9557 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8336 |\n", + "| fps | 94 |\n", + "| time_elapsed | 935 |\n", + "| total_timesteps | 88309 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000513 |\n", + "| n_updates | 9577 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8340 |\n", + "| fps | 94 |\n", + "| time_elapsed | 935 |\n", + "| total_timesteps | 88348 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00818 |\n", + "| n_updates | 9586 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8344 |\n", + "| fps | 94 |\n", + "| time_elapsed | 936 |\n", + "| total_timesteps | 88390 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00539 |\n", + "| n_updates | 9597 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8348 |\n", + "| fps | 94 |\n", + "| time_elapsed | 937 |\n", + "| total_timesteps | 88442 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00414 |\n", + "| n_updates | 9610 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8352 |\n", + "| fps | 94 |\n", + "| time_elapsed | 938 |\n", + "| total_timesteps | 88495 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00654 |\n", + "| n_updates | 9623 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8356 |\n", + "| fps | 94 |\n", + "| time_elapsed | 939 |\n", + "| total_timesteps | 88520 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00193 |\n", + "| n_updates | 9629 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8360 |\n", + "| fps | 94 |\n", + "| time_elapsed | 940 |\n", + "| total_timesteps | 88545 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0064 |\n", + "| n_updates | 9636 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8364 |\n", + "| fps | 94 |\n", + "| time_elapsed | 941 |\n", + "| total_timesteps | 88612 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000222 |\n", + "| n_updates | 9652 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8368 |\n", + "| fps | 94 |\n", + "| time_elapsed | 942 |\n", + "| total_timesteps | 88664 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0141 |\n", + "| n_updates | 9665 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8372 |\n", + "| fps | 94 |\n", + "| time_elapsed | 942 |\n", + "| total_timesteps | 88690 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00147 |\n", + "| n_updates | 9672 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8376 |\n", + "| fps | 94 |\n", + "| time_elapsed | 944 |\n", + "| total_timesteps | 88741 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000532 |\n", + "| n_updates | 9685 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8380 |\n", + "| fps | 93 |\n", + "| time_elapsed | 944 |\n", + "| total_timesteps | 88766 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00198 |\n", + "| n_updates | 9691 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8384 |\n", + "| fps | 93 |\n", + "| time_elapsed | 945 |\n", + "| total_timesteps | 88834 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000377 |\n", + "| n_updates | 9708 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8388 |\n", + "| fps | 93 |\n", + "| time_elapsed | 946 |\n", + "| total_timesteps | 88885 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00242 |\n", + "| n_updates | 9721 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8392 |\n", + "| fps | 93 |\n", + "| time_elapsed | 947 |\n", + "| total_timesteps | 88924 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0116 |\n", + "| n_updates | 9730 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8396 |\n", + "| fps | 93 |\n", + "| time_elapsed | 948 |\n", + "| total_timesteps | 88982 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000636 |\n", + "| n_updates | 9745 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8400 |\n", + "| fps | 93 |\n", + "| time_elapsed | 950 |\n", + "| total_timesteps | 89046 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00731 |\n", + "| n_updates | 9761 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8404 |\n", + "| fps | 93 |\n", + "| time_elapsed | 950 |\n", + "| total_timesteps | 89073 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000925 |\n", + "| n_updates | 9768 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8408 |\n", + "| fps | 93 |\n", + "| time_elapsed | 951 |\n", + "| total_timesteps | 89100 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00019 |\n", + "| n_updates | 9774 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8412 |\n", + "| fps | 93 |\n", + "| time_elapsed | 951 |\n", + "| total_timesteps | 89128 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0158 |\n", + "| n_updates | 9781 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8416 |\n", + "| fps | 93 |\n", + "| time_elapsed | 952 |\n", + "| total_timesteps | 89154 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00273 |\n", + "| n_updates | 9788 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8420 |\n", + "| fps | 93 |\n", + "| time_elapsed | 953 |\n", + "| total_timesteps | 89194 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00345 |\n", + "| n_updates | 9798 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8424 |\n", + "| fps | 93 |\n", + "| time_elapsed | 954 |\n", + "| total_timesteps | 89230 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00314 |\n", + "| n_updates | 9807 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8428 |\n", + "| fps | 93 |\n", + "| time_elapsed | 954 |\n", + "| total_timesteps | 89270 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00377 |\n", + "| n_updates | 9817 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8432 |\n", + "| fps | 93 |\n", + "| time_elapsed | 955 |\n", + "| total_timesteps | 89320 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00124 |\n", + "| n_updates | 9829 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8436 |\n", + "| fps | 93 |\n", + "| time_elapsed | 956 |\n", + "| total_timesteps | 89363 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00206 |\n", + "| n_updates | 9840 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8440 |\n", + "| fps | 93 |\n", + "| time_elapsed | 958 |\n", + "| total_timesteps | 89420 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00251 |\n", + "| n_updates | 9854 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8444 |\n", + "| fps | 93 |\n", + "| time_elapsed | 958 |\n", + "| total_timesteps | 89463 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 8.22e-05 |\n", + "| n_updates | 9865 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8448 |\n", + "| fps | 93 |\n", + "| time_elapsed | 959 |\n", + "| total_timesteps | 89499 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00237 |\n", + "| n_updates | 9874 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8452 |\n", + "| fps | 93 |\n", + "| time_elapsed | 960 |\n", + "| total_timesteps | 89541 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000766 |\n", + "| n_updates | 9885 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8456 |\n", + "| fps | 93 |\n", + "| time_elapsed | 961 |\n", + "| total_timesteps | 89601 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00504 |\n", + "| n_updates | 9900 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8460 |\n", + "| fps | 93 |\n", + "| time_elapsed | 962 |\n", + "| total_timesteps | 89637 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000346 |\n", + "| n_updates | 9909 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8464 |\n", + "| fps | 93 |\n", + "| time_elapsed | 963 |\n", + "| total_timesteps | 89688 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000548 |\n", + "| n_updates | 9921 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8468 |\n", + "| fps | 93 |\n", + "| time_elapsed | 964 |\n", + "| total_timesteps | 89724 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000743 |\n", + "| n_updates | 9930 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8472 |\n", + "| fps | 93 |\n", + "| time_elapsed | 964 |\n", + "| total_timesteps | 89747 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000692 |\n", + "| n_updates | 9936 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8476 |\n", + "| fps | 92 |\n", + "| time_elapsed | 966 |\n", + "| total_timesteps | 89801 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00152 |\n", + "| n_updates | 9950 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8480 |\n", + "| fps | 92 |\n", + "| time_elapsed | 967 |\n", + "| total_timesteps | 89870 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00119 |\n", + "| n_updates | 9967 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8484 |\n", + "| fps | 92 |\n", + "| time_elapsed | 968 |\n", + "| total_timesteps | 89928 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00179 |\n", + "| n_updates | 9981 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8488 |\n", + "| fps | 92 |\n", + "| time_elapsed | 969 |\n", + "| total_timesteps | 89954 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00316 |\n", + "| n_updates | 9988 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8492 |\n", + "| fps | 92 |\n", + "| time_elapsed | 969 |\n", + "| total_timesteps | 89991 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0106 |\n", + "| n_updates | 9997 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8496 |\n", + "| fps | 92 |\n", + "| time_elapsed | 970 |\n", + "| total_timesteps | 90027 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00192 |\n", + "| n_updates | 10006 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8500 |\n", + "| fps | 92 |\n", + "| time_elapsed | 971 |\n", + "| total_timesteps | 90054 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00362 |\n", + "| n_updates | 10013 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8504 |\n", + "| fps | 92 |\n", + "| time_elapsed | 972 |\n", + "| total_timesteps | 90107 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00488 |\n", + "| n_updates | 10026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8508 |\n", + "| fps | 92 |\n", + "| time_elapsed | 972 |\n", + "| total_timesteps | 90136 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00849 |\n", + "| n_updates | 10033 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8512 |\n", + "| fps | 92 |\n", + "| time_elapsed | 973 |\n", + "| total_timesteps | 90161 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00424 |\n", + "| n_updates | 10040 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8516 |\n", + "| fps | 92 |\n", + "| time_elapsed | 974 |\n", + "| total_timesteps | 90213 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000924 |\n", + "| n_updates | 10053 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8520 |\n", + "| fps | 92 |\n", + "| time_elapsed | 975 |\n", + "| total_timesteps | 90267 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000907 |\n", + "| n_updates | 10066 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8524 |\n", + "| fps | 92 |\n", + "| time_elapsed | 976 |\n", + "| total_timesteps | 90300 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00386 |\n", + "| n_updates | 10074 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8528 |\n", + "| fps | 92 |\n", + "| time_elapsed | 977 |\n", + "| total_timesteps | 90335 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00727 |\n", + "| n_updates | 10083 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8532 |\n", + "| fps | 92 |\n", + "| time_elapsed | 978 |\n", + "| total_timesteps | 90389 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00855 |\n", + "| n_updates | 10097 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8536 |\n", + "| fps | 92 |\n", + "| time_elapsed | 979 |\n", + "| total_timesteps | 90428 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00282 |\n", + "| n_updates | 10106 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8540 |\n", + "| fps | 92 |\n", + "| time_elapsed | 979 |\n", + "| total_timesteps | 90465 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0128 |\n", + "| n_updates | 10116 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8544 |\n", + "| fps | 92 |\n", + "| time_elapsed | 980 |\n", + "| total_timesteps | 90500 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00391 |\n", + "| n_updates | 10124 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8548 |\n", + "| fps | 92 |\n", + "| time_elapsed | 981 |\n", + "| total_timesteps | 90563 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000946 |\n", + "| n_updates | 10140 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8552 |\n", + "| fps | 92 |\n", + "| time_elapsed | 982 |\n", + "| total_timesteps | 90607 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0054 |\n", + "| n_updates | 10151 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8556 |\n", + "| fps | 92 |\n", + "| time_elapsed | 983 |\n", + "| total_timesteps | 90632 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0028 |\n", + "| n_updates | 10157 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8560 |\n", + "| fps | 92 |\n", + "| time_elapsed | 983 |\n", + "| total_timesteps | 90660 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0082 |\n", + "| n_updates | 10164 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8564 |\n", + "| fps | 92 |\n", + "| time_elapsed | 984 |\n", + "| total_timesteps | 90685 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00125 |\n", + "| n_updates | 10171 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8568 |\n", + "| fps | 92 |\n", + "| time_elapsed | 985 |\n", + "| total_timesteps | 90743 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0122 |\n", + "| n_updates | 10185 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8572 |\n", + "| fps | 92 |\n", + "| time_elapsed | 986 |\n", + "| total_timesteps | 90780 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00317 |\n", + "| n_updates | 10194 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8576 |\n", + "| fps | 91 |\n", + "| time_elapsed | 987 |\n", + "| total_timesteps | 90817 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00367 |\n", + "| n_updates | 10204 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8580 |\n", + "| fps | 91 |\n", + "| time_elapsed | 988 |\n", + "| total_timesteps | 90865 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00305 |\n", + "| n_updates | 10216 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8584 |\n", + "| fps | 91 |\n", + "| time_elapsed | 989 |\n", + "| total_timesteps | 90921 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.003 |\n", + "| n_updates | 10230 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8588 |\n", + "| fps | 91 |\n", + "| time_elapsed | 990 |\n", + "| total_timesteps | 90960 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000485 |\n", + "| n_updates | 10239 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8592 |\n", + "| fps | 91 |\n", + "| time_elapsed | 991 |\n", + "| total_timesteps | 91013 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00122 |\n", + "| n_updates | 10253 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8596 |\n", + "| fps | 91 |\n", + "| time_elapsed | 992 |\n", + "| total_timesteps | 91066 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0074 |\n", + "| n_updates | 10266 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8600 |\n", + "| fps | 91 |\n", + "| time_elapsed | 993 |\n", + "| total_timesteps | 91091 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00356 |\n", + "| n_updates | 10272 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8604 |\n", + "| fps | 91 |\n", + "| time_elapsed | 993 |\n", + "| total_timesteps | 91119 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00238 |\n", + "| n_updates | 10279 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8608 |\n", + "| fps | 91 |\n", + "| time_elapsed | 994 |\n", + "| total_timesteps | 91160 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00233 |\n", + "| n_updates | 10289 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8612 |\n", + "| fps | 91 |\n", + "| time_elapsed | 995 |\n", + "| total_timesteps | 91187 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00282 |\n", + "| n_updates | 10296 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8616 |\n", + "| fps | 91 |\n", + "| time_elapsed | 996 |\n", + "| total_timesteps | 91247 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000453 |\n", + "| n_updates | 10311 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8620 |\n", + "| fps | 91 |\n", + "| time_elapsed | 996 |\n", + "| total_timesteps | 91273 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00131 |\n", + "| n_updates | 10318 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8624 |\n", + "| fps | 91 |\n", + "| time_elapsed | 997 |\n", + "| total_timesteps | 91312 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00141 |\n", + "| n_updates | 10327 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8628 |\n", + "| fps | 91 |\n", + "| time_elapsed | 998 |\n", + "| total_timesteps | 91353 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00551 |\n", + "| n_updates | 10338 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8632 |\n", + "| fps | 91 |\n", + "| time_elapsed | 999 |\n", + "| total_timesteps | 91390 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000698 |\n", + "| n_updates | 10347 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8636 |\n", + "| fps | 91 |\n", + "| time_elapsed | 1000 |\n", + "| total_timesteps | 91431 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.017 |\n", + "| n_updates | 10357 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8640 |\n", + "| fps | 91 |\n", + "| time_elapsed | 1001 |\n", + "| total_timesteps | 91471 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00207 |\n", + "| n_updates | 10367 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8644 |\n", + "| fps | 91 |\n", + "| time_elapsed | 1002 |\n", + "| total_timesteps | 91526 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000612 |\n", + "| n_updates | 10381 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8648 |\n", + "| fps | 91 |\n", + "| time_elapsed | 1003 |\n", + "| total_timesteps | 91567 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0125 |\n", + "| n_updates | 10391 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8652 |\n", + "| fps | 91 |\n", + "| time_elapsed | 1004 |\n", + "| total_timesteps | 91627 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00122 |\n", + "| n_updates | 10406 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8656 |\n", + "| fps | 91 |\n", + "| time_elapsed | 1005 |\n", + "| total_timesteps | 91687 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00389 |\n", + "| n_updates | 10421 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8660 |\n", + "| fps | 91 |\n", + "| time_elapsed | 1005 |\n", + "| total_timesteps | 91713 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00236 |\n", + "| n_updates | 10428 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8664 |\n", + "| fps | 91 |\n", + "| time_elapsed | 1006 |\n", + "| total_timesteps | 91739 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00205 |\n", + "| n_updates | 10434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8668 |\n", + "| fps | 91 |\n", + "| time_elapsed | 1007 |\n", + "| total_timesteps | 91811 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00317 |\n", + "| n_updates | 10452 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8672 |\n", + "| fps | 91 |\n", + "| time_elapsed | 1009 |\n", + "| total_timesteps | 91877 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00119 |\n", + "| n_updates | 10469 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8676 |\n", + "| fps | 91 |\n", + "| time_elapsed | 1010 |\n", + "| total_timesteps | 91922 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00611 |\n", + "| n_updates | 10480 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8680 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1010 |\n", + "| total_timesteps | 91948 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00751 |\n", + "| n_updates | 10486 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8684 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1011 |\n", + "| total_timesteps | 91975 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00786 |\n", + "| n_updates | 10493 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8688 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1011 |\n", + "| total_timesteps | 92003 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00168 |\n", + "| n_updates | 10500 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8692 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1012 |\n", + "| total_timesteps | 92029 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00199 |\n", + "| n_updates | 10507 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8696 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1013 |\n", + "| total_timesteps | 92080 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00282 |\n", + "| n_updates | 10519 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8700 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1013 |\n", + "| total_timesteps | 92106 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00133 |\n", + "| n_updates | 10526 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8704 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1014 |\n", + "| total_timesteps | 92132 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000527 |\n", + "| n_updates | 10532 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8708 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1014 |\n", + "| total_timesteps | 92167 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00252 |\n", + "| n_updates | 10541 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8712 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1015 |\n", + "| total_timesteps | 92208 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00723 |\n", + "| n_updates | 10551 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8716 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1016 |\n", + "| total_timesteps | 92235 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00507 |\n", + "| n_updates | 10558 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8720 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1016 |\n", + "| total_timesteps | 92263 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00173 |\n", + "| n_updates | 10565 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8724 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1017 |\n", + "| total_timesteps | 92288 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00969 |\n", + "| n_updates | 10571 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8728 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1018 |\n", + "| total_timesteps | 92332 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00224 |\n", + "| n_updates | 10582 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8732 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1018 |\n", + "| total_timesteps | 92368 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00232 |\n", + "| n_updates | 10591 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8736 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1019 |\n", + "| total_timesteps | 92395 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0215 |\n", + "| n_updates | 10598 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8740 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1020 |\n", + "| total_timesteps | 92435 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00738 |\n", + "| n_updates | 10608 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8744 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1021 |\n", + "| total_timesteps | 92475 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00355 |\n", + "| n_updates | 10618 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8748 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1021 |\n", + "| total_timesteps | 92501 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0018 |\n", + "| n_updates | 10625 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8752 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1022 |\n", + "| total_timesteps | 92528 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0132 |\n", + "| n_updates | 10631 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8756 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1022 |\n", + "| total_timesteps | 92553 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00202 |\n", + "| n_updates | 10638 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8760 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1023 |\n", + "| total_timesteps | 92579 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000519 |\n", + "| n_updates | 10644 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8764 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1023 |\n", + "| total_timesteps | 92611 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0126 |\n", + "| n_updates | 10652 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8768 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1024 |\n", + "| total_timesteps | 92665 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000882 |\n", + "| n_updates | 10666 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8772 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1025 |\n", + "| total_timesteps | 92713 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000665 |\n", + "| n_updates | 10678 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8776 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1026 |\n", + "| total_timesteps | 92752 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00295 |\n", + "| n_updates | 10687 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8780 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1027 |\n", + "| total_timesteps | 92807 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0166 |\n", + "| n_updates | 10701 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8784 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1028 |\n", + "| total_timesteps | 92834 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00247 |\n", + "| n_updates | 10708 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8788 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1028 |\n", + "| total_timesteps | 92862 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0194 |\n", + "| n_updates | 10715 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8792 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1029 |\n", + "| total_timesteps | 92914 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0115 |\n", + "| n_updates | 10728 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8796 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1030 |\n", + "| total_timesteps | 92966 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000976 |\n", + "| n_updates | 10741 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8800 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1031 |\n", + "| total_timesteps | 92991 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00317 |\n", + "| n_updates | 10747 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8804 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1033 |\n", + "| total_timesteps | 93073 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00832 |\n", + "| n_updates | 10768 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8808 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1033 |\n", + "| total_timesteps | 93116 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0033 |\n", + "| n_updates | 10778 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8812 |\n", + "| fps | 90 |\n", + "| time_elapsed | 1034 |\n", + "| total_timesteps | 93159 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00145 |\n", + "| n_updates | 10789 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8816 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1035 |\n", + "| total_timesteps | 93200 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00133 |\n", + "| n_updates | 10799 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8820 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1036 |\n", + "| total_timesteps | 93225 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000385 |\n", + "| n_updates | 10806 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8824 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1036 |\n", + "| total_timesteps | 93252 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00252 |\n", + "| n_updates | 10812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8828 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1038 |\n", + "| total_timesteps | 93339 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00301 |\n", + "| n_updates | 10834 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8832 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1039 |\n", + "| total_timesteps | 93380 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00201 |\n", + "| n_updates | 10844 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8836 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1039 |\n", + "| total_timesteps | 93407 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00141 |\n", + "| n_updates | 10851 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8840 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1040 |\n", + "| total_timesteps | 93453 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000785 |\n", + "| n_updates | 10863 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8844 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1041 |\n", + "| total_timesteps | 93511 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00136 |\n", + "| n_updates | 10877 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8848 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1042 |\n", + "| total_timesteps | 93535 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00573 |\n", + "| n_updates | 10883 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8852 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1043 |\n", + "| total_timesteps | 93578 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0119 |\n", + "| n_updates | 10894 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8856 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1044 |\n", + "| total_timesteps | 93629 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00329 |\n", + "| n_updates | 10907 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8860 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1045 |\n", + "| total_timesteps | 93664 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000739 |\n", + "| n_updates | 10915 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8864 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1045 |\n", + "| total_timesteps | 93690 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00646 |\n", + "| n_updates | 10922 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8868 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1047 |\n", + "| total_timesteps | 93756 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00147 |\n", + "| n_updates | 10938 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8872 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1048 |\n", + "| total_timesteps | 93816 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00114 |\n", + "| n_updates | 10953 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8876 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1049 |\n", + "| total_timesteps | 93859 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000424 |\n", + "| n_updates | 10964 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8880 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1050 |\n", + "| total_timesteps | 93896 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00392 |\n", + "| n_updates | 10973 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8884 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1050 |\n", + "| total_timesteps | 93923 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0048 |\n", + "| n_updates | 10980 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8888 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1051 |\n", + "| total_timesteps | 93947 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00102 |\n", + "| n_updates | 10986 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8892 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1052 |\n", + "| total_timesteps | 93980 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00304 |\n", + "| n_updates | 10994 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8896 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1053 |\n", + "| total_timesteps | 94034 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00127 |\n", + "| n_updates | 11008 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8900 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1054 |\n", + "| total_timesteps | 94077 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0103 |\n", + "| n_updates | 11019 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8904 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1055 |\n", + "| total_timesteps | 94139 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00512 |\n", + "| n_updates | 11034 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8908 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1056 |\n", + "| total_timesteps | 94190 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00244 |\n", + "| n_updates | 11047 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8912 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1057 |\n", + "| total_timesteps | 94218 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00251 |\n", + "| n_updates | 11054 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8916 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1057 |\n", + "| total_timesteps | 94243 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00564 |\n", + "| n_updates | 11060 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8920 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1058 |\n", + "| total_timesteps | 94270 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0112 |\n", + "| n_updates | 11067 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8924 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1058 |\n", + "| total_timesteps | 94296 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0029 |\n", + "| n_updates | 11073 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8928 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1059 |\n", + "| total_timesteps | 94332 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00017 |\n", + "| n_updates | 11082 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8932 |\n", + "| fps | 89 |\n", + "| time_elapsed | 1060 |\n", + "| total_timesteps | 94359 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00419 |\n", + "| n_updates | 11089 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8936 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1060 |\n", + "| total_timesteps | 94385 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00111 |\n", + "| n_updates | 11096 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8940 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1061 |\n", + "| total_timesteps | 94412 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00182 |\n", + "| n_updates | 11102 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8944 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1061 |\n", + "| total_timesteps | 94438 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0017 |\n", + "| n_updates | 11109 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8948 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1062 |\n", + "| total_timesteps | 94466 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0021 |\n", + "| n_updates | 11116 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8952 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1063 |\n", + "| total_timesteps | 94516 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00806 |\n", + "| n_updates | 11128 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8956 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1063 |\n", + "| total_timesteps | 94540 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000249 |\n", + "| n_updates | 11134 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8960 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1064 |\n", + "| total_timesteps | 94576 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00128 |\n", + "| n_updates | 11143 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8964 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1065 |\n", + "| total_timesteps | 94630 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00533 |\n", + "| n_updates | 11157 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8968 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1067 |\n", + "| total_timesteps | 94701 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00408 |\n", + "| n_updates | 11175 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8972 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1068 |\n", + "| total_timesteps | 94746 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00132 |\n", + "| n_updates | 11186 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8976 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1069 |\n", + "| total_timesteps | 94781 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00641 |\n", + "| n_updates | 11195 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8980 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1069 |\n", + "| total_timesteps | 94807 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00134 |\n", + "| n_updates | 11201 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8984 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1070 |\n", + "| total_timesteps | 94833 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00156 |\n", + "| n_updates | 11208 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8988 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1070 |\n", + "| total_timesteps | 94861 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00395 |\n", + "| n_updates | 11215 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8992 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1071 |\n", + "| total_timesteps | 94887 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000926 |\n", + "| n_updates | 11221 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 8996 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1071 |\n", + "| total_timesteps | 94911 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0042 |\n", + "| n_updates | 11227 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9000 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1073 |\n", + "| total_timesteps | 94987 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00801 |\n", + "| n_updates | 11246 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9004 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1073 |\n", + "| total_timesteps | 95014 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0113 |\n", + "| n_updates | 11253 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9008 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1075 |\n", + "| total_timesteps | 95067 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0018 |\n", + "| n_updates | 11266 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9012 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1075 |\n", + "| total_timesteps | 95094 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00621 |\n", + "| n_updates | 11273 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9016 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1076 |\n", + "| total_timesteps | 95121 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00431 |\n", + "| n_updates | 11280 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9020 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1077 |\n", + "| total_timesteps | 95188 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00361 |\n", + "| n_updates | 11296 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9024 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1078 |\n", + "| total_timesteps | 95214 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00489 |\n", + "| n_updates | 11303 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9028 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1079 |\n", + "| total_timesteps | 95257 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00565 |\n", + "| n_updates | 11314 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9032 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1079 |\n", + "| total_timesteps | 95283 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00135 |\n", + "| n_updates | 11320 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9036 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1081 |\n", + "| total_timesteps | 95357 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0062 |\n", + "| n_updates | 11339 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9040 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1082 |\n", + "| total_timesteps | 95414 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00105 |\n", + "| n_updates | 11353 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9044 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1084 |\n", + "| total_timesteps | 95491 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0036 |\n", + "| n_updates | 11372 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9048 |\n", + "| fps | 88 |\n", + "| time_elapsed | 1085 |\n", + "| total_timesteps | 95539 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00749 |\n", + "| n_updates | 11384 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9052 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1086 |\n", + "| total_timesteps | 95562 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.002 |\n", + "| n_updates | 11390 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9056 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1086 |\n", + "| total_timesteps | 95585 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00162 |\n", + "| n_updates | 11396 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9060 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1087 |\n", + "| total_timesteps | 95612 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00235 |\n", + "| n_updates | 11402 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9064 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1087 |\n", + "| total_timesteps | 95637 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00298 |\n", + "| n_updates | 11409 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9068 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1089 |\n", + "| total_timesteps | 95678 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00236 |\n", + "| n_updates | 11419 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9072 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1090 |\n", + "| total_timesteps | 95718 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00176 |\n", + "| n_updates | 11429 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9076 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1091 |\n", + "| total_timesteps | 95767 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0164 |\n", + "| n_updates | 11441 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9080 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1092 |\n", + "| total_timesteps | 95826 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00151 |\n", + "| n_updates | 11456 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9084 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1093 |\n", + "| total_timesteps | 95871 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000385 |\n", + "| n_updates | 11467 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9088 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1094 |\n", + "| total_timesteps | 95894 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00839 |\n", + "| n_updates | 11473 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9092 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1095 |\n", + "| total_timesteps | 95957 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00515 |\n", + "| n_updates | 11489 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9096 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1096 |\n", + "| total_timesteps | 95996 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00473 |\n", + "| n_updates | 11498 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9100 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1097 |\n", + "| total_timesteps | 96034 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00678 |\n", + "| n_updates | 11508 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9104 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1098 |\n", + "| total_timesteps | 96061 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000791 |\n", + "| n_updates | 11515 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9108 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1099 |\n", + "| total_timesteps | 96098 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0037 |\n", + "| n_updates | 11524 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9112 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1099 |\n", + "| total_timesteps | 96125 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00581 |\n", + "| n_updates | 11531 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9116 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1100 |\n", + "| total_timesteps | 96162 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000204 |\n", + "| n_updates | 11540 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9120 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1101 |\n", + "| total_timesteps | 96188 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000151 |\n", + "| n_updates | 11546 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9124 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1102 |\n", + "| total_timesteps | 96230 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000606 |\n", + "| n_updates | 11557 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9128 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1102 |\n", + "| total_timesteps | 96256 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000899 |\n", + "| n_updates | 11563 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9132 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1103 |\n", + "| total_timesteps | 96282 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00201 |\n", + "| n_updates | 11570 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9136 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1104 |\n", + "| total_timesteps | 96356 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000692 |\n", + "| n_updates | 11588 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9140 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1105 |\n", + "| total_timesteps | 96399 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000126 |\n", + "| n_updates | 11599 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9144 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1107 |\n", + "| total_timesteps | 96455 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00867 |\n", + "| n_updates | 11613 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9148 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1107 |\n", + "| total_timesteps | 96479 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0125 |\n", + "| n_updates | 11619 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9152 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1109 |\n", + "| total_timesteps | 96542 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00656 |\n", + "| n_updates | 11635 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9156 |\n", + "| fps | 87 |\n", + "| time_elapsed | 1109 |\n", + "| total_timesteps | 96570 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00267 |\n", + "| n_updates | 11642 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9160 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1110 |\n", + "| total_timesteps | 96597 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00544 |\n", + "| n_updates | 11649 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9164 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1110 |\n", + "| total_timesteps | 96624 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00348 |\n", + "| n_updates | 11655 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9168 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1111 |\n", + "| total_timesteps | 96666 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00245 |\n", + "| n_updates | 11666 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9172 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1113 |\n", + "| total_timesteps | 96725 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00366 |\n", + "| n_updates | 11681 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9176 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1114 |\n", + "| total_timesteps | 96768 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000973 |\n", + "| n_updates | 11691 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9180 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1115 |\n", + "| total_timesteps | 96811 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000388 |\n", + "| n_updates | 11702 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9184 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1116 |\n", + "| total_timesteps | 96856 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00284 |\n", + "| n_updates | 11713 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9188 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1116 |\n", + "| total_timesteps | 96883 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000431 |\n", + "| n_updates | 11720 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9192 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1117 |\n", + "| total_timesteps | 96910 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000486 |\n", + "| n_updates | 11727 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9196 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1118 |\n", + "| total_timesteps | 96937 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00277 |\n", + "| n_updates | 11734 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9200 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1119 |\n", + "| total_timesteps | 96988 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0013 |\n", + "| n_updates | 11746 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9204 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1120 |\n", + "| total_timesteps | 97030 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000828 |\n", + "| n_updates | 11757 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9208 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1120 |\n", + "| total_timesteps | 97057 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00465 |\n", + "| n_updates | 11764 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9212 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1122 |\n", + "| total_timesteps | 97156 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00113 |\n", + "| n_updates | 11788 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9216 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1123 |\n", + "| total_timesteps | 97196 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00411 |\n", + "| n_updates | 11798 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9220 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1124 |\n", + "| total_timesteps | 97222 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00142 |\n", + "| n_updates | 11805 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9224 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1124 |\n", + "| total_timesteps | 97248 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00186 |\n", + "| n_updates | 11811 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9228 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1125 |\n", + "| total_timesteps | 97274 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000846 |\n", + "| n_updates | 11818 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9232 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1126 |\n", + "| total_timesteps | 97333 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0109 |\n", + "| n_updates | 11833 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9236 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1127 |\n", + "| total_timesteps | 97377 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00139 |\n", + "| n_updates | 11844 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9240 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1128 |\n", + "| total_timesteps | 97404 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00101 |\n", + "| n_updates | 11850 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9244 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1129 |\n", + "| total_timesteps | 97456 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00642 |\n", + "| n_updates | 11863 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9248 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1130 |\n", + "| total_timesteps | 97482 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0047 |\n", + "| n_updates | 11870 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9252 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1131 |\n", + "| total_timesteps | 97556 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.012 |\n", + "| n_updates | 11888 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9256 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1132 |\n", + "| total_timesteps | 97582 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0016 |\n", + "| n_updates | 11895 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9260 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1132 |\n", + "| total_timesteps | 97608 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000957 |\n", + "| n_updates | 11901 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9264 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1133 |\n", + "| total_timesteps | 97639 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0104 |\n", + "| n_updates | 11909 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9268 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1134 |\n", + "| total_timesteps | 97697 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00147 |\n", + "| n_updates | 11924 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9272 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1135 |\n", + "| total_timesteps | 97722 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00123 |\n", + "| n_updates | 11930 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9276 |\n", + "| fps | 86 |\n", + "| time_elapsed | 1137 |\n", + "| total_timesteps | 97834 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00065 |\n", + "| n_updates | 11958 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9280 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1138 |\n", + "| total_timesteps | 97885 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00122 |\n", + "| n_updates | 11971 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9284 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1139 |\n", + "| total_timesteps | 97918 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00876 |\n", + "| n_updates | 11979 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9288 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1139 |\n", + "| total_timesteps | 97960 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000887 |\n", + "| n_updates | 11989 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9292 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1140 |\n", + "| total_timesteps | 97986 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000228 |\n", + "| n_updates | 11996 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9296 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1141 |\n", + "| total_timesteps | 98037 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00311 |\n", + "| n_updates | 12009 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9300 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1142 |\n", + "| total_timesteps | 98061 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00209 |\n", + "| n_updates | 12015 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9304 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1142 |\n", + "| total_timesteps | 98087 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00963 |\n", + "| n_updates | 12021 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9308 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1143 |\n", + "| total_timesteps | 98148 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00129 |\n", + "| n_updates | 12036 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9312 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1144 |\n", + "| total_timesteps | 98186 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0031 |\n", + "| n_updates | 12046 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9316 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1145 |\n", + "| total_timesteps | 98229 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00246 |\n", + "| n_updates | 12057 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9320 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1146 |\n", + "| total_timesteps | 98271 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00222 |\n", + "| n_updates | 12067 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9324 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1147 |\n", + "| total_timesteps | 98304 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000452 |\n", + "| n_updates | 12075 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9328 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1147 |\n", + "| total_timesteps | 98326 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00219 |\n", + "| n_updates | 12081 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9332 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1148 |\n", + "| total_timesteps | 98367 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00138 |\n", + "| n_updates | 12091 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9336 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1149 |\n", + "| total_timesteps | 98409 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000284 |\n", + "| n_updates | 12102 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9340 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1150 |\n", + "| total_timesteps | 98479 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00298 |\n", + "| n_updates | 12119 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9344 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1151 |\n", + "| total_timesteps | 98506 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00627 |\n", + "| n_updates | 12126 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9348 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1151 |\n", + "| total_timesteps | 98531 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00597 |\n", + "| n_updates | 12132 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9352 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1152 |\n", + "| total_timesteps | 98574 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00127 |\n", + "| n_updates | 12143 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9356 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1153 |\n", + "| total_timesteps | 98614 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000383 |\n", + "| n_updates | 12153 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9360 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1155 |\n", + "| total_timesteps | 98697 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000716 |\n", + "| n_updates | 12174 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9364 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1156 |\n", + "| total_timesteps | 98756 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00035 |\n", + "| n_updates | 12188 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9368 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1156 |\n", + "| total_timesteps | 98783 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000572 |\n", + "| n_updates | 12195 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9372 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1157 |\n", + "| total_timesteps | 98820 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000761 |\n", + "| n_updates | 12204 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9376 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1158 |\n", + "| total_timesteps | 98854 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00361 |\n", + "| n_updates | 12213 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9380 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1159 |\n", + "| total_timesteps | 98904 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00684 |\n", + "| n_updates | 12225 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9384 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1160 |\n", + "| total_timesteps | 98930 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00371 |\n", + "| n_updates | 12232 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9388 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1160 |\n", + "| total_timesteps | 98966 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00216 |\n", + "| n_updates | 12241 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9392 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1162 |\n", + "| total_timesteps | 99052 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000462 |\n", + "| n_updates | 12262 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9396 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1163 |\n", + "| total_timesteps | 99087 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000327 |\n", + "| n_updates | 12271 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9400 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1164 |\n", + "| total_timesteps | 99110 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000795 |\n", + "| n_updates | 12277 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9404 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1164 |\n", + "| total_timesteps | 99137 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00224 |\n", + "| n_updates | 12284 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9408 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1165 |\n", + "| total_timesteps | 99180 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00345 |\n", + "| n_updates | 12294 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9412 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1166 |\n", + "| total_timesteps | 99220 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00247 |\n", + "| n_updates | 12304 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9416 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1166 |\n", + "| total_timesteps | 99247 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00531 |\n", + "| n_updates | 12311 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9420 |\n", + "| fps | 85 |\n", + "| time_elapsed | 1167 |\n", + "| total_timesteps | 99290 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00319 |\n", + "| n_updates | 12322 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9424 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1168 |\n", + "| total_timesteps | 99336 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00718 |\n", + "| n_updates | 12333 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9428 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1169 |\n", + "| total_timesteps | 99363 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000293 |\n", + "| n_updates | 12340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9432 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1169 |\n", + "| total_timesteps | 99390 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000352 |\n", + "| n_updates | 12347 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9436 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1170 |\n", + "| total_timesteps | 99431 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00137 |\n", + "| n_updates | 12357 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9440 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1171 |\n", + "| total_timesteps | 99456 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00485 |\n", + "| n_updates | 12363 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9444 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1171 |\n", + "| total_timesteps | 99482 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00122 |\n", + "| n_updates | 12370 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9448 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1172 |\n", + "| total_timesteps | 99523 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000757 |\n", + "| n_updates | 12380 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9452 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1173 |\n", + "| total_timesteps | 99567 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00305 |\n", + "| n_updates | 12391 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9456 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1174 |\n", + "| total_timesteps | 99613 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00109 |\n", + "| n_updates | 12403 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9460 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1175 |\n", + "| total_timesteps | 99641 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00246 |\n", + "| n_updates | 12410 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9464 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1175 |\n", + "| total_timesteps | 99683 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00221 |\n", + "| n_updates | 12420 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9468 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1176 |\n", + "| total_timesteps | 99727 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0134 |\n", + "| n_updates | 12431 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9472 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1177 |\n", + "| total_timesteps | 99753 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00202 |\n", + "| n_updates | 12438 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9476 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1177 |\n", + "| total_timesteps | 99779 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0022 |\n", + "| n_updates | 12444 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9480 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1178 |\n", + "| total_timesteps | 99803 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000889 |\n", + "| n_updates | 12450 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9484 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1179 |\n", + "| total_timesteps | 99845 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00378 |\n", + "| n_updates | 12461 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9488 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1180 |\n", + "| total_timesteps | 99888 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00218 |\n", + "| n_updates | 12471 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9492 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1180 |\n", + "| total_timesteps | 99915 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00758 |\n", + "| n_updates | 12478 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9496 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1181 |\n", + "| total_timesteps | 99963 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00144 |\n", + "| n_updates | 12490 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9500 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1183 |\n", + "| total_timesteps | 100020 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0114 |\n", + "| n_updates | 12504 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9504 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1183 |\n", + "| total_timesteps | 100045 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0137 |\n", + "| n_updates | 12511 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9508 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1184 |\n", + "| total_timesteps | 100072 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00635 |\n", + "| n_updates | 12517 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9512 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1185 |\n", + "| total_timesteps | 100113 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00726 |\n", + "| n_updates | 12528 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9516 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1187 |\n", + "| total_timesteps | 100182 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00668 |\n", + "| n_updates | 12545 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9520 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1187 |\n", + "| total_timesteps | 100210 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00247 |\n", + "| n_updates | 12552 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9524 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1189 |\n", + "| total_timesteps | 100267 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00723 |\n", + "| n_updates | 12566 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9528 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1190 |\n", + "| total_timesteps | 100327 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0116 |\n", + "| n_updates | 12581 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9532 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1191 |\n", + "| total_timesteps | 100369 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0116 |\n", + "| n_updates | 12592 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9536 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1192 |\n", + "| total_timesteps | 100421 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00182 |\n", + "| n_updates | 12605 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9540 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1193 |\n", + "| total_timesteps | 100477 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0018 |\n", + "| n_updates | 12619 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9544 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1194 |\n", + "| total_timesteps | 100505 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0274 |\n", + "| n_updates | 12626 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9548 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1194 |\n", + "| total_timesteps | 100529 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00437 |\n", + "| n_updates | 12632 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9552 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1196 |\n", + "| total_timesteps | 100612 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00367 |\n", + "| n_updates | 12652 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9556 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1197 |\n", + "| total_timesteps | 100636 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0108 |\n", + "| n_updates | 12658 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9560 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1197 |\n", + "| total_timesteps | 100663 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00164 |\n", + "| n_updates | 12665 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9564 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1198 |\n", + "| total_timesteps | 100707 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00586 |\n", + "| n_updates | 12676 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9568 |\n", + "| fps | 84 |\n", + "| time_elapsed | 1199 |\n", + "| total_timesteps | 100735 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00976 |\n", + "| n_updates | 12683 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9572 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1199 |\n", + "| total_timesteps | 100761 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000898 |\n", + "| n_updates | 12690 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9576 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1200 |\n", + "| total_timesteps | 100784 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00115 |\n", + "| n_updates | 12695 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9580 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1201 |\n", + "| total_timesteps | 100834 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00359 |\n", + "| n_updates | 12708 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9584 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1202 |\n", + "| total_timesteps | 100893 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00512 |\n", + "| n_updates | 12723 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9588 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1203 |\n", + "| total_timesteps | 100919 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0109 |\n", + "| n_updates | 12729 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9592 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1204 |\n", + "| total_timesteps | 100946 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00198 |\n", + "| n_updates | 12736 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9596 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1204 |\n", + "| total_timesteps | 100972 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0158 |\n", + "| n_updates | 12742 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9600 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1205 |\n", + "| total_timesteps | 101005 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 12751 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9604 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1206 |\n", + "| total_timesteps | 101057 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00913 |\n", + "| n_updates | 12764 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9608 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1207 |\n", + "| total_timesteps | 101082 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00188 |\n", + "| n_updates | 12770 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9612 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1207 |\n", + "| total_timesteps | 101123 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00215 |\n", + "| n_updates | 12780 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9616 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1208 |\n", + "| total_timesteps | 101147 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00191 |\n", + "| n_updates | 12786 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9620 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1210 |\n", + "| total_timesteps | 101227 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00126 |\n", + "| n_updates | 12806 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9624 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1210 |\n", + "| total_timesteps | 101253 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00532 |\n", + "| n_updates | 12813 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9628 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1211 |\n", + "| total_timesteps | 101278 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00672 |\n", + "| n_updates | 12819 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9632 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1211 |\n", + "| total_timesteps | 101304 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00142 |\n", + "| n_updates | 12825 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9636 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1212 |\n", + "| total_timesteps | 101338 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.014 |\n", + "| n_updates | 12834 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9640 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1212 |\n", + "| total_timesteps | 101363 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00568 |\n", + "| n_updates | 12840 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9644 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1213 |\n", + "| total_timesteps | 101386 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000609 |\n", + "| n_updates | 12846 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9648 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1214 |\n", + "| total_timesteps | 101419 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00288 |\n", + "| n_updates | 12854 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9652 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1214 |\n", + "| total_timesteps | 101452 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00576 |\n", + "| n_updates | 12862 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9656 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1215 |\n", + "| total_timesteps | 101478 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00655 |\n", + "| n_updates | 12869 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9660 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1216 |\n", + "| total_timesteps | 101501 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00325 |\n", + "| n_updates | 12875 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9664 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1217 |\n", + "| total_timesteps | 101545 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00189 |\n", + "| n_updates | 12886 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9668 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1217 |\n", + "| total_timesteps | 101580 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00264 |\n", + "| n_updates | 12894 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9672 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1218 |\n", + "| total_timesteps | 101606 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0012 |\n", + "| n_updates | 12901 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9676 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1218 |\n", + "| total_timesteps | 101632 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00221 |\n", + "| n_updates | 12907 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9680 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1220 |\n", + "| total_timesteps | 101685 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0124 |\n", + "| n_updates | 12921 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9684 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1220 |\n", + "| total_timesteps | 101725 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00452 |\n", + "| n_updates | 12931 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9688 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1221 |\n", + "| total_timesteps | 101768 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00136 |\n", + "| n_updates | 12941 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9692 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1222 |\n", + "| total_timesteps | 101795 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00598 |\n", + "| n_updates | 12948 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9696 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1222 |\n", + "| total_timesteps | 101822 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00376 |\n", + "| n_updates | 12955 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9700 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1223 |\n", + "| total_timesteps | 101863 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00193 |\n", + "| n_updates | 12965 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9704 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1224 |\n", + "| total_timesteps | 101898 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00212 |\n", + "| n_updates | 12974 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9708 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1225 |\n", + "| total_timesteps | 101955 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00561 |\n", + "| n_updates | 12988 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9712 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1226 |\n", + "| total_timesteps | 101983 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0026 |\n", + "| n_updates | 12995 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9716 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1226 |\n", + "| total_timesteps | 102011 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00322 |\n", + "| n_updates | 13002 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9720 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1227 |\n", + "| total_timesteps | 102039 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00139 |\n", + "| n_updates | 13009 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9724 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1228 |\n", + "| total_timesteps | 102064 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00542 |\n", + "| n_updates | 13015 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9728 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1228 |\n", + "| total_timesteps | 102092 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0114 |\n", + "| n_updates | 13022 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9732 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1229 |\n", + "| total_timesteps | 102118 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0129 |\n", + "| n_updates | 13029 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9736 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1229 |\n", + "| total_timesteps | 102154 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0041 |\n", + "| n_updates | 13038 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9740 |\n", + "| fps | 83 |\n", + "| time_elapsed | 1231 |\n", + "| total_timesteps | 102207 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000675 |\n", + "| n_updates | 13051 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9744 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1232 |\n", + "| total_timesteps | 102260 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00376 |\n", + "| n_updates | 13064 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9748 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1232 |\n", + "| total_timesteps | 102286 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00563 |\n", + "| n_updates | 13071 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9752 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1233 |\n", + "| total_timesteps | 102323 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00542 |\n", + "| n_updates | 13080 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9756 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1234 |\n", + "| total_timesteps | 102382 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0167 |\n", + "| n_updates | 13095 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9760 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1235 |\n", + "| total_timesteps | 102407 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00225 |\n", + "| n_updates | 13101 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9764 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1236 |\n", + "| total_timesteps | 102434 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0154 |\n", + "| n_updates | 13108 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9768 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1236 |\n", + "| total_timesteps | 102476 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.012 |\n", + "| n_updates | 13118 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9772 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1237 |\n", + "| total_timesteps | 102517 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00177 |\n", + "| n_updates | 13129 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.12 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9776 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1238 |\n", + "| total_timesteps | 102564 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00375 |\n", + "| n_updates | 13140 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9780 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1239 |\n", + "| total_timesteps | 102586 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00208 |\n", + "| n_updates | 13146 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9784 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1240 |\n", + "| total_timesteps | 102624 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000688 |\n", + "| n_updates | 13155 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9788 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1240 |\n", + "| total_timesteps | 102651 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00428 |\n", + "| n_updates | 13162 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.12 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9792 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1241 |\n", + "| total_timesteps | 102712 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00635 |\n", + "| n_updates | 13177 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.13 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9796 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1243 |\n", + "| total_timesteps | 102788 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00218 |\n", + "| n_updates | 13196 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9800 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1244 |\n", + "| total_timesteps | 102832 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000752 |\n", + "| n_updates | 13207 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9804 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1245 |\n", + "| total_timesteps | 102900 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0025 |\n", + "| n_updates | 13224 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9808 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1247 |\n", + "| total_timesteps | 102958 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00278 |\n", + "| n_updates | 13239 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9812 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1248 |\n", + "| total_timesteps | 103002 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00574 |\n", + "| n_updates | 13250 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9816 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1249 |\n", + "| total_timesteps | 103053 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0022 |\n", + "| n_updates | 13263 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9820 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1250 |\n", + "| total_timesteps | 103122 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00102 |\n", + "| n_updates | 13280 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9824 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1251 |\n", + "| total_timesteps | 103175 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00477 |\n", + "| n_updates | 13293 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9828 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1252 |\n", + "| total_timesteps | 103198 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00189 |\n", + "| n_updates | 13299 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9832 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1252 |\n", + "| total_timesteps | 103240 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00102 |\n", + "| n_updates | 13309 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9836 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1253 |\n", + "| total_timesteps | 103267 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000699 |\n", + "| n_updates | 13316 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9840 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1254 |\n", + "| total_timesteps | 103294 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000201 |\n", + "| n_updates | 13323 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9844 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1255 |\n", + "| total_timesteps | 103355 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0077 |\n", + "| n_updates | 13338 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9848 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1255 |\n", + "| total_timesteps | 103382 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0043 |\n", + "| n_updates | 13345 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9852 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1256 |\n", + "| total_timesteps | 103406 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000859 |\n", + "| n_updates | 13351 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9856 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1257 |\n", + "| total_timesteps | 103433 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00268 |\n", + "| n_updates | 13358 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9860 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1257 |\n", + "| total_timesteps | 103469 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00658 |\n", + "| n_updates | 13367 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9864 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1258 |\n", + "| total_timesteps | 103527 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000842 |\n", + "| n_updates | 13381 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9868 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1259 |\n", + "| total_timesteps | 103553 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00387 |\n", + "| n_updates | 13388 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9872 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1260 |\n", + "| total_timesteps | 103580 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00732 |\n", + "| n_updates | 13394 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9876 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1260 |\n", + "| total_timesteps | 103605 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00488 |\n", + "| n_updates | 13401 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.12 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9880 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1261 |\n", + "| total_timesteps | 103630 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00754 |\n", + "| n_updates | 13407 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.12 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9884 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1261 |\n", + "| total_timesteps | 103656 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0019 |\n", + "| n_updates | 13413 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.13 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9888 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1262 |\n", + "| total_timesteps | 103712 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.001 |\n", + "| n_updates | 13427 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9892 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1263 |\n", + "| total_timesteps | 103738 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00997 |\n", + "| n_updates | 13434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9896 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1264 |\n", + "| total_timesteps | 103765 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000837 |\n", + "| n_updates | 13441 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9900 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1264 |\n", + "| total_timesteps | 103790 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00664 |\n", + "| n_updates | 13447 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9904 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1265 |\n", + "| total_timesteps | 103831 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00207 |\n", + "| n_updates | 13457 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9908 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1266 |\n", + "| total_timesteps | 103877 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00157 |\n", + "| n_updates | 13469 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9912 |\n", + "| fps | 82 |\n", + "| time_elapsed | 1267 |\n", + "| total_timesteps | 103904 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000783 |\n", + "| n_updates | 13475 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9916 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1267 |\n", + "| total_timesteps | 103930 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00121 |\n", + "| n_updates | 13482 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.07 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9920 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1268 |\n", + "| total_timesteps | 103968 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00676 |\n", + "| n_updates | 13491 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.07 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9924 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1269 |\n", + "| total_timesteps | 104010 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00187 |\n", + "| n_updates | 13502 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.07 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9928 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1270 |\n", + "| total_timesteps | 104079 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00625 |\n", + "| n_updates | 13519 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9932 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1272 |\n", + "| total_timesteps | 104142 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00156 |\n", + "| n_updates | 13535 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9936 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1273 |\n", + "| total_timesteps | 104168 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00239 |\n", + "| n_updates | 13541 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.13 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9940 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1273 |\n", + "| total_timesteps | 104216 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0127 |\n", + "| n_updates | 13553 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.13 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9944 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1275 |\n", + "| total_timesteps | 104267 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00189 |\n", + "| n_updates | 13566 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9948 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1275 |\n", + "| total_timesteps | 104290 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00142 |\n", + "| n_updates | 13572 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9952 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1276 |\n", + "| total_timesteps | 104316 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00865 |\n", + "| n_updates | 13578 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9956 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1276 |\n", + "| total_timesteps | 104342 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00144 |\n", + "| n_updates | 13585 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9960 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1277 |\n", + "| total_timesteps | 104368 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00586 |\n", + "| n_updates | 13591 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9964 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1277 |\n", + "| total_timesteps | 104393 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00482 |\n", + "| n_updates | 13598 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9968 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1279 |\n", + "| total_timesteps | 104479 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000383 |\n", + "| n_updates | 13619 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9972 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1280 |\n", + "| total_timesteps | 104539 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00462 |\n", + "| n_updates | 13634 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9976 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1281 |\n", + "| total_timesteps | 104590 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00272 |\n", + "| n_updates | 13647 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9980 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1282 |\n", + "| total_timesteps | 104632 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00209 |\n", + "| n_updates | 13657 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9984 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1283 |\n", + "| total_timesteps | 104673 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0014 |\n", + "| n_updates | 13668 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9988 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1284 |\n", + "| total_timesteps | 104699 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00479 |\n", + "| n_updates | 13674 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9992 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1285 |\n", + "| total_timesteps | 104757 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00465 |\n", + "| n_updates | 13689 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 9996 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1286 |\n", + "| total_timesteps | 104781 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00207 |\n", + "| n_updates | 13695 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10000 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1286 |\n", + "| total_timesteps | 104805 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00477 |\n", + "| n_updates | 13701 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10004 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1287 |\n", + "| total_timesteps | 104851 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00241 |\n", + "| n_updates | 13712 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10008 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1288 |\n", + "| total_timesteps | 104903 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000973 |\n", + "| n_updates | 13725 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10012 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1289 |\n", + "| total_timesteps | 104951 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00215 |\n", + "| n_updates | 13737 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10016 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1290 |\n", + "| total_timesteps | 105006 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000361 |\n", + "| n_updates | 13751 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10020 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1291 |\n", + "| total_timesteps | 105034 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00174 |\n", + "| n_updates | 13758 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10024 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1292 |\n", + "| total_timesteps | 105067 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00277 |\n", + "| n_updates | 13766 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10028 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1293 |\n", + "| total_timesteps | 105117 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00513 |\n", + "| n_updates | 13779 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10032 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1294 |\n", + "| total_timesteps | 105190 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000366 |\n", + "| n_updates | 13797 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10036 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1295 |\n", + "| total_timesteps | 105236 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 13808 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10040 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1296 |\n", + "| total_timesteps | 105272 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00509 |\n", + "| n_updates | 13817 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10044 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1296 |\n", + "| total_timesteps | 105300 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00408 |\n", + "| n_updates | 13824 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10048 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1298 |\n", + "| total_timesteps | 105388 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.001 |\n", + "| n_updates | 13846 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10052 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1299 |\n", + "| total_timesteps | 105415 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00123 |\n", + "| n_updates | 13853 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10056 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1300 |\n", + "| total_timesteps | 105442 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000893 |\n", + "| n_updates | 13860 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10060 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1300 |\n", + "| total_timesteps | 105485 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.007 |\n", + "| n_updates | 13871 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10064 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1301 |\n", + "| total_timesteps | 105512 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00224 |\n", + "| n_updates | 13877 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10068 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1302 |\n", + "| total_timesteps | 105540 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0043 |\n", + "| n_updates | 13884 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10072 |\n", + "| fps | 81 |\n", + "| time_elapsed | 1303 |\n", + "| total_timesteps | 105618 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00238 |\n", + "| n_updates | 13904 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10076 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1304 |\n", + "| total_timesteps | 105662 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.023 |\n", + "| n_updates | 13915 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10080 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1305 |\n", + "| total_timesteps | 105705 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0021 |\n", + "| n_updates | 13926 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10084 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1306 |\n", + "| total_timesteps | 105744 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00476 |\n", + "| n_updates | 13935 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10088 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1307 |\n", + "| total_timesteps | 105781 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000267 |\n", + "| n_updates | 13945 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10092 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1307 |\n", + "| total_timesteps | 105808 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0012 |\n", + "| n_updates | 13951 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10096 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1309 |\n", + "| total_timesteps | 105883 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00941 |\n", + "| n_updates | 13970 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10100 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1310 |\n", + "| total_timesteps | 105950 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0018 |\n", + "| n_updates | 13987 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10104 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1311 |\n", + "| total_timesteps | 105974 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000489 |\n", + "| n_updates | 13993 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10108 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1311 |\n", + "| total_timesteps | 106001 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00105 |\n", + "| n_updates | 14000 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10112 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1312 |\n", + "| total_timesteps | 106060 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000787 |\n", + "| n_updates | 14014 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10116 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1313 |\n", + "| total_timesteps | 106082 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00273 |\n", + "| n_updates | 14020 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10120 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1314 |\n", + "| total_timesteps | 106134 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00995 |\n", + "| n_updates | 14033 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10124 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1315 |\n", + "| total_timesteps | 106161 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00157 |\n", + "| n_updates | 14040 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10128 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1316 |\n", + "| total_timesteps | 106206 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000294 |\n", + "| n_updates | 14051 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10132 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1317 |\n", + "| total_timesteps | 106286 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000283 |\n", + "| n_updates | 14071 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10136 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1319 |\n", + "| total_timesteps | 106360 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00128 |\n", + "| n_updates | 14089 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10140 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1320 |\n", + "| total_timesteps | 106419 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00377 |\n", + "| n_updates | 14104 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10144 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1322 |\n", + "| total_timesteps | 106505 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00596 |\n", + "| n_updates | 14126 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10148 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1322 |\n", + "| total_timesteps | 106532 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000876 |\n", + "| n_updates | 14132 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10152 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1323 |\n", + "| total_timesteps | 106560 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0014 |\n", + "| n_updates | 14139 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10156 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1324 |\n", + "| total_timesteps | 106596 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00271 |\n", + "| n_updates | 14148 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10160 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1326 |\n", + "| total_timesteps | 106703 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000886 |\n", + "| n_updates | 14175 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10164 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1327 |\n", + "| total_timesteps | 106739 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00145 |\n", + "| n_updates | 14184 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10168 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1327 |\n", + "| total_timesteps | 106765 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00132 |\n", + "| n_updates | 14191 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10172 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1328 |\n", + "| total_timesteps | 106789 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000338 |\n", + "| n_updates | 14197 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10176 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1329 |\n", + "| total_timesteps | 106836 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000754 |\n", + "| n_updates | 14208 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10180 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1330 |\n", + "| total_timesteps | 106860 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00524 |\n", + "| n_updates | 14214 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10184 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1330 |\n", + "| total_timesteps | 106883 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00639 |\n", + "| n_updates | 14220 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10188 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1331 |\n", + "| total_timesteps | 106926 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000359 |\n", + "| n_updates | 14231 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10192 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1332 |\n", + "| total_timesteps | 106970 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00149 |\n", + "| n_updates | 14242 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10196 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1333 |\n", + "| total_timesteps | 107013 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00387 |\n", + "| n_updates | 14253 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10200 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1334 |\n", + "| total_timesteps | 107039 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00254 |\n", + "| n_updates | 14259 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10204 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1334 |\n", + "| total_timesteps | 107078 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0021 |\n", + "| n_updates | 14269 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10208 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1336 |\n", + "| total_timesteps | 107129 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00111 |\n", + "| n_updates | 14282 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10212 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1336 |\n", + "| total_timesteps | 107155 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00289 |\n", + "| n_updates | 14288 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10216 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1337 |\n", + "| total_timesteps | 107181 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00122 |\n", + "| n_updates | 14295 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10220 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1338 |\n", + "| total_timesteps | 107232 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00437 |\n", + "| n_updates | 14307 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10224 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1339 |\n", + "| total_timesteps | 107298 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000854 |\n", + "| n_updates | 14324 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10228 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1340 |\n", + "| total_timesteps | 107334 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00417 |\n", + "| n_updates | 14333 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10232 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1341 |\n", + "| total_timesteps | 107362 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0018 |\n", + "| n_updates | 14340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10236 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1342 |\n", + "| total_timesteps | 107409 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00102 |\n", + "| n_updates | 14352 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10240 |\n", + "| fps | 80 |\n", + "| time_elapsed | 1342 |\n", + "| total_timesteps | 107444 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000505 |\n", + "| n_updates | 14360 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10244 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1343 |\n", + "| total_timesteps | 107477 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00208 |\n", + "| n_updates | 14369 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10248 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1344 |\n", + "| total_timesteps | 107511 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00664 |\n", + "| n_updates | 14377 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10252 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1345 |\n", + "| total_timesteps | 107536 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00101 |\n", + "| n_updates | 14383 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10256 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1345 |\n", + "| total_timesteps | 107560 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00174 |\n", + "| n_updates | 14389 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10260 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1346 |\n", + "| total_timesteps | 107587 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000432 |\n", + "| n_updates | 14396 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10264 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1346 |\n", + "| total_timesteps | 107623 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0033 |\n", + "| n_updates | 14405 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10268 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1348 |\n", + "| total_timesteps | 107680 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00101 |\n", + "| n_updates | 14419 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10272 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1350 |\n", + "| total_timesteps | 107782 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000893 |\n", + "| n_updates | 14445 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10276 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1350 |\n", + "| total_timesteps | 107808 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000869 |\n", + "| n_updates | 14451 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10280 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1352 |\n", + "| total_timesteps | 107884 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00354 |\n", + "| n_updates | 14470 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10284 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1353 |\n", + "| total_timesteps | 107912 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000196 |\n", + "| n_updates | 14477 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10288 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1354 |\n", + "| total_timesteps | 107988 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.007 |\n", + "| n_updates | 14496 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10292 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1356 |\n", + "| total_timesteps | 108057 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0052 |\n", + "| n_updates | 14514 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10296 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1357 |\n", + "| total_timesteps | 108117 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000576 |\n", + "| n_updates | 14529 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10300 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1358 |\n", + "| total_timesteps | 108185 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000313 |\n", + "| n_updates | 14546 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10304 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1359 |\n", + "| total_timesteps | 108208 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00127 |\n", + "| n_updates | 14551 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10308 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1360 |\n", + "| total_timesteps | 108249 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0137 |\n", + "| n_updates | 14562 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10312 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1361 |\n", + "| total_timesteps | 108298 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000252 |\n", + "| n_updates | 14574 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10316 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1362 |\n", + "| total_timesteps | 108380 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00135 |\n", + "| n_updates | 14594 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10320 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1363 |\n", + "| total_timesteps | 108407 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00956 |\n", + "| n_updates | 14601 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10324 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1364 |\n", + "| total_timesteps | 108458 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00633 |\n", + "| n_updates | 14614 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10328 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1365 |\n", + "| total_timesteps | 108481 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000624 |\n", + "| n_updates | 14620 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10332 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1365 |\n", + "| total_timesteps | 108523 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0012 |\n", + "| n_updates | 14630 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10336 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1366 |\n", + "| total_timesteps | 108550 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00154 |\n", + "| n_updates | 14637 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10340 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1367 |\n", + "| total_timesteps | 108586 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00283 |\n", + "| n_updates | 14646 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10344 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1367 |\n", + "| total_timesteps | 108613 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00171 |\n", + "| n_updates | 14653 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10348 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1369 |\n", + "| total_timesteps | 108687 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00206 |\n", + "| n_updates | 14671 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10352 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1370 |\n", + "| total_timesteps | 108720 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0194 |\n", + "| n_updates | 14679 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10356 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1371 |\n", + "| total_timesteps | 108771 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00115 |\n", + "| n_updates | 14692 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10360 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1371 |\n", + "| total_timesteps | 108797 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000593 |\n", + "| n_updates | 14699 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10364 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1372 |\n", + "| total_timesteps | 108825 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00264 |\n", + "| n_updates | 14706 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10368 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1372 |\n", + "| total_timesteps | 108853 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000782 |\n", + "| n_updates | 14713 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10372 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1373 |\n", + "| total_timesteps | 108897 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000191 |\n", + "| n_updates | 14724 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10376 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1374 |\n", + "| total_timesteps | 108940 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00117 |\n", + "| n_updates | 14734 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10380 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1375 |\n", + "| total_timesteps | 109000 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00127 |\n", + "| n_updates | 14749 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10384 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1376 |\n", + "| total_timesteps | 109026 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0149 |\n", + "| n_updates | 14756 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10388 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1377 |\n", + "| total_timesteps | 109052 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00266 |\n", + "| n_updates | 14762 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10392 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1377 |\n", + "| total_timesteps | 109094 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00342 |\n", + "| n_updates | 14773 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10396 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1379 |\n", + "| total_timesteps | 109147 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00277 |\n", + "| n_updates | 14786 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10400 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1379 |\n", + "| total_timesteps | 109189 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00389 |\n", + "| n_updates | 14797 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10404 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1380 |\n", + "| total_timesteps | 109234 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000754 |\n", + "| n_updates | 14808 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10408 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1381 |\n", + "| total_timesteps | 109276 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00095 |\n", + "| n_updates | 14818 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10412 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1382 |\n", + "| total_timesteps | 109311 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000829 |\n", + "| n_updates | 14827 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10416 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1383 |\n", + "| total_timesteps | 109354 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00444 |\n", + "| n_updates | 14838 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10420 |\n", + "| fps | 79 |\n", + "| time_elapsed | 1384 |\n", + "| total_timesteps | 109406 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000458 |\n", + "| n_updates | 14851 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10424 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1385 |\n", + "| total_timesteps | 109450 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0213 |\n", + "| n_updates | 14862 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10428 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1387 |\n", + "| total_timesteps | 109525 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 14881 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10432 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1388 |\n", + "| total_timesteps | 109561 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00217 |\n", + "| n_updates | 14890 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10436 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1389 |\n", + "| total_timesteps | 109627 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00496 |\n", + "| n_updates | 14906 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10440 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1389 |\n", + "| total_timesteps | 109652 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00534 |\n", + "| n_updates | 14912 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10444 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1390 |\n", + "| total_timesteps | 109695 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00329 |\n", + "| n_updates | 14923 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10448 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1391 |\n", + "| total_timesteps | 109736 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000785 |\n", + "| n_updates | 14933 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10452 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1392 |\n", + "| total_timesteps | 109778 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000577 |\n", + "| n_updates | 14944 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10456 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1393 |\n", + "| total_timesteps | 109811 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00972 |\n", + "| n_updates | 14952 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10460 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1393 |\n", + "| total_timesteps | 109835 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0022 |\n", + "| n_updates | 14958 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10464 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1394 |\n", + "| total_timesteps | 109877 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00866 |\n", + "| n_updates | 14969 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10468 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1396 |\n", + "| total_timesteps | 109935 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00158 |\n", + "| n_updates | 14983 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10472 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1397 |\n", + "| total_timesteps | 109976 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000884 |\n", + "| n_updates | 14993 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10476 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1398 |\n", + "| total_timesteps | 110037 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0194 |\n", + "| n_updates | 15009 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10480 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1399 |\n", + "| total_timesteps | 110063 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00523 |\n", + "| n_updates | 15015 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10484 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1399 |\n", + "| total_timesteps | 110103 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0043 |\n", + "| n_updates | 15025 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10488 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1401 |\n", + "| total_timesteps | 110171 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00954 |\n", + "| n_updates | 15042 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10492 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1402 |\n", + "| total_timesteps | 110228 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00247 |\n", + "| n_updates | 15056 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10496 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1403 |\n", + "| total_timesteps | 110255 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00723 |\n", + "| n_updates | 15063 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10500 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1403 |\n", + "| total_timesteps | 110291 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00172 |\n", + "| n_updates | 15072 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10504 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1404 |\n", + "| total_timesteps | 110332 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00117 |\n", + "| n_updates | 15082 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10508 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1406 |\n", + "| total_timesteps | 110409 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00173 |\n", + "| n_updates | 15102 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10512 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1407 |\n", + "| total_timesteps | 110467 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00248 |\n", + "| n_updates | 15116 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10516 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1408 |\n", + "| total_timesteps | 110521 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00538 |\n", + "| n_updates | 15130 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10520 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1409 |\n", + "| total_timesteps | 110571 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0144 |\n", + "| n_updates | 15142 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10524 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1410 |\n", + "| total_timesteps | 110624 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00234 |\n", + "| n_updates | 15155 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10528 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1411 |\n", + "| total_timesteps | 110657 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00368 |\n", + "| n_updates | 15164 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10532 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1412 |\n", + "| total_timesteps | 110694 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00807 |\n", + "| n_updates | 15173 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10536 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1413 |\n", + "| total_timesteps | 110744 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00475 |\n", + "| n_updates | 15185 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10540 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1414 |\n", + "| total_timesteps | 110796 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0113 |\n", + "| n_updates | 15198 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10544 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1415 |\n", + "| total_timesteps | 110821 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00363 |\n", + "| n_updates | 15205 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10548 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1415 |\n", + "| total_timesteps | 110863 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00301 |\n", + "| n_updates | 15215 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10552 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1417 |\n", + "| total_timesteps | 110926 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00304 |\n", + "| n_updates | 15231 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10556 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1418 |\n", + "| total_timesteps | 110971 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00106 |\n", + "| n_updates | 15242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10560 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1419 |\n", + "| total_timesteps | 111023 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00129 |\n", + "| n_updates | 15255 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10564 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1420 |\n", + "| total_timesteps | 111067 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0075 |\n", + "| n_updates | 15266 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10568 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1420 |\n", + "| total_timesteps | 111091 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00143 |\n", + "| n_updates | 15272 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10572 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1421 |\n", + "| total_timesteps | 111120 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0015 |\n", + "| n_updates | 15279 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10576 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1422 |\n", + "| total_timesteps | 111171 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00683 |\n", + "| n_updates | 15292 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10580 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1423 |\n", + "| total_timesteps | 111237 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00196 |\n", + "| n_updates | 15309 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10584 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1424 |\n", + "| total_timesteps | 111276 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00194 |\n", + "| n_updates | 15318 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10588 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1425 |\n", + "| total_timesteps | 111299 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00168 |\n", + "| n_updates | 15324 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10592 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1425 |\n", + "| total_timesteps | 111337 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00578 |\n", + "| n_updates | 15334 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10596 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1426 |\n", + "| total_timesteps | 111379 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0105 |\n", + "| n_updates | 15344 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10600 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1427 |\n", + "| total_timesteps | 111405 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00343 |\n", + "| n_updates | 15351 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10604 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1427 |\n", + "| total_timesteps | 111432 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0145 |\n", + "| n_updates | 15357 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10608 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1428 |\n", + "| total_timesteps | 111459 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00602 |\n", + "| n_updates | 15364 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10612 |\n", + "| fps | 78 |\n", + "| time_elapsed | 1429 |\n", + "| total_timesteps | 111484 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000945 |\n", + "| n_updates | 15370 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10616 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1430 |\n", + "| total_timesteps | 111536 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00146 |\n", + "| n_updates | 15383 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10620 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1431 |\n", + "| total_timesteps | 111582 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00986 |\n", + "| n_updates | 15395 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10624 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1431 |\n", + "| total_timesteps | 111618 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00327 |\n", + "| n_updates | 15404 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10628 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1432 |\n", + "| total_timesteps | 111642 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00236 |\n", + "| n_updates | 15410 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10632 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1432 |\n", + "| total_timesteps | 111670 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00139 |\n", + "| n_updates | 15417 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10636 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1434 |\n", + "| total_timesteps | 111722 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0103 |\n", + "| n_updates | 15430 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10640 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1434 |\n", + "| total_timesteps | 111756 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00238 |\n", + "| n_updates | 15438 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10644 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1435 |\n", + "| total_timesteps | 111782 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00139 |\n", + "| n_updates | 15445 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10648 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1435 |\n", + "| total_timesteps | 111808 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00148 |\n", + "| n_updates | 15451 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10652 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1437 |\n", + "| total_timesteps | 111901 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00148 |\n", + "| n_updates | 15475 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10656 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1439 |\n", + "| total_timesteps | 111963 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0192 |\n", + "| n_updates | 15490 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10660 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1439 |\n", + "| total_timesteps | 111989 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.008 |\n", + "| n_updates | 15497 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10664 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1440 |\n", + "| total_timesteps | 112041 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00025 |\n", + "| n_updates | 15510 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10668 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1441 |\n", + "| total_timesteps | 112069 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000679 |\n", + "| n_updates | 15517 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10672 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1442 |\n", + "| total_timesteps | 112120 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00562 |\n", + "| n_updates | 15529 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10676 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1444 |\n", + "| total_timesteps | 112219 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000599 |\n", + "| n_updates | 15554 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10680 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1445 |\n", + "| total_timesteps | 112264 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00551 |\n", + "| n_updates | 15565 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10684 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1446 |\n", + "| total_timesteps | 112301 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0182 |\n", + "| n_updates | 15575 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10688 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1447 |\n", + "| total_timesteps | 112359 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00744 |\n", + "| n_updates | 15589 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10692 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1447 |\n", + "| total_timesteps | 112386 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00476 |\n", + "| n_updates | 15596 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10696 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1448 |\n", + "| total_timesteps | 112438 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00782 |\n", + "| n_updates | 15609 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10700 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1449 |\n", + "| total_timesteps | 112485 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00222 |\n", + "| n_updates | 15621 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10704 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1451 |\n", + "| total_timesteps | 112554 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00749 |\n", + "| n_updates | 15638 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10708 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1452 |\n", + "| total_timesteps | 112611 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0115 |\n", + "| n_updates | 15652 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10712 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1453 |\n", + "| total_timesteps | 112651 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00948 |\n", + "| n_updates | 15662 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10716 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1453 |\n", + "| total_timesteps | 112677 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00228 |\n", + "| n_updates | 15669 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10720 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1455 |\n", + "| total_timesteps | 112761 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00131 |\n", + "| n_updates | 15690 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10724 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1457 |\n", + "| total_timesteps | 112805 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0026 |\n", + "| n_updates | 15701 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10728 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1458 |\n", + "| total_timesteps | 112880 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0099 |\n", + "| n_updates | 15719 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10732 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1460 |\n", + "| total_timesteps | 112956 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0043 |\n", + "| n_updates | 15738 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10736 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1462 |\n", + "| total_timesteps | 113061 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000412 |\n", + "| n_updates | 15765 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10740 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1464 |\n", + "| total_timesteps | 113120 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00449 |\n", + "| n_updates | 15779 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10744 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1465 |\n", + "| total_timesteps | 113176 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00661 |\n", + "| n_updates | 15793 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10748 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1466 |\n", + "| total_timesteps | 113219 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0058 |\n", + "| n_updates | 15804 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10752 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1466 |\n", + "| total_timesteps | 113243 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000382 |\n", + "| n_updates | 15810 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10756 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1467 |\n", + "| total_timesteps | 113269 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000238 |\n", + "| n_updates | 15817 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10760 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1468 |\n", + "| total_timesteps | 113305 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0101 |\n", + "| n_updates | 15826 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10764 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1470 |\n", + "| total_timesteps | 113410 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00494 |\n", + "| n_updates | 15852 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10768 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1470 |\n", + "| total_timesteps | 113437 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00111 |\n", + "| n_updates | 15859 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10772 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1471 |\n", + "| total_timesteps | 113463 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00487 |\n", + "| n_updates | 15865 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10776 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1472 |\n", + "| total_timesteps | 113508 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00205 |\n", + "| n_updates | 15876 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10780 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1472 |\n", + "| total_timesteps | 113535 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00927 |\n", + "| n_updates | 15883 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10784 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1474 |\n", + "| total_timesteps | 113603 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00785 |\n", + "| n_updates | 15900 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10788 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1475 |\n", + "| total_timesteps | 113645 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00619 |\n", + "| n_updates | 15911 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10792 |\n", + "| fps | 77 |\n", + "| time_elapsed | 1476 |\n", + "| total_timesteps | 113696 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0172 |\n", + "| n_updates | 15923 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10796 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1477 |\n", + "| total_timesteps | 113732 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00186 |\n", + "| n_updates | 15932 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10800 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1478 |\n", + "| total_timesteps | 113783 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00167 |\n", + "| n_updates | 15945 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10804 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1478 |\n", + "| total_timesteps | 113818 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00368 |\n", + "| n_updates | 15954 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10808 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1479 |\n", + "| total_timesteps | 113863 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00407 |\n", + "| n_updates | 15965 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10812 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1481 |\n", + "| total_timesteps | 113928 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00219 |\n", + "| n_updates | 15981 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10816 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1482 |\n", + "| total_timesteps | 113986 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00144 |\n", + "| n_updates | 15996 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10820 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1483 |\n", + "| total_timesteps | 114018 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00101 |\n", + "| n_updates | 16004 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10824 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1483 |\n", + "| total_timesteps | 114051 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00208 |\n", + "| n_updates | 16012 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10828 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1484 |\n", + "| total_timesteps | 114085 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.007 |\n", + "| n_updates | 16021 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10832 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1485 |\n", + "| total_timesteps | 114149 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00636 |\n", + "| n_updates | 16037 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10836 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1486 |\n", + "| total_timesteps | 114209 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0048 |\n", + "| n_updates | 16052 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10840 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1489 |\n", + "| total_timesteps | 114313 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00492 |\n", + "| n_updates | 16078 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10844 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1490 |\n", + "| total_timesteps | 114361 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00457 |\n", + "| n_updates | 16090 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10848 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1490 |\n", + "| total_timesteps | 114403 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00365 |\n", + "| n_updates | 16100 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10852 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1491 |\n", + "| total_timesteps | 114428 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00326 |\n", + "| n_updates | 16106 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10856 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1492 |\n", + "| total_timesteps | 114463 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00121 |\n", + "| n_updates | 16115 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10860 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1492 |\n", + "| total_timesteps | 114496 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00655 |\n", + "| n_updates | 16123 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10864 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1493 |\n", + "| total_timesteps | 114529 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00589 |\n", + "| n_updates | 16132 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10868 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1495 |\n", + "| total_timesteps | 114597 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00379 |\n", + "| n_updates | 16149 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10872 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1496 |\n", + "| total_timesteps | 114633 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00153 |\n", + "| n_updates | 16158 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10876 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1497 |\n", + "| total_timesteps | 114696 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0049 |\n", + "| n_updates | 16173 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10880 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1499 |\n", + "| total_timesteps | 114797 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00386 |\n", + "| n_updates | 16199 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10884 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1500 |\n", + "| total_timesteps | 114825 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00126 |\n", + "| n_updates | 16206 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10888 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1501 |\n", + "| total_timesteps | 114880 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00272 |\n", + "| n_updates | 16219 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10892 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1502 |\n", + "| total_timesteps | 114922 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00161 |\n", + "| n_updates | 16230 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10896 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1503 |\n", + "| total_timesteps | 114949 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0027 |\n", + "| n_updates | 16237 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10900 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1504 |\n", + "| total_timesteps | 115008 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0006 |\n", + "| n_updates | 16251 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10904 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1505 |\n", + "| total_timesteps | 115036 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00913 |\n", + "| n_updates | 16258 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10908 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1506 |\n", + "| total_timesteps | 115087 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00173 |\n", + "| n_updates | 16271 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10912 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1507 |\n", + "| total_timesteps | 115171 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00167 |\n", + "| n_updates | 16292 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10916 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1509 |\n", + "| total_timesteps | 115217 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00185 |\n", + "| n_updates | 16304 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10920 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1510 |\n", + "| total_timesteps | 115278 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00362 |\n", + "| n_updates | 16319 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10924 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1512 |\n", + "| total_timesteps | 115362 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00309 |\n", + "| n_updates | 16340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10928 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1513 |\n", + "| total_timesteps | 115404 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00903 |\n", + "| n_updates | 16350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10932 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1514 |\n", + "| total_timesteps | 115441 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000479 |\n", + "| n_updates | 16360 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10936 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1515 |\n", + "| total_timesteps | 115493 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00132 |\n", + "| n_updates | 16373 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10940 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1516 |\n", + "| total_timesteps | 115543 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00151 |\n", + "| n_updates | 16385 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10944 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1517 |\n", + "| total_timesteps | 115578 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000895 |\n", + "| n_updates | 16394 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10948 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1517 |\n", + "| total_timesteps | 115613 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00232 |\n", + "| n_updates | 16403 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10952 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1518 |\n", + "| total_timesteps | 115665 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00237 |\n", + "| n_updates | 16416 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10956 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1520 |\n", + "| total_timesteps | 115725 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00506 |\n", + "| n_updates | 16431 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10960 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1520 |\n", + "| total_timesteps | 115749 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00919 |\n", + "| n_updates | 16437 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10964 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1521 |\n", + "| total_timesteps | 115809 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.015 |\n", + "| n_updates | 16452 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10968 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1523 |\n", + "| total_timesteps | 115879 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000776 |\n", + "| n_updates | 16469 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10972 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1524 |\n", + "| total_timesteps | 115929 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0017 |\n", + "| n_updates | 16482 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10976 |\n", + "| fps | 76 |\n", + "| time_elapsed | 1525 |\n", + "| total_timesteps | 115979 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00194 |\n", + "| n_updates | 16494 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10980 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1526 |\n", + "| total_timesteps | 116014 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00127 |\n", + "| n_updates | 16503 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10984 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1527 |\n", + "| total_timesteps | 116073 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000529 |\n", + "| n_updates | 16518 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10988 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1528 |\n", + "| total_timesteps | 116099 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00116 |\n", + "| n_updates | 16524 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10992 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1528 |\n", + "| total_timesteps | 116126 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00511 |\n", + "| n_updates | 16531 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 10996 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1530 |\n", + "| total_timesteps | 116193 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00206 |\n", + "| n_updates | 16548 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11000 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1531 |\n", + "| total_timesteps | 116229 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00222 |\n", + "| n_updates | 16557 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11004 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1531 |\n", + "| total_timesteps | 116266 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00222 |\n", + "| n_updates | 16566 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11008 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1533 |\n", + "| total_timesteps | 116317 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00656 |\n", + "| n_updates | 16579 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11012 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1534 |\n", + "| total_timesteps | 116383 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00823 |\n", + "| n_updates | 16595 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11016 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1535 |\n", + "| total_timesteps | 116421 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00106 |\n", + "| n_updates | 16605 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11020 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1535 |\n", + "| total_timesteps | 116449 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00147 |\n", + "| n_updates | 16612 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11024 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1536 |\n", + "| total_timesteps | 116486 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00113 |\n", + "| n_updates | 16621 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11028 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1537 |\n", + "| total_timesteps | 116514 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0005 |\n", + "| n_updates | 16628 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11032 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1538 |\n", + "| total_timesteps | 116552 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000751 |\n", + "| n_updates | 16637 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11036 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1539 |\n", + "| total_timesteps | 116613 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00327 |\n", + "| n_updates | 16653 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11040 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1540 |\n", + "| total_timesteps | 116655 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00517 |\n", + "| n_updates | 16663 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11044 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1540 |\n", + "| total_timesteps | 116683 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00102 |\n", + "| n_updates | 16670 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11048 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1541 |\n", + "| total_timesteps | 116709 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00305 |\n", + "| n_updates | 16677 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11052 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1542 |\n", + "| total_timesteps | 116785 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00735 |\n", + "| n_updates | 16696 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11056 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1544 |\n", + "| total_timesteps | 116844 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00895 |\n", + "| n_updates | 16710 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11060 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1545 |\n", + "| total_timesteps | 116920 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00567 |\n", + "| n_updates | 16729 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11064 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1546 |\n", + "| total_timesteps | 116955 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000546 |\n", + "| n_updates | 16738 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11068 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1547 |\n", + "| total_timesteps | 117031 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000665 |\n", + "| n_updates | 16757 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11072 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1549 |\n", + "| total_timesteps | 117088 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00533 |\n", + "| n_updates | 16771 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11076 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1549 |\n", + "| total_timesteps | 117116 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00123 |\n", + "| n_updates | 16778 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11080 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1550 |\n", + "| total_timesteps | 117161 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00128 |\n", + "| n_updates | 16790 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11084 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1551 |\n", + "| total_timesteps | 117208 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00236 |\n", + "| n_updates | 16801 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11088 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1553 |\n", + "| total_timesteps | 117255 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00991 |\n", + "| n_updates | 16813 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 312 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11092 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1556 |\n", + "| total_timesteps | 117415 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0134 |\n", + "| n_updates | 16853 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 313 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11096 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1557 |\n", + "| total_timesteps | 117466 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00385 |\n", + "| n_updates | 16866 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 315 |\n", + "| ep_rew_mean | 2.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11100 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1558 |\n", + "| total_timesteps | 117503 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00255 |\n", + "| n_updates | 16875 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 315 |\n", + "| ep_rew_mean | 2.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11104 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1560 |\n", + "| total_timesteps | 117589 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00234 |\n", + "| n_updates | 16897 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 317 |\n", + "| ep_rew_mean | 2.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11108 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1561 |\n", + "| total_timesteps | 117634 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00935 |\n", + "| n_updates | 16908 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11112 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1562 |\n", + "| total_timesteps | 117661 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00153 |\n", + "| n_updates | 16915 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 317 |\n", + "| ep_rew_mean | 2.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11116 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1562 |\n", + "| total_timesteps | 117686 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00427 |\n", + "| n_updates | 16921 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11120 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1563 |\n", + "| total_timesteps | 117712 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00746 |\n", + "| n_updates | 16927 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11124 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1564 |\n", + "| total_timesteps | 117782 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00707 |\n", + "| n_updates | 16945 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11128 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1565 |\n", + "| total_timesteps | 117817 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00455 |\n", + "| n_updates | 16954 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11132 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1566 |\n", + "| total_timesteps | 117852 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000738 |\n", + "| n_updates | 16962 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11136 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1567 |\n", + "| total_timesteps | 117910 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00138 |\n", + "| n_updates | 16977 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11140 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1568 |\n", + "| total_timesteps | 117936 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00253 |\n", + "| n_updates | 16983 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11144 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1569 |\n", + "| total_timesteps | 117985 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00233 |\n", + "| n_updates | 16996 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 319 |\n", + "| ep_rew_mean | 2.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11148 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1571 |\n", + "| total_timesteps | 118059 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00617 |\n", + "| n_updates | 17014 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 321 |\n", + "| ep_rew_mean | 2.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11152 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1572 |\n", + "| total_timesteps | 118133 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00228 |\n", + "| n_updates | 17033 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 320 |\n", + "| ep_rew_mean | 2.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11156 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1573 |\n", + "| total_timesteps | 118170 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00634 |\n", + "| n_updates | 17042 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 319 |\n", + "| ep_rew_mean | 2.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11160 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1574 |\n", + "| total_timesteps | 118199 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00138 |\n", + "| n_updates | 17049 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 319 |\n", + "| ep_rew_mean | 2.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11164 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1575 |\n", + "| total_timesteps | 118233 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00113 |\n", + "| n_updates | 17058 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 319 |\n", + "| ep_rew_mean | 2.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11168 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1576 |\n", + "| total_timesteps | 118292 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00168 |\n", + "| n_updates | 17072 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 319 |\n", + "| ep_rew_mean | 2.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11172 |\n", + "| fps | 75 |\n", + "| time_elapsed | 1577 |\n", + "| total_timesteps | 118342 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00237 |\n", + "| n_updates | 17085 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11176 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1578 |\n", + "| total_timesteps | 118367 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00178 |\n", + "| n_updates | 17091 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11180 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1579 |\n", + "| total_timesteps | 118438 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000862 |\n", + "| n_updates | 17109 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11184 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1581 |\n", + "| total_timesteps | 118491 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00813 |\n", + "| n_updates | 17122 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11188 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1581 |\n", + "| total_timesteps | 118525 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000985 |\n", + "| n_updates | 17131 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 317 |\n", + "| ep_rew_mean | 2.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11192 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1582 |\n", + "| total_timesteps | 118577 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00151 |\n", + "| n_updates | 17144 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 317 |\n", + "| ep_rew_mean | 2.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11196 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1583 |\n", + "| total_timesteps | 118605 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00062 |\n", + "| n_updates | 17151 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 317 |\n", + "| ep_rew_mean | 2.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11200 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1584 |\n", + "| total_timesteps | 118656 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.026 |\n", + "| n_updates | 17163 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 317 |\n", + "| ep_rew_mean | 2.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11204 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1586 |\n", + "| total_timesteps | 118752 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0012 |\n", + "| n_updates | 17187 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11208 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1588 |\n", + "| total_timesteps | 118819 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00244 |\n", + "| n_updates | 17204 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 319 |\n", + "| ep_rew_mean | 2.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11212 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1589 |\n", + "| total_timesteps | 118895 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00108 |\n", + "| n_updates | 17223 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 320 |\n", + "| ep_rew_mean | 2.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11216 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1590 |\n", + "| total_timesteps | 118921 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000976 |\n", + "| n_updates | 17230 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11220 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1590 |\n", + "| total_timesteps | 118943 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00228 |\n", + "| n_updates | 17235 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11224 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1592 |\n", + "| total_timesteps | 119010 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000783 |\n", + "| n_updates | 17252 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 319 |\n", + "| ep_rew_mean | 2.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11228 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1593 |\n", + "| total_timesteps | 119049 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 17262 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 317 |\n", + "| ep_rew_mean | 2.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11232 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1594 |\n", + "| total_timesteps | 119100 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0021 |\n", + "| n_updates | 17274 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11236 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1595 |\n", + "| total_timesteps | 119141 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000947 |\n", + "| n_updates | 17285 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 315 |\n", + "| ep_rew_mean | 2.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11240 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1597 |\n", + "| total_timesteps | 119229 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0035 |\n", + "| n_updates | 17307 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 315 |\n", + "| ep_rew_mean | 2.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11244 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1598 |\n", + "| total_timesteps | 119259 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000987 |\n", + "| n_updates | 17314 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 314 |\n", + "| ep_rew_mean | 2.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11248 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1598 |\n", + "| total_timesteps | 119293 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00277 |\n", + "| n_updates | 17323 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 315 |\n", + "| ep_rew_mean | 2.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11252 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1600 |\n", + "| total_timesteps | 119369 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00404 |\n", + "| n_updates | 17342 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11256 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1602 |\n", + "| total_timesteps | 119421 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00158 |\n", + "| n_updates | 17355 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11260 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1603 |\n", + "| total_timesteps | 119482 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0117 |\n", + "| n_updates | 17370 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11264 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1604 |\n", + "| total_timesteps | 119508 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000797 |\n", + "| n_updates | 17376 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 315 |\n", + "| ep_rew_mean | 2.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11268 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1606 |\n", + "| total_timesteps | 119562 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00357 |\n", + "| n_updates | 17390 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11272 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1606 |\n", + "| total_timesteps | 119591 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0013 |\n", + "| n_updates | 17397 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11276 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1608 |\n", + "| total_timesteps | 119637 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00132 |\n", + "| n_updates | 17409 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 317 |\n", + "| ep_rew_mean | 2.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11280 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1609 |\n", + "| total_timesteps | 119685 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00121 |\n", + "| n_updates | 17421 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 317 |\n", + "| ep_rew_mean | 2.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11284 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1610 |\n", + "| total_timesteps | 119721 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00785 |\n", + "| n_updates | 17430 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11288 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1611 |\n", + "| total_timesteps | 119766 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00669 |\n", + "| n_updates | 17441 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.4 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11292 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1612 |\n", + "| total_timesteps | 119812 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00125 |\n", + "| n_updates | 17452 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11296 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1612 |\n", + "| total_timesteps | 119839 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000472 |\n", + "| n_updates | 17459 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 315 |\n", + "| ep_rew_mean | 2.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11300 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1613 |\n", + "| total_timesteps | 119873 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00072 |\n", + "| n_updates | 17468 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 315 |\n", + "| ep_rew_mean | 2.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11304 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1614 |\n", + "| total_timesteps | 119925 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000811 |\n", + "| n_updates | 17481 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 315 |\n", + "| ep_rew_mean | 2.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11308 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1615 |\n", + "| total_timesteps | 119973 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000849 |\n", + "| n_updates | 17493 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 315 |\n", + "| ep_rew_mean | 2.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11312 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1615 |\n", + "| total_timesteps | 119998 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0012 |\n", + "| n_updates | 17499 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 315 |\n", + "| ep_rew_mean | 2.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11316 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1617 |\n", + "| total_timesteps | 120064 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00745 |\n", + "| n_updates | 17515 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11320 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1618 |\n", + "| total_timesteps | 120132 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00203 |\n", + "| n_updates | 17532 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11324 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1619 |\n", + "| total_timesteps | 120159 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0111 |\n", + "| n_updates | 17539 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 315 |\n", + "| ep_rew_mean | 2.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11328 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1619 |\n", + "| total_timesteps | 120184 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00676 |\n", + "| n_updates | 17545 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 314 |\n", + "| ep_rew_mean | 2.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11332 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1620 |\n", + "| total_timesteps | 120218 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00497 |\n", + "| n_updates | 17554 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 313 |\n", + "| ep_rew_mean | 2.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11336 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1621 |\n", + "| total_timesteps | 120270 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000769 |\n", + "| n_updates | 17567 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 311 |\n", + "| ep_rew_mean | 2.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11340 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1622 |\n", + "| total_timesteps | 120321 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00454 |\n", + "| n_updates | 17580 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 311 |\n", + "| ep_rew_mean | 2.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11344 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1622 |\n", + "| total_timesteps | 120348 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00312 |\n", + "| n_updates | 17586 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11348 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1623 |\n", + "| total_timesteps | 120375 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00271 |\n", + "| n_updates | 17593 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11352 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1624 |\n", + "| total_timesteps | 120411 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00202 |\n", + "| n_updates | 17602 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11356 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1624 |\n", + "| total_timesteps | 120437 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000655 |\n", + "| n_updates | 17609 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11360 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1625 |\n", + "| total_timesteps | 120466 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00433 |\n", + "| n_updates | 17616 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11364 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1626 |\n", + "| total_timesteps | 120492 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0115 |\n", + "| n_updates | 17622 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11368 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1627 |\n", + "| total_timesteps | 120535 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00296 |\n", + "| n_updates | 17633 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11372 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1627 |\n", + "| total_timesteps | 120563 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0109 |\n", + "| n_updates | 17640 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11376 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1628 |\n", + "| total_timesteps | 120600 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00813 |\n", + "| n_updates | 17649 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11380 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1628 |\n", + "| total_timesteps | 120626 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00934 |\n", + "| n_updates | 17656 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11384 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1629 |\n", + "| total_timesteps | 120651 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00286 |\n", + "| n_updates | 17662 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11388 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1630 |\n", + "| total_timesteps | 120678 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00187 |\n", + "| n_updates | 17669 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11392 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1630 |\n", + "| total_timesteps | 120705 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00469 |\n", + "| n_updates | 17676 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11396 |\n", + "| fps | 74 |\n", + "| time_elapsed | 1631 |\n", + "| total_timesteps | 120732 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00728 |\n", + "| n_updates | 17682 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11400 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1632 |\n", + "| total_timesteps | 120758 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00727 |\n", + "| n_updates | 17689 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11404 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1632 |\n", + "| total_timesteps | 120783 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00202 |\n", + "| n_updates | 17695 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11408 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1633 |\n", + "| total_timesteps | 120809 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0107 |\n", + "| n_updates | 17702 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11412 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1633 |\n", + "| total_timesteps | 120835 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00268 |\n", + "| n_updates | 17708 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11416 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1634 |\n", + "| total_timesteps | 120881 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.011 |\n", + "| n_updates | 17720 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11420 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1636 |\n", + "| total_timesteps | 120951 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00406 |\n", + "| n_updates | 17737 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11424 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1638 |\n", + "| total_timesteps | 121013 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00724 |\n", + "| n_updates | 17753 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11428 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1638 |\n", + "| total_timesteps | 121048 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00278 |\n", + "| n_updates | 17761 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11432 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1639 |\n", + "| total_timesteps | 121091 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00331 |\n", + "| n_updates | 17772 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11436 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1641 |\n", + "| total_timesteps | 121191 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0107 |\n", + "| n_updates | 17797 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11440 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1642 |\n", + "| total_timesteps | 121242 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00577 |\n", + "| n_updates | 17810 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11444 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1643 |\n", + "| total_timesteps | 121267 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0135 |\n", + "| n_updates | 17816 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11448 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1644 |\n", + "| total_timesteps | 121303 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00989 |\n", + "| n_updates | 17825 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11452 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1644 |\n", + "| total_timesteps | 121330 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000565 |\n", + "| n_updates | 17832 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11456 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1645 |\n", + "| total_timesteps | 121356 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0031 |\n", + "| n_updates | 17838 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11460 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1646 |\n", + "| total_timesteps | 121391 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00191 |\n", + "| n_updates | 17847 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11464 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1647 |\n", + "| total_timesteps | 121438 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00254 |\n", + "| n_updates | 17859 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11468 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1647 |\n", + "| total_timesteps | 121467 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00496 |\n", + "| n_updates | 17866 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11472 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1648 |\n", + "| total_timesteps | 121511 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00179 |\n", + "| n_updates | 17877 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11476 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1649 |\n", + "| total_timesteps | 121548 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00509 |\n", + "| n_updates | 17886 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11480 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1649 |\n", + "| total_timesteps | 121572 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00282 |\n", + "| n_updates | 17892 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11484 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1650 |\n", + "| total_timesteps | 121620 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00193 |\n", + "| n_updates | 17904 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11488 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1651 |\n", + "| total_timesteps | 121666 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00143 |\n", + "| n_updates | 17916 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11492 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1652 |\n", + "| total_timesteps | 121707 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00947 |\n", + "| n_updates | 17926 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11496 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1654 |\n", + "| total_timesteps | 121783 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00538 |\n", + "| n_updates | 17945 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11500 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1655 |\n", + "| total_timesteps | 121826 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00252 |\n", + "| n_updates | 17956 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11504 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1656 |\n", + "| total_timesteps | 121885 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.012 |\n", + "| n_updates | 17971 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11508 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1657 |\n", + "| total_timesteps | 121939 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00315 |\n", + "| n_updates | 17984 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11512 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1658 |\n", + "| total_timesteps | 121964 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00378 |\n", + "| n_updates | 17990 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11516 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1659 |\n", + "| total_timesteps | 122026 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000564 |\n", + "| n_updates | 18006 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11520 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1660 |\n", + "| total_timesteps | 122076 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00224 |\n", + "| n_updates | 18018 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11524 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1661 |\n", + "| total_timesteps | 122113 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00827 |\n", + "| n_updates | 18028 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11528 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1662 |\n", + "| total_timesteps | 122136 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000601 |\n", + "| n_updates | 18033 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11532 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1663 |\n", + "| total_timesteps | 122190 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000658 |\n", + "| n_updates | 18047 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11536 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1664 |\n", + "| total_timesteps | 122227 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00234 |\n", + "| n_updates | 18056 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11540 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1666 |\n", + "| total_timesteps | 122289 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00305 |\n", + "| n_updates | 18072 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11544 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1667 |\n", + "| total_timesteps | 122349 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0041 |\n", + "| n_updates | 18087 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11548 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1667 |\n", + "| total_timesteps | 122375 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00582 |\n", + "| n_updates | 18093 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11552 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1669 |\n", + "| total_timesteps | 122442 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0083 |\n", + "| n_updates | 18110 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11556 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1670 |\n", + "| total_timesteps | 122484 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00529 |\n", + "| n_updates | 18120 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11560 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1670 |\n", + "| total_timesteps | 122510 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00569 |\n", + "| n_updates | 18127 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11564 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1671 |\n", + "| total_timesteps | 122536 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00328 |\n", + "| n_updates | 18133 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11568 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1671 |\n", + "| total_timesteps | 122561 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0111 |\n", + "| n_updates | 18140 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11572 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1672 |\n", + "| total_timesteps | 122588 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00334 |\n", + "| n_updates | 18146 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11576 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1672 |\n", + "| total_timesteps | 122614 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00233 |\n", + "| n_updates | 18153 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11580 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1674 |\n", + "| total_timesteps | 122666 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00109 |\n", + "| n_updates | 18166 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11584 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1675 |\n", + "| total_timesteps | 122718 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0139 |\n", + "| n_updates | 18179 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11588 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1675 |\n", + "| total_timesteps | 122744 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00118 |\n", + "| n_updates | 18185 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11592 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1677 |\n", + "| total_timesteps | 122819 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00408 |\n", + "| n_updates | 18204 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11596 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1678 |\n", + "| total_timesteps | 122862 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00242 |\n", + "| n_updates | 18215 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11600 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1679 |\n", + "| total_timesteps | 122909 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00706 |\n", + "| n_updates | 18227 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11604 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1679 |\n", + "| total_timesteps | 122945 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00328 |\n", + "| n_updates | 18236 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11608 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1681 |\n", + "| total_timesteps | 123039 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00287 |\n", + "| n_updates | 18259 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11612 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1682 |\n", + "| total_timesteps | 123099 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00859 |\n", + "| n_updates | 18274 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11616 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1683 |\n", + "| total_timesteps | 123150 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00355 |\n", + "| n_updates | 18287 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11620 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1684 |\n", + "| total_timesteps | 123195 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00465 |\n", + "| n_updates | 18298 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11624 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1685 |\n", + "| total_timesteps | 123246 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00232 |\n", + "| n_updates | 18311 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11628 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1686 |\n", + "| total_timesteps | 123280 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00543 |\n", + "| n_updates | 18319 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11632 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1687 |\n", + "| total_timesteps | 123326 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0129 |\n", + "| n_updates | 18331 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11636 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1688 |\n", + "| total_timesteps | 123365 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00148 |\n", + "| n_updates | 18341 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11640 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1689 |\n", + "| total_timesteps | 123402 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0158 |\n", + "| n_updates | 18350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11644 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1689 |\n", + "| total_timesteps | 123439 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00203 |\n", + "| n_updates | 18359 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11648 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1690 |\n", + "| total_timesteps | 123474 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00573 |\n", + "| n_updates | 18368 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11652 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1691 |\n", + "| total_timesteps | 123502 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00432 |\n", + "| n_updates | 18375 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11656 |\n", + "| fps | 73 |\n", + "| time_elapsed | 1692 |\n", + "| total_timesteps | 123537 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000754 |\n", + "| n_updates | 18384 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11660 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1693 |\n", + "| total_timesteps | 123608 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00555 |\n", + "| n_updates | 18401 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11664 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1694 |\n", + "| total_timesteps | 123668 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00208 |\n", + "| n_updates | 18416 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11668 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1695 |\n", + "| total_timesteps | 123705 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00135 |\n", + "| n_updates | 18426 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11672 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1696 |\n", + "| total_timesteps | 123740 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00556 |\n", + "| n_updates | 18434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11676 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1697 |\n", + "| total_timesteps | 123800 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00369 |\n", + "| n_updates | 18449 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11680 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1699 |\n", + "| total_timesteps | 123876 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00459 |\n", + "| n_updates | 18468 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11684 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1699 |\n", + "| total_timesteps | 123919 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00474 |\n", + "| n_updates | 18479 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11688 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1700 |\n", + "| total_timesteps | 123952 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00203 |\n", + "| n_updates | 18487 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11692 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1701 |\n", + "| total_timesteps | 123975 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00234 |\n", + "| n_updates | 18493 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11696 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1701 |\n", + "| total_timesteps | 123998 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.003 |\n", + "| n_updates | 18499 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11700 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1702 |\n", + "| total_timesteps | 124022 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0113 |\n", + "| n_updates | 18505 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11704 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1702 |\n", + "| total_timesteps | 124059 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00234 |\n", + "| n_updates | 18514 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11708 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1704 |\n", + "| total_timesteps | 124127 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00332 |\n", + "| n_updates | 18531 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11712 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1705 |\n", + "| total_timesteps | 124204 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0033 |\n", + "| n_updates | 18550 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11716 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1708 |\n", + "| total_timesteps | 124322 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00209 |\n", + "| n_updates | 18580 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11720 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1709 |\n", + "| total_timesteps | 124382 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0047 |\n", + "| n_updates | 18595 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11724 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1710 |\n", + "| total_timesteps | 124426 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00141 |\n", + "| n_updates | 18606 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11728 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1712 |\n", + "| total_timesteps | 124503 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000858 |\n", + "| n_updates | 18625 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11732 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1713 |\n", + "| total_timesteps | 124577 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00162 |\n", + "| n_updates | 18644 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11736 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1714 |\n", + "| total_timesteps | 124629 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00458 |\n", + "| n_updates | 18657 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11740 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1716 |\n", + "| total_timesteps | 124721 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00307 |\n", + "| n_updates | 18680 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11744 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1718 |\n", + "| total_timesteps | 124800 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00438 |\n", + "| n_updates | 18699 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11748 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1719 |\n", + "| total_timesteps | 124835 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00971 |\n", + "| n_updates | 18708 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11752 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1720 |\n", + "| total_timesteps | 124913 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00767 |\n", + "| n_updates | 18728 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11756 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1721 |\n", + "| total_timesteps | 124955 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00752 |\n", + "| n_updates | 18738 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11760 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1722 |\n", + "| total_timesteps | 124990 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00158 |\n", + "| n_updates | 18747 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11764 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1723 |\n", + "| total_timesteps | 125032 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00077 |\n", + "| n_updates | 18757 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11768 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1724 |\n", + "| total_timesteps | 125076 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00103 |\n", + "| n_updates | 18768 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11772 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1725 |\n", + "| total_timesteps | 125125 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00893 |\n", + "| n_updates | 18781 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11776 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1725 |\n", + "| total_timesteps | 125161 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00143 |\n", + "| n_updates | 18790 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11780 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1726 |\n", + "| total_timesteps | 125196 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000886 |\n", + "| n_updates | 18798 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11784 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1727 |\n", + "| total_timesteps | 125256 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00311 |\n", + "| n_updates | 18813 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11788 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1729 |\n", + "| total_timesteps | 125331 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00709 |\n", + "| n_updates | 18832 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11792 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1730 |\n", + "| total_timesteps | 125404 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00643 |\n", + "| n_updates | 18850 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11796 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1731 |\n", + "| total_timesteps | 125441 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00645 |\n", + "| n_updates | 18860 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11800 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1732 |\n", + "| total_timesteps | 125508 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00489 |\n", + "| n_updates | 18876 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11804 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1733 |\n", + "| total_timesteps | 125568 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00197 |\n", + "| n_updates | 18891 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11808 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1734 |\n", + "| total_timesteps | 125609 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00389 |\n", + "| n_updates | 18902 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11812 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1735 |\n", + "| total_timesteps | 125644 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00234 |\n", + "| n_updates | 18910 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11816 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1737 |\n", + "| total_timesteps | 125740 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0126 |\n", + "| n_updates | 18934 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11820 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1738 |\n", + "| total_timesteps | 125776 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00992 |\n", + "| n_updates | 18943 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11824 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1739 |\n", + "| total_timesteps | 125862 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000779 |\n", + "| n_updates | 18965 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11828 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1740 |\n", + "| total_timesteps | 125907 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0026 |\n", + "| n_updates | 18976 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11832 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1741 |\n", + "| total_timesteps | 125945 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0014 |\n", + "| n_updates | 18986 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11836 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1742 |\n", + "| total_timesteps | 125991 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00234 |\n", + "| n_updates | 18997 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11840 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1743 |\n", + "| total_timesteps | 126026 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00667 |\n", + "| n_updates | 19006 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11844 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1744 |\n", + "| total_timesteps | 126102 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00177 |\n", + "| n_updates | 19025 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11848 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1745 |\n", + "| total_timesteps | 126137 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00186 |\n", + "| n_updates | 19034 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11852 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1745 |\n", + "| total_timesteps | 126164 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00186 |\n", + "| n_updates | 19040 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11856 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1747 |\n", + "| total_timesteps | 126231 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00811 |\n", + "| n_updates | 19057 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11860 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1748 |\n", + "| total_timesteps | 126277 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00157 |\n", + "| n_updates | 19069 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11864 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1749 |\n", + "| total_timesteps | 126303 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00164 |\n", + "| n_updates | 19075 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11868 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1749 |\n", + "| total_timesteps | 126338 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0057 |\n", + "| n_updates | 19084 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11872 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1750 |\n", + "| total_timesteps | 126383 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00181 |\n", + "| n_updates | 19095 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11876 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1751 |\n", + "| total_timesteps | 126418 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00734 |\n", + "| n_updates | 19104 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11880 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1752 |\n", + "| total_timesteps | 126441 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00393 |\n", + "| n_updates | 19110 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11884 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1753 |\n", + "| total_timesteps | 126528 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0156 |\n", + "| n_updates | 19131 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11888 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1754 |\n", + "| total_timesteps | 126564 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 19140 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11892 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1755 |\n", + "| total_timesteps | 126613 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00197 |\n", + "| n_updates | 19153 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11896 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1757 |\n", + "| total_timesteps | 126685 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00155 |\n", + "| n_updates | 19171 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11900 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1758 |\n", + "| total_timesteps | 126757 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00628 |\n", + "| n_updates | 19189 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11904 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1760 |\n", + "| total_timesteps | 126839 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00696 |\n", + "| n_updates | 19209 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 313 |\n", + "| ep_rew_mean | 2.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11908 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1762 |\n", + "| total_timesteps | 126927 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00158 |\n", + "| n_updates | 19231 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11912 |\n", + "| fps | 72 |\n", + "| time_elapsed | 1763 |\n", + "| total_timesteps | 126987 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00165 |\n", + "| n_updates | 19246 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11916 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1764 |\n", + "| total_timesteps | 127048 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00965 |\n", + "| n_updates | 19261 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11920 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1765 |\n", + "| total_timesteps | 127093 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00774 |\n", + "| n_updates | 19273 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11924 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1767 |\n", + "| total_timesteps | 127170 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00532 |\n", + "| n_updates | 19292 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 317 |\n", + "| ep_rew_mean | 2.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11928 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1768 |\n", + "| total_timesteps | 127246 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00239 |\n", + "| n_updates | 19311 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 318 |\n", + "| ep_rew_mean | 2.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11932 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1769 |\n", + "| total_timesteps | 127292 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00328 |\n", + "| n_updates | 19322 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11936 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1770 |\n", + "| total_timesteps | 127328 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00423 |\n", + "| n_updates | 19331 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11940 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1771 |\n", + "| total_timesteps | 127372 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00224 |\n", + "| n_updates | 19342 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11944 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1771 |\n", + "| total_timesteps | 127406 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00279 |\n", + "| n_updates | 19351 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 316 |\n", + "| ep_rew_mean | 2.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11948 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1773 |\n", + "| total_timesteps | 127501 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00324 |\n", + "| n_updates | 19375 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 319 |\n", + "| ep_rew_mean | 2.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11952 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1775 |\n", + "| total_timesteps | 127565 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00562 |\n", + "| n_updates | 19391 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 322 |\n", + "| ep_rew_mean | 2.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11956 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1776 |\n", + "| total_timesteps | 127649 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00385 |\n", + "| n_updates | 19412 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 322 |\n", + "| ep_rew_mean | 2.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11960 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1777 |\n", + "| total_timesteps | 127677 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00195 |\n", + "| n_updates | 19419 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 322 |\n", + "| ep_rew_mean | 2.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11964 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1778 |\n", + "| total_timesteps | 127703 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00153 |\n", + "| n_updates | 19425 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 321 |\n", + "| ep_rew_mean | 2.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11968 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1780 |\n", + "| total_timesteps | 127798 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000558 |\n", + "| n_updates | 19449 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 325 |\n", + "| ep_rew_mean | 2.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11972 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1783 |\n", + "| total_timesteps | 127918 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00118 |\n", + "| n_updates | 19479 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 329 |\n", + "| ep_rew_mean | 2.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11976 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1785 |\n", + "| total_timesteps | 128019 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00202 |\n", + "| n_updates | 19504 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 329 |\n", + "| ep_rew_mean | 2.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11980 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1786 |\n", + "| total_timesteps | 128046 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0027 |\n", + "| n_updates | 19511 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 329 |\n", + "| ep_rew_mean | 2.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11984 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1788 |\n", + "| total_timesteps | 128130 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00401 |\n", + "| n_updates | 19532 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 331 |\n", + "| ep_rew_mean | 2.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11988 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1790 |\n", + "| total_timesteps | 128224 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00962 |\n", + "| n_updates | 19555 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 333 |\n", + "| ep_rew_mean | 2.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11992 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1792 |\n", + "| total_timesteps | 128310 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00258 |\n", + "| n_updates | 19577 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 333 |\n", + "| ep_rew_mean | 2.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 11996 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1793 |\n", + "| total_timesteps | 128336 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00541 |\n", + "| n_updates | 19583 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 334 |\n", + "| ep_rew_mean | 2.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12000 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1795 |\n", + "| total_timesteps | 128422 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00485 |\n", + "| n_updates | 19605 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 334 |\n", + "| ep_rew_mean | 2.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12004 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1796 |\n", + "| total_timesteps | 128458 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00126 |\n", + "| n_updates | 19614 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 333 |\n", + "| ep_rew_mean | 2.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12008 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1796 |\n", + "| total_timesteps | 128495 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00191 |\n", + "| n_updates | 19623 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 334 |\n", + "| ep_rew_mean | 2.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12012 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1798 |\n", + "| total_timesteps | 128573 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0088 |\n", + "| n_updates | 19643 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 335 |\n", + "| ep_rew_mean | 2.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12016 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1799 |\n", + "| total_timesteps | 128630 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00508 |\n", + "| n_updates | 19657 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 335 |\n", + "| ep_rew_mean | 2.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12020 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1801 |\n", + "| total_timesteps | 128681 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0016 |\n", + "| n_updates | 19670 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 335 |\n", + "| ep_rew_mean | 2.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12024 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1802 |\n", + "| total_timesteps | 128743 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00196 |\n", + "| n_updates | 19685 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 337 |\n", + "| ep_rew_mean | 2.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12028 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1804 |\n", + "| total_timesteps | 128853 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0013 |\n", + "| n_updates | 19713 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 339 |\n", + "| ep_rew_mean | 2.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12032 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1806 |\n", + "| total_timesteps | 128936 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00291 |\n", + "| n_updates | 19733 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 343 |\n", + "| ep_rew_mean | 2.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12036 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1809 |\n", + "| total_timesteps | 129041 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000557 |\n", + "| n_updates | 19760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 344 |\n", + "| ep_rew_mean | 2.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12040 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1811 |\n", + "| total_timesteps | 129127 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00119 |\n", + "| n_updates | 19781 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 344 |\n", + "| ep_rew_mean | 2.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12044 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1813 |\n", + "| total_timesteps | 129252 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00174 |\n", + "| n_updates | 19812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 347 |\n", + "| ep_rew_mean | 3.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12048 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1816 |\n", + "| total_timesteps | 129372 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00891 |\n", + "| n_updates | 19842 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 350 |\n", + "| ep_rew_mean | 3.07 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12052 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1817 |\n", + "| total_timesteps | 129465 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00147 |\n", + "| n_updates | 19866 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 352 |\n", + "| ep_rew_mean | 3.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12056 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1819 |\n", + "| total_timesteps | 129547 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00118 |\n", + "| n_updates | 19886 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 354 |\n", + "| ep_rew_mean | 3.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12060 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1821 |\n", + "| total_timesteps | 129621 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0032 |\n", + "| n_updates | 19905 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 354 |\n", + "| ep_rew_mean | 3.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12064 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1822 |\n", + "| total_timesteps | 129687 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00156 |\n", + "| n_updates | 19921 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 356 |\n", + "| ep_rew_mean | 3.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12068 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1823 |\n", + "| total_timesteps | 129738 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00234 |\n", + "| n_updates | 19934 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 358 |\n", + "| ep_rew_mean | 3.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12072 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1824 |\n", + "| total_timesteps | 129781 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00374 |\n", + "| n_updates | 19945 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 359 |\n", + "| ep_rew_mean | 3.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12076 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1826 |\n", + "| total_timesteps | 129842 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00964 |\n", + "| n_updates | 19960 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 360 |\n", + "| ep_rew_mean | 3.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12080 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1827 |\n", + "| total_timesteps | 129918 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00448 |\n", + "| n_updates | 19979 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 360 |\n", + "| ep_rew_mean | 3.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12084 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1829 |\n", + "| total_timesteps | 129992 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00748 |\n", + "| n_updates | 19997 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 361 |\n", + "| ep_rew_mean | 3.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12088 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1830 |\n", + "| total_timesteps | 130035 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0101 |\n", + "| n_updates | 20008 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 360 |\n", + "| ep_rew_mean | 3.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12092 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1831 |\n", + "| total_timesteps | 130105 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00981 |\n", + "| n_updates | 20026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 361 |\n", + "| ep_rew_mean | 3.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12096 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1833 |\n", + "| total_timesteps | 130181 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00637 |\n", + "| n_updates | 20045 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 362 |\n", + "| ep_rew_mean | 3.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12100 |\n", + "| fps | 71 |\n", + "| time_elapsed | 1833 |\n", + "| total_timesteps | 130223 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00549 |\n", + "| n_updates | 20055 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 362 |\n", + "| ep_rew_mean | 3.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12104 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1835 |\n", + "| total_timesteps | 130278 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00498 |\n", + "| n_updates | 20069 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 363 |\n", + "| ep_rew_mean | 3.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12108 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1836 |\n", + "| total_timesteps | 130315 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0108 |\n", + "| n_updates | 20078 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 366 |\n", + "| ep_rew_mean | 3.35 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12112 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1839 |\n", + "| total_timesteps | 130466 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00966 |\n", + "| n_updates | 20116 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 365 |\n", + "| ep_rew_mean | 3.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12116 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1840 |\n", + "| total_timesteps | 130517 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00399 |\n", + "| n_updates | 20129 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 366 |\n", + "| ep_rew_mean | 3.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12120 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1841 |\n", + "| total_timesteps | 130579 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00165 |\n", + "| n_updates | 20144 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 366 |\n", + "| ep_rew_mean | 3.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12124 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1842 |\n", + "| total_timesteps | 130604 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00601 |\n", + "| n_updates | 20150 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 365 |\n", + "| ep_rew_mean | 3.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12128 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1843 |\n", + "| total_timesteps | 130641 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00597 |\n", + "| n_updates | 20160 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 364 |\n", + "| ep_rew_mean | 3.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12132 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1843 |\n", + "| total_timesteps | 130679 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00177 |\n", + "| n_updates | 20169 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 365 |\n", + "| ep_rew_mean | 3.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12136 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1844 |\n", + "| total_timesteps | 130715 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00202 |\n", + "| n_updates | 20178 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 364 |\n", + "| ep_rew_mean | 3.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12140 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1845 |\n", + "| total_timesteps | 130751 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00289 |\n", + "| n_updates | 20187 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 364 |\n", + "| ep_rew_mean | 3.31 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12144 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1847 |\n", + "| total_timesteps | 130842 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00808 |\n", + "| n_updates | 20210 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 367 |\n", + "| ep_rew_mean | 3.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12148 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1848 |\n", + "| total_timesteps | 130887 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00591 |\n", + "| n_updates | 20221 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 369 |\n", + "| ep_rew_mean | 3.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12152 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1850 |\n", + "| total_timesteps | 130969 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00468 |\n", + "| n_updates | 20242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 372 |\n", + "| ep_rew_mean | 3.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12156 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1852 |\n", + "| total_timesteps | 131104 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0111 |\n", + "| n_updates | 20275 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 373 |\n", + "| ep_rew_mean | 3.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12160 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1854 |\n", + "| total_timesteps | 131175 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00309 |\n", + "| n_updates | 20293 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 373 |\n", + "| ep_rew_mean | 3.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12164 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1856 |\n", + "| total_timesteps | 131268 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00417 |\n", + "| n_updates | 20316 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 374 |\n", + "| ep_rew_mean | 3.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12168 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1857 |\n", + "| total_timesteps | 131346 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00243 |\n", + "| n_updates | 20336 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 376 |\n", + "| ep_rew_mean | 3.52 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12172 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1859 |\n", + "| total_timesteps | 131397 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00406 |\n", + "| n_updates | 20349 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 378 |\n", + "| ep_rew_mean | 3.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12176 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1860 |\n", + "| total_timesteps | 131490 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00825 |\n", + "| n_updates | 20372 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 378 |\n", + "| ep_rew_mean | 3.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12180 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1862 |\n", + "| total_timesteps | 131573 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0125 |\n", + "| n_updates | 20393 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 378 |\n", + "| ep_rew_mean | 3.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12184 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1864 |\n", + "| total_timesteps | 131652 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00305 |\n", + "| n_updates | 20412 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 381 |\n", + "| ep_rew_mean | 3.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12188 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1865 |\n", + "| total_timesteps | 131740 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00254 |\n", + "| n_updates | 20434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 383 |\n", + "| ep_rew_mean | 3.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12192 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1867 |\n", + "| total_timesteps | 131812 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00782 |\n", + "| n_updates | 20452 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 386 |\n", + "| ep_rew_mean | 3.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12196 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1869 |\n", + "| total_timesteps | 131923 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00429 |\n", + "| n_updates | 20480 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 389 |\n", + "| ep_rew_mean | 3.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12200 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1870 |\n", + "| total_timesteps | 131969 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0145 |\n", + "| n_updates | 20492 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 389 |\n", + "| ep_rew_mean | 3.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12204 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1872 |\n", + "| total_timesteps | 132060 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00548 |\n", + "| n_updates | 20514 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 390 |\n", + "| ep_rew_mean | 3.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12208 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1874 |\n", + "| total_timesteps | 132142 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0131 |\n", + "| n_updates | 20535 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 391 |\n", + "| ep_rew_mean | 3.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12212 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1876 |\n", + "| total_timesteps | 132242 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00844 |\n", + "| n_updates | 20560 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 392 |\n", + "| ep_rew_mean | 3.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12216 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1877 |\n", + "| total_timesteps | 132307 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00367 |\n", + "| n_updates | 20576 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 390 |\n", + "| ep_rew_mean | 3.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12220 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1878 |\n", + "| total_timesteps | 132374 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0165 |\n", + "| n_updates | 20593 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 390 |\n", + "| ep_rew_mean | 3.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12224 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1880 |\n", + "| total_timesteps | 132457 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00375 |\n", + "| n_updates | 20614 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 392 |\n", + "| ep_rew_mean | 3.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12228 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1882 |\n", + "| total_timesteps | 132538 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00226 |\n", + "| n_updates | 20634 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 391 |\n", + "| ep_rew_mean | 3.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12232 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1883 |\n", + "| total_timesteps | 132590 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00513 |\n", + "| n_updates | 20647 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 393 |\n", + "| ep_rew_mean | 3.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12236 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1885 |\n", + "| total_timesteps | 132681 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00897 |\n", + "| n_updates | 20670 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 391 |\n", + "| ep_rew_mean | 3.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12240 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1886 |\n", + "| total_timesteps | 132731 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00136 |\n", + "| n_updates | 20682 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 391 |\n", + "| ep_rew_mean | 3.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12244 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1887 |\n", + "| total_timesteps | 132803 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00284 |\n", + "| n_updates | 20700 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 391 |\n", + "| ep_rew_mean | 3.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12248 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1888 |\n", + "| total_timesteps | 132845 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00503 |\n", + "| n_updates | 20711 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 392 |\n", + "| ep_rew_mean | 3.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12252 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1890 |\n", + "| total_timesteps | 132916 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0024 |\n", + "| n_updates | 20728 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 393 |\n", + "| ep_rew_mean | 3.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12256 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1892 |\n", + "| total_timesteps | 133048 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00298 |\n", + "| n_updates | 20761 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 395 |\n", + "| ep_rew_mean | 3.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12260 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1893 |\n", + "| total_timesteps | 133104 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00355 |\n", + "| n_updates | 20775 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 395 |\n", + "| ep_rew_mean | 3.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12264 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1895 |\n", + "| total_timesteps | 133194 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00246 |\n", + "| n_updates | 20798 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 397 |\n", + "| ep_rew_mean | 4.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12268 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1896 |\n", + "| total_timesteps | 133252 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00306 |\n", + "| n_updates | 20812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 398 |\n", + "| ep_rew_mean | 4.03 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12272 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1898 |\n", + "| total_timesteps | 133329 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00501 |\n", + "| n_updates | 20832 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 399 |\n", + "| ep_rew_mean | 4.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12276 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1899 |\n", + "| total_timesteps | 133387 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0087 |\n", + "| n_updates | 20846 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 401 |\n", + "| ep_rew_mean | 4.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12280 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1900 |\n", + "| total_timesteps | 133463 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00394 |\n", + "| n_updates | 20865 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 401 |\n", + "| ep_rew_mean | 4.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12284 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1902 |\n", + "| total_timesteps | 133528 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00678 |\n", + "| n_updates | 20881 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 402 |\n", + "| ep_rew_mean | 4.09 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12288 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1903 |\n", + "| total_timesteps | 133587 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00125 |\n", + "| n_updates | 20896 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 400 |\n", + "| ep_rew_mean | 4.06 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12292 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1905 |\n", + "| total_timesteps | 133671 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0033 |\n", + "| n_updates | 20917 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 402 |\n", + "| ep_rew_mean | 4.09 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12296 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1907 |\n", + "| total_timesteps | 133771 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00168 |\n", + "| n_updates | 20942 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 404 |\n", + "| ep_rew_mean | 4.12 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12300 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1908 |\n", + "| total_timesteps | 133834 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00297 |\n", + "| n_updates | 20958 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 404 |\n", + "| ep_rew_mean | 4.12 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12304 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1909 |\n", + "| total_timesteps | 133867 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00588 |\n", + "| n_updates | 20966 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 403 |\n", + "| ep_rew_mean | 4.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12308 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1910 |\n", + "| total_timesteps | 133941 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00405 |\n", + "| n_updates | 20985 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 405 |\n", + "| ep_rew_mean | 4.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12312 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1912 |\n", + "| total_timesteps | 134049 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00267 |\n", + "| n_updates | 21012 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 405 |\n", + "| ep_rew_mean | 4.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12316 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1913 |\n", + "| total_timesteps | 134106 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00696 |\n", + "| n_updates | 21026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 407 |\n", + "| ep_rew_mean | 4.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12320 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1915 |\n", + "| total_timesteps | 134170 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00377 |\n", + "| n_updates | 21042 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 407 |\n", + "| ep_rew_mean | 4.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12324 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1915 |\n", + "| total_timesteps | 134202 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0132 |\n", + "| n_updates | 21050 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 406 |\n", + "| ep_rew_mean | 4.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12328 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1917 |\n", + "| total_timesteps | 134307 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00267 |\n", + "| n_updates | 21076 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 409 |\n", + "| ep_rew_mean | 4.22 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12332 |\n", + "| fps | 70 |\n", + "| time_elapsed | 1920 |\n", + "| total_timesteps | 134416 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00467 |\n", + "| n_updates | 21103 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 411 |\n", + "| ep_rew_mean | 4.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12336 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1921 |\n", + "| total_timesteps | 134493 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0105 |\n", + "| n_updates | 21123 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 413 |\n", + "| ep_rew_mean | 4.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12340 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1923 |\n", + "| total_timesteps | 134577 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00363 |\n", + "| n_updates | 21144 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 413 |\n", + "| ep_rew_mean | 4.32 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12344 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1924 |\n", + "| total_timesteps | 134621 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00467 |\n", + "| n_updates | 21155 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 412 |\n", + "| ep_rew_mean | 4.29 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12348 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1926 |\n", + "| total_timesteps | 134723 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00176 |\n", + "| n_updates | 21180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 416 |\n", + "| ep_rew_mean | 4.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12352 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1928 |\n", + "| total_timesteps | 134849 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00699 |\n", + "| n_updates | 21212 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 419 |\n", + "| ep_rew_mean | 4.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12356 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1930 |\n", + "| total_timesteps | 134914 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0145 |\n", + "| n_updates | 21228 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 420 |\n", + "| ep_rew_mean | 4.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12360 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1931 |\n", + "| total_timesteps | 134996 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00185 |\n", + "| n_updates | 21248 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 420 |\n", + "| ep_rew_mean | 4.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12364 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1933 |\n", + "| total_timesteps | 135096 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00203 |\n", + "| n_updates | 21273 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 423 |\n", + "| ep_rew_mean | 4.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12368 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1934 |\n", + "| total_timesteps | 135127 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00387 |\n", + "| n_updates | 21281 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 423 |\n", + "| ep_rew_mean | 4.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12372 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1934 |\n", + "| total_timesteps | 135162 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00579 |\n", + "| n_updates | 21290 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 424 |\n", + "| ep_rew_mean | 4.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12376 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1936 |\n", + "| total_timesteps | 135243 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000712 |\n", + "| n_updates | 21310 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 425 |\n", + "| ep_rew_mean | 4.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12380 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1937 |\n", + "| total_timesteps | 135287 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00167 |\n", + "| n_updates | 21321 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 425 |\n", + "| ep_rew_mean | 4.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12384 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1939 |\n", + "| total_timesteps | 135360 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00487 |\n", + "| n_updates | 21339 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 425 |\n", + "| ep_rew_mean | 4.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12388 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1941 |\n", + "| total_timesteps | 135460 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0135 |\n", + "| n_updates | 21364 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 428 |\n", + "| ep_rew_mean | 4.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12392 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1942 |\n", + "| total_timesteps | 135529 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00872 |\n", + "| n_updates | 21382 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 430 |\n", + "| ep_rew_mean | 4.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12396 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1945 |\n", + "| total_timesteps | 135683 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00212 |\n", + "| n_updates | 21420 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 431 |\n", + "| ep_rew_mean | 4.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12400 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1947 |\n", + "| total_timesteps | 135760 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00241 |\n", + "| n_updates | 21439 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 431 |\n", + "| ep_rew_mean | 4.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12404 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1947 |\n", + "| total_timesteps | 135793 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00825 |\n", + "| n_updates | 21448 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 429 |\n", + "| ep_rew_mean | 4.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12408 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1949 |\n", + "| total_timesteps | 135861 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00695 |\n", + "| n_updates | 21465 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 428 |\n", + "| ep_rew_mean | 4.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12412 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1951 |\n", + "| total_timesteps | 135963 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00559 |\n", + "| n_updates | 21490 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 431 |\n", + "| ep_rew_mean | 4.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12416 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1952 |\n", + "| total_timesteps | 136021 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00126 |\n", + "| n_updates | 21505 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 431 |\n", + "| ep_rew_mean | 4.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12420 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1953 |\n", + "| total_timesteps | 136097 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00994 |\n", + "| n_updates | 21524 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 431 |\n", + "| ep_rew_mean | 4.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12424 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1955 |\n", + "| total_timesteps | 136194 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00392 |\n", + "| n_updates | 21548 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 432 |\n", + "| ep_rew_mean | 4.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12428 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1958 |\n", + "| total_timesteps | 136306 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00279 |\n", + "| n_updates | 21576 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 433 |\n", + "| ep_rew_mean | 4.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12432 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1959 |\n", + "| total_timesteps | 136389 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0151 |\n", + "| n_updates | 21597 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 435 |\n", + "| ep_rew_mean | 4.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12436 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1961 |\n", + "| total_timesteps | 136442 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00865 |\n", + "| n_updates | 21610 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 438 |\n", + "| ep_rew_mean | 4.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12440 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1963 |\n", + "| total_timesteps | 136558 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00178 |\n", + "| n_updates | 21639 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 438 |\n", + "| ep_rew_mean | 4.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12444 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1964 |\n", + "| total_timesteps | 136639 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00375 |\n", + "| n_updates | 21659 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 441 |\n", + "| ep_rew_mean | 4.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12448 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1966 |\n", + "| total_timesteps | 136727 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00251 |\n", + "| n_updates | 21681 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 440 |\n", + "| ep_rew_mean | 4.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12452 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1967 |\n", + "| total_timesteps | 136768 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0075 |\n", + "| n_updates | 21691 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 439 |\n", + "| ep_rew_mean | 4.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12456 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1969 |\n", + "| total_timesteps | 136867 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00373 |\n", + "| n_updates | 21716 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 443 |\n", + "| ep_rew_mean | 4.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12460 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1972 |\n", + "| total_timesteps | 136993 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00648 |\n", + "| n_updates | 21748 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 443 |\n", + "| ep_rew_mean | 4.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12464 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1972 |\n", + "| total_timesteps | 137040 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00278 |\n", + "| n_updates | 21759 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 445 |\n", + "| ep_rew_mean | 5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12468 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1975 |\n", + "| total_timesteps | 137151 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00792 |\n", + "| n_updates | 21787 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 445 |\n", + "| ep_rew_mean | 4.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12472 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1977 |\n", + "| total_timesteps | 137263 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00922 |\n", + "| n_updates | 21815 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 442 |\n", + "| ep_rew_mean | 4.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12476 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1978 |\n", + "| total_timesteps | 137334 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0075 |\n", + "| n_updates | 21833 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 446 |\n", + "| ep_rew_mean | 5.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12480 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1980 |\n", + "| total_timesteps | 137425 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00149 |\n", + "| n_updates | 21856 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 446 |\n", + "| ep_rew_mean | 5.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12484 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1982 |\n", + "| total_timesteps | 137499 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00348 |\n", + "| n_updates | 21874 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 445 |\n", + "| ep_rew_mean | 5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12488 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1982 |\n", + "| total_timesteps | 137524 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00101 |\n", + "| n_updates | 21880 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 443 |\n", + "| ep_rew_mean | 4.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12492 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1983 |\n", + "| total_timesteps | 137584 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00333 |\n", + "| n_updates | 21895 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 442 |\n", + "| ep_rew_mean | 4.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12496 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1984 |\n", + "| total_timesteps | 137610 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00172 |\n", + "| n_updates | 21902 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 440 |\n", + "| ep_rew_mean | 4.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12500 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1985 |\n", + "| total_timesteps | 137656 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00672 |\n", + "| n_updates | 21913 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 440 |\n", + "| ep_rew_mean | 4.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12504 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1986 |\n", + "| total_timesteps | 137729 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00422 |\n", + "| n_updates | 21932 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 442 |\n", + "| ep_rew_mean | 4.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12508 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1987 |\n", + "| total_timesteps | 137772 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00887 |\n", + "| n_updates | 21942 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 442 |\n", + "| ep_rew_mean | 4.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12512 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1989 |\n", + "| total_timesteps | 137853 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000924 |\n", + "| n_updates | 21963 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 442 |\n", + "| ep_rew_mean | 4.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12516 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1990 |\n", + "| total_timesteps | 137916 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00299 |\n", + "| n_updates | 21978 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 444 |\n", + "| ep_rew_mean | 4.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12520 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1992 |\n", + "| total_timesteps | 137998 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00529 |\n", + "| n_updates | 21999 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 444 |\n", + "| ep_rew_mean | 4.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12524 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1993 |\n", + "| total_timesteps | 138050 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00515 |\n", + "| n_updates | 22012 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 442 |\n", + "| ep_rew_mean | 4.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12528 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1994 |\n", + "| total_timesteps | 138101 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00597 |\n", + "| n_updates | 22025 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 441 |\n", + "| ep_rew_mean | 4.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12532 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1996 |\n", + "| total_timesteps | 138172 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00439 |\n", + "| n_updates | 22042 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 440 |\n", + "| ep_rew_mean | 4.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12536 |\n", + "| fps | 69 |\n", + "| time_elapsed | 1999 |\n", + "| total_timesteps | 138324 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00438 |\n", + "| n_updates | 22080 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 442 |\n", + "| ep_rew_mean | 4.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12540 |\n", + "| fps | 69 |\n", + "| time_elapsed | 2001 |\n", + "| total_timesteps | 138416 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0041 |\n", + "| n_updates | 22103 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 442 |\n", + "| ep_rew_mean | 4.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12544 |\n", + "| fps | 69 |\n", + "| time_elapsed | 2004 |\n", + "| total_timesteps | 138577 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00454 |\n", + "| n_updates | 22144 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 443 |\n", + "| ep_rew_mean | 5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12548 |\n", + "| fps | 69 |\n", + "| time_elapsed | 2005 |\n", + "| total_timesteps | 138618 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00922 |\n", + "| n_updates | 22154 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 440 |\n", + "| ep_rew_mean | 4.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12552 |\n", + "| fps | 69 |\n", + "| time_elapsed | 2006 |\n", + "| total_timesteps | 138651 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000709 |\n", + "| n_updates | 22162 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 437 |\n", + "| ep_rew_mean | 4.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12556 |\n", + "| fps | 69 |\n", + "| time_elapsed | 2007 |\n", + "| total_timesteps | 138696 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0016 |\n", + "| n_updates | 22173 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 435 |\n", + "| ep_rew_mean | 4.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12560 |\n", + "| fps | 69 |\n", + "| time_elapsed | 2008 |\n", + "| total_timesteps | 138735 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00254 |\n", + "| n_updates | 22183 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 435 |\n", + "| ep_rew_mean | 4.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12564 |\n", + "| fps | 69 |\n", + "| time_elapsed | 2010 |\n", + "| total_timesteps | 138835 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00426 |\n", + "| n_updates | 22208 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 437 |\n", + "| ep_rew_mean | 4.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12568 |\n", + "| fps | 69 |\n", + "| time_elapsed | 2011 |\n", + "| total_timesteps | 138907 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00404 |\n", + "| n_updates | 22226 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 437 |\n", + "| ep_rew_mean | 4.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12572 |\n", + "| fps | 69 |\n", + "| time_elapsed | 2012 |\n", + "| total_timesteps | 138953 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00958 |\n", + "| n_updates | 22238 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 438 |\n", + "| ep_rew_mean | 4.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12576 |\n", + "| fps | 69 |\n", + "| time_elapsed | 2014 |\n", + "| total_timesteps | 139037 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0034 |\n", + "| n_updates | 22259 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 440 |\n", + "| ep_rew_mean | 5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12580 |\n", + "| fps | 69 |\n", + "| time_elapsed | 2016 |\n", + "| total_timesteps | 139138 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0117 |\n", + "| n_updates | 22284 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 440 |\n", + "| ep_rew_mean | 5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12584 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2017 |\n", + "| total_timesteps | 139228 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000964 |\n", + "| n_updates | 22306 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 442 |\n", + "| ep_rew_mean | 5.06 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12588 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2020 |\n", + "| total_timesteps | 139365 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00411 |\n", + "| n_updates | 22341 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 445 |\n", + "| ep_rew_mean | 5.12 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12592 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2023 |\n", + "| total_timesteps | 139488 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0044 |\n", + "| n_updates | 22371 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 448 |\n", + "| ep_rew_mean | 5.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12596 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2024 |\n", + "| total_timesteps | 139569 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00335 |\n", + "| n_updates | 22392 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 447 |\n", + "| ep_rew_mean | 5.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12600 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2025 |\n", + "| total_timesteps | 139629 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00393 |\n", + "| n_updates | 22407 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 447 |\n", + "| ep_rew_mean | 5.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12604 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2027 |\n", + "| total_timesteps | 139715 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00812 |\n", + "| n_updates | 22428 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 449 |\n", + "| ep_rew_mean | 5.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12608 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2029 |\n", + "| total_timesteps | 139806 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0101 |\n", + "| n_updates | 22451 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 446 |\n", + "| ep_rew_mean | 5.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12612 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2030 |\n", + "| total_timesteps | 139874 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0116 |\n", + "| n_updates | 22468 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 449 |\n", + "| ep_rew_mean | 5.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12616 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2032 |\n", + "| total_timesteps | 139985 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00157 |\n", + "| n_updates | 22496 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 450 |\n", + "| ep_rew_mean | 5.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12620 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2034 |\n", + "| total_timesteps | 140069 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00555 |\n", + "| n_updates | 22517 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 450 |\n", + "| ep_rew_mean | 5.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12624 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2036 |\n", + "| total_timesteps | 140162 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00217 |\n", + "| n_updates | 22540 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 453 |\n", + "| ep_rew_mean | 5.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12628 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2038 |\n", + "| total_timesteps | 140294 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0121 |\n", + "| n_updates | 22573 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 457 |\n", + "| ep_rew_mean | 5.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12632 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2040 |\n", + "| total_timesteps | 140396 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 22598 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 459 |\n", + "| ep_rew_mean | 5.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12636 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2041 |\n", + "| total_timesteps | 140439 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0131 |\n", + "| n_updates | 22609 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 461 |\n", + "| ep_rew_mean | 5.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12640 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2043 |\n", + "| total_timesteps | 140519 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0188 |\n", + "| n_updates | 22629 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 461 |\n", + "| ep_rew_mean | 5.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12644 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2045 |\n", + "| total_timesteps | 140622 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0103 |\n", + "| n_updates | 22655 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 461 |\n", + "| ep_rew_mean | 5.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12648 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2046 |\n", + "| total_timesteps | 140657 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00664 |\n", + "| n_updates | 22664 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 461 |\n", + "| ep_rew_mean | 5.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12652 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2048 |\n", + "| total_timesteps | 140773 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0104 |\n", + "| n_updates | 22693 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 461 |\n", + "| ep_rew_mean | 5.42 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12656 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2050 |\n", + "| total_timesteps | 140880 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0202 |\n", + "| n_updates | 22719 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 463 |\n", + "| ep_rew_mean | 5.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12660 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2052 |\n", + "| total_timesteps | 140992 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00884 |\n", + "| n_updates | 22747 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 463 |\n", + "| ep_rew_mean | 5.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12664 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2054 |\n", + "| total_timesteps | 141100 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00468 |\n", + "| n_updates | 22774 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 464 |\n", + "| ep_rew_mean | 5.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12668 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2056 |\n", + "| total_timesteps | 141201 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0116 |\n", + "| n_updates | 22800 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 464 |\n", + "| ep_rew_mean | 5.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12672 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2057 |\n", + "| total_timesteps | 141234 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0064 |\n", + "| n_updates | 22808 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 463 |\n", + "| ep_rew_mean | 5.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12676 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2059 |\n", + "| total_timesteps | 141363 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00192 |\n", + "| n_updates | 22840 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 465 |\n", + "| ep_rew_mean | 5.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12680 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2061 |\n", + "| total_timesteps | 141433 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00758 |\n", + "| n_updates | 22858 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 465 |\n", + "| ep_rew_mean | 5.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12684 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2063 |\n", + "| total_timesteps | 141538 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00275 |\n", + "| n_updates | 22884 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 465 |\n", + "| ep_rew_mean | 5.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12688 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2064 |\n", + "| total_timesteps | 141583 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.005 |\n", + "| n_updates | 22895 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 464 |\n", + "| ep_rew_mean | 5.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12692 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2066 |\n", + "| total_timesteps | 141713 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00435 |\n", + "| n_updates | 22928 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 467 |\n", + "| ep_rew_mean | 5.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12696 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2068 |\n", + "| total_timesteps | 141811 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00294 |\n", + "| n_updates | 22952 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 467 |\n", + "| ep_rew_mean | 5.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12700 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2070 |\n", + "| total_timesteps | 141897 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00471 |\n", + "| n_updates | 22974 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 467 |\n", + "| ep_rew_mean | 5.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12704 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2072 |\n", + "| total_timesteps | 142004 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00235 |\n", + "| n_updates | 23000 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 468 |\n", + "| ep_rew_mean | 5.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12708 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2074 |\n", + "| total_timesteps | 142088 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00361 |\n", + "| n_updates | 23021 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 468 |\n", + "| ep_rew_mean | 5.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12712 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2076 |\n", + "| total_timesteps | 142189 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00365 |\n", + "| n_updates | 23047 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 468 |\n", + "| ep_rew_mean | 5.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12716 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2077 |\n", + "| total_timesteps | 142278 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0108 |\n", + "| n_updates | 23069 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 471 |\n", + "| ep_rew_mean | 5.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12720 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2080 |\n", + "| total_timesteps | 142410 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00438 |\n", + "| n_updates | 23102 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 471 |\n", + "| ep_rew_mean | 5.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12724 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2082 |\n", + "| total_timesteps | 142507 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00393 |\n", + "| n_updates | 23126 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 472 |\n", + "| ep_rew_mean | 5.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12728 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2084 |\n", + "| total_timesteps | 142606 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0062 |\n", + "| n_updates | 23151 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 474 |\n", + "| ep_rew_mean | 5.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12732 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2086 |\n", + "| total_timesteps | 142719 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00503 |\n", + "| n_updates | 23179 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 475 |\n", + "| ep_rew_mean | 5.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12736 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2088 |\n", + "| total_timesteps | 142793 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00433 |\n", + "| n_updates | 23198 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 477 |\n", + "| ep_rew_mean | 5.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12740 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2090 |\n", + "| total_timesteps | 142900 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0124 |\n", + "| n_updates | 23224 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 477 |\n", + "| ep_rew_mean | 5.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12744 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2091 |\n", + "| total_timesteps | 142966 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00476 |\n", + "| n_updates | 23241 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 477 |\n", + "| ep_rew_mean | 5.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12748 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2092 |\n", + "| total_timesteps | 143010 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00545 |\n", + "| n_updates | 23252 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 476 |\n", + "| ep_rew_mean | 5.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12752 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2093 |\n", + "| total_timesteps | 143072 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00632 |\n", + "| n_updates | 23267 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 477 |\n", + "| ep_rew_mean | 5.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12756 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2095 |\n", + "| total_timesteps | 143163 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00877 |\n", + "| n_updates | 23290 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 478 |\n", + "| ep_rew_mean | 5.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12760 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2098 |\n", + "| total_timesteps | 143302 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0017 |\n", + "| n_updates | 23325 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 478 |\n", + "| ep_rew_mean | 5.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12764 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2100 |\n", + "| total_timesteps | 143401 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0115 |\n", + "| n_updates | 23350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 478 |\n", + "| ep_rew_mean | 5.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12768 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2101 |\n", + "| total_timesteps | 143459 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00433 |\n", + "| n_updates | 23364 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 481 |\n", + "| ep_rew_mean | 5.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12772 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2103 |\n", + "| total_timesteps | 143560 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00945 |\n", + "| n_updates | 23389 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 480 |\n", + "| ep_rew_mean | 5.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12776 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2104 |\n", + "| total_timesteps | 143619 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00421 |\n", + "| n_updates | 23404 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 481 |\n", + "| ep_rew_mean | 5.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12780 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2106 |\n", + "| total_timesteps | 143724 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00718 |\n", + "| n_updates | 23430 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 481 |\n", + "| ep_rew_mean | 5.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12784 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2108 |\n", + "| total_timesteps | 143831 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00425 |\n", + "| n_updates | 23457 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 483 |\n", + "| ep_rew_mean | 5.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12788 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2110 |\n", + "| total_timesteps | 143946 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00348 |\n", + "| n_updates | 23486 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 485 |\n", + "| ep_rew_mean | 5.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12792 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2112 |\n", + "| total_timesteps | 144012 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.005 |\n", + "| n_updates | 23502 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 484 |\n", + "| ep_rew_mean | 5.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12796 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2113 |\n", + "| total_timesteps | 144068 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00803 |\n", + "| n_updates | 23516 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 484 |\n", + "| ep_rew_mean | 5.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12800 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2115 |\n", + "| total_timesteps | 144169 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00242 |\n", + "| n_updates | 23542 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 484 |\n", + "| ep_rew_mean | 5.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12804 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2118 |\n", + "| total_timesteps | 144311 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00321 |\n", + "| n_updates | 23577 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 489 |\n", + "| ep_rew_mean | 5.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12808 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2120 |\n", + "| total_timesteps | 144415 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0134 |\n", + "| n_updates | 23603 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 488 |\n", + "| ep_rew_mean | 5.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12812 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2122 |\n", + "| total_timesteps | 144540 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.002 |\n", + "| n_updates | 23634 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 492 |\n", + "| ep_rew_mean | 5.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12816 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2124 |\n", + "| total_timesteps | 144623 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00385 |\n", + "| n_updates | 23655 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 492 |\n", + "| ep_rew_mean | 5.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12820 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2125 |\n", + "| total_timesteps | 144700 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00224 |\n", + "| n_updates | 23674 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 492 |\n", + "| ep_rew_mean | 5.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12824 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2127 |\n", + "| total_timesteps | 144798 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00734 |\n", + "| n_updates | 23699 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 493 |\n", + "| ep_rew_mean | 5.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12828 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2129 |\n", + "| total_timesteps | 144871 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00218 |\n", + "| n_updates | 23717 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 491 |\n", + "| ep_rew_mean | 5.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12832 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2130 |\n", + "| total_timesteps | 144932 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0076 |\n", + "| n_updates | 23732 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 491 |\n", + "| ep_rew_mean | 5.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12836 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2132 |\n", + "| total_timesteps | 145018 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00762 |\n", + "| n_updates | 23754 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 491 |\n", + "| ep_rew_mean | 5.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12840 |\n", + "| fps | 68 |\n", + "| time_elapsed | 2133 |\n", + "| total_timesteps | 145091 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00244 |\n", + "| n_updates | 23772 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 491 |\n", + "| ep_rew_mean | 5.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12844 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2136 |\n", + "| total_timesteps | 145221 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00635 |\n", + "| n_updates | 23805 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 497 |\n", + "| ep_rew_mean | 6.06 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12848 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2138 |\n", + "| total_timesteps | 145333 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0134 |\n", + "| n_updates | 23833 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 495 |\n", + "| ep_rew_mean | 6.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12852 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2140 |\n", + "| total_timesteps | 145459 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00843 |\n", + "| n_updates | 23864 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 495 |\n", + "| ep_rew_mean | 6.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12856 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2142 |\n", + "| total_timesteps | 145534 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0112 |\n", + "| n_updates | 23883 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 495 |\n", + "| ep_rew_mean | 6.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12860 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2144 |\n", + "| total_timesteps | 145632 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0173 |\n", + "| n_updates | 23907 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 495 |\n", + "| ep_rew_mean | 6.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12864 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2145 |\n", + "| total_timesteps | 145699 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00225 |\n", + "| n_updates | 23924 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 495 |\n", + "| ep_rew_mean | 6.01 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12868 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2147 |\n", + "| total_timesteps | 145792 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00367 |\n", + "| n_updates | 23947 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 499 |\n", + "| ep_rew_mean | 6.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12872 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2149 |\n", + "| total_timesteps | 145928 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00629 |\n", + "| n_updates | 23981 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 499 |\n", + "| ep_rew_mean | 6.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12876 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2150 |\n", + "| total_timesteps | 145973 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0116 |\n", + "| n_updates | 23993 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 502 |\n", + "| ep_rew_mean | 6.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12880 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2152 |\n", + "| total_timesteps | 146077 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00507 |\n", + "| n_updates | 24019 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 502 |\n", + "| ep_rew_mean | 6.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12884 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2154 |\n", + "| total_timesteps | 146171 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0041 |\n", + "| n_updates | 24042 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 504 |\n", + "| ep_rew_mean | 6.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12888 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2157 |\n", + "| total_timesteps | 146298 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0073 |\n", + "| n_updates | 24074 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 503 |\n", + "| ep_rew_mean | 6.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12892 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2158 |\n", + "| total_timesteps | 146377 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00539 |\n", + "| n_updates | 24094 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 502 |\n", + "| ep_rew_mean | 6.13 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12896 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2160 |\n", + "| total_timesteps | 146447 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00557 |\n", + "| n_updates | 24111 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 501 |\n", + "| ep_rew_mean | 6.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12900 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2161 |\n", + "| total_timesteps | 146530 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0096 |\n", + "| n_updates | 24132 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 501 |\n", + "| ep_rew_mean | 6.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12904 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2164 |\n", + "| total_timesteps | 146654 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00479 |\n", + "| n_updates | 24163 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 504 |\n", + "| ep_rew_mean | 6.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12908 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2166 |\n", + "| total_timesteps | 146753 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00926 |\n", + "| n_updates | 24188 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 506 |\n", + "| ep_rew_mean | 6.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12912 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2168 |\n", + "| total_timesteps | 146869 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00101 |\n", + "| n_updates | 24217 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 506 |\n", + "| ep_rew_mean | 6.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12916 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2169 |\n", + "| total_timesteps | 146946 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00369 |\n", + "| n_updates | 24236 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 510 |\n", + "| ep_rew_mean | 6.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12920 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2172 |\n", + "| total_timesteps | 147090 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00301 |\n", + "| n_updates | 24272 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 510 |\n", + "| ep_rew_mean | 6.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12924 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2173 |\n", + "| total_timesteps | 147137 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00233 |\n", + "| n_updates | 24284 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 507 |\n", + "| ep_rew_mean | 6.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12928 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2176 |\n", + "| total_timesteps | 147278 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0115 |\n", + "| n_updates | 24319 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 510 |\n", + "| ep_rew_mean | 6.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12932 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2178 |\n", + "| total_timesteps | 147362 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0033 |\n", + "| n_updates | 24340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 511 |\n", + "| ep_rew_mean | 6.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12936 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2179 |\n", + "| total_timesteps | 147451 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0034 |\n", + "| n_updates | 24362 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 510 |\n", + "| ep_rew_mean | 6.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12940 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2181 |\n", + "| total_timesteps | 147560 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00292 |\n", + "| n_updates | 24389 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 510 |\n", + "| ep_rew_mean | 6.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12944 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2182 |\n", + "| total_timesteps | 147608 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00341 |\n", + "| n_updates | 24401 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 508 |\n", + "| ep_rew_mean | 6.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12948 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2184 |\n", + "| total_timesteps | 147693 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00721 |\n", + "| n_updates | 24423 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 509 |\n", + "| ep_rew_mean | 6.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12952 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2186 |\n", + "| total_timesteps | 147797 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00555 |\n", + "| n_updates | 24449 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 509 |\n", + "| ep_rew_mean | 6.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12956 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2187 |\n", + "| total_timesteps | 147832 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0106 |\n", + "| n_updates | 24457 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 508 |\n", + "| ep_rew_mean | 6.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12960 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2189 |\n", + "| total_timesteps | 147952 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00332 |\n", + "| n_updates | 24487 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 508 |\n", + "| ep_rew_mean | 6.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12964 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2191 |\n", + "| total_timesteps | 148049 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00638 |\n", + "| n_updates | 24512 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 511 |\n", + "| ep_rew_mean | 6.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12968 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2194 |\n", + "| total_timesteps | 148190 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0129 |\n", + "| n_updates | 24547 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 511 |\n", + "| ep_rew_mean | 6.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12972 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2196 |\n", + "| total_timesteps | 148261 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0194 |\n", + "| n_updates | 24565 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 511 |\n", + "| ep_rew_mean | 6.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12976 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2197 |\n", + "| total_timesteps | 148324 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00293 |\n", + "| n_updates | 24580 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 512 |\n", + "| ep_rew_mean | 6.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12980 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2200 |\n", + "| total_timesteps | 148470 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00161 |\n", + "| n_updates | 24617 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 512 |\n", + "| ep_rew_mean | 6.3 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12984 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2202 |\n", + "| total_timesteps | 148570 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00279 |\n", + "| n_updates | 24642 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 513 |\n", + "| ep_rew_mean | 6.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12988 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2204 |\n", + "| total_timesteps | 148681 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00553 |\n", + "| n_updates | 24670 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 517 |\n", + "| ep_rew_mean | 6.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12992 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2205 |\n", + "| total_timesteps | 148761 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00878 |\n", + "| n_updates | 24690 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 518 |\n", + "| ep_rew_mean | 6.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 12996 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2207 |\n", + "| total_timesteps | 148856 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00577 |\n", + "| n_updates | 24713 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 519 |\n", + "| ep_rew_mean | 6.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13000 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2208 |\n", + "| total_timesteps | 148898 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00463 |\n", + "| n_updates | 24724 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 519 |\n", + "| ep_rew_mean | 6.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13004 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2210 |\n", + "| total_timesteps | 148983 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00503 |\n", + "| n_updates | 24745 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 521 |\n", + "| ep_rew_mean | 6.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13008 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2211 |\n", + "| total_timesteps | 149064 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.015 |\n", + "| n_updates | 24765 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 520 |\n", + "| ep_rew_mean | 6.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13012 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2213 |\n", + "| total_timesteps | 149143 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00124 |\n", + "| n_updates | 24785 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 521 |\n", + "| ep_rew_mean | 6.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13016 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2215 |\n", + "| total_timesteps | 149238 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00602 |\n", + "| n_updates | 24809 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 521 |\n", + "| ep_rew_mean | 6.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13020 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2216 |\n", + "| total_timesteps | 149301 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00221 |\n", + "| n_updates | 24825 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 521 |\n", + "| ep_rew_mean | 6.5 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13024 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2218 |\n", + "| total_timesteps | 149392 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00306 |\n", + "| n_updates | 24847 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 523 |\n", + "| ep_rew_mean | 6.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13028 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2220 |\n", + "| total_timesteps | 149476 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00252 |\n", + "| n_updates | 24868 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 524 |\n", + "| ep_rew_mean | 6.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13032 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2221 |\n", + "| total_timesteps | 149510 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0267 |\n", + "| n_updates | 24877 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 525 |\n", + "| ep_rew_mean | 6.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13036 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2224 |\n", + "| total_timesteps | 149654 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00387 |\n", + "| n_updates | 24913 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 524 |\n", + "| ep_rew_mean | 6.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13040 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2226 |\n", + "| total_timesteps | 149768 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00556 |\n", + "| n_updates | 24941 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 524 |\n", + "| ep_rew_mean | 6.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13044 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2230 |\n", + "| total_timesteps | 149926 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.000811 |\n", + "| n_updates | 24981 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 524 |\n", + "| ep_rew_mean | 6.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13048 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2230 |\n", + "| total_timesteps | 149954 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00209 |\n", + "| n_updates | 24988 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 524 |\n", + "| ep_rew_mean | 6.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13052 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2233 |\n", + "| total_timesteps | 150070 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0131 |\n", + "| n_updates | 25017 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 526 |\n", + "| ep_rew_mean | 6.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13056 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2234 |\n", + "| total_timesteps | 150147 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00584 |\n", + "| n_updates | 25036 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 529 |\n", + "| ep_rew_mean | 6.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13060 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2236 |\n", + "| total_timesteps | 150225 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0106 |\n", + "| n_updates | 25056 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 529 |\n", + "| ep_rew_mean | 6.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13064 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2238 |\n", + "| total_timesteps | 150313 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00534 |\n", + "| n_updates | 25078 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 528 |\n", + "| ep_rew_mean | 6.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13068 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2241 |\n", + "| total_timesteps | 150431 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00938 |\n", + "| n_updates | 25107 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13072 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2244 |\n", + "| total_timesteps | 150579 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00552 |\n", + "| n_updates | 25144 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 535 |\n", + "| ep_rew_mean | 6.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13076 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2246 |\n", + "| total_timesteps | 150685 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.019 |\n", + "| n_updates | 25171 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 6.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13080 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2248 |\n", + "| total_timesteps | 150804 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00762 |\n", + "| n_updates | 25200 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 6.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13084 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2251 |\n", + "| total_timesteps | 150942 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00419 |\n", + "| n_updates | 25235 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13088 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2253 |\n", + "| total_timesteps | 151002 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.012 |\n", + "| n_updates | 25250 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13092 |\n", + "| fps | 67 |\n", + "| time_elapsed | 2254 |\n", + "| total_timesteps | 151047 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00712 |\n", + "| n_updates | 25261 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13096 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2255 |\n", + "| total_timesteps | 151112 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0027 |\n", + "| n_updates | 25277 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 530 |\n", + "| ep_rew_mean | 6.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13100 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2256 |\n", + "| total_timesteps | 151147 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00578 |\n", + "| n_updates | 25286 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 530 |\n", + "| ep_rew_mean | 6.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13104 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2257 |\n", + "| total_timesteps | 151219 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0034 |\n", + "| n_updates | 25304 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 529 |\n", + "| ep_rew_mean | 6.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13108 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2260 |\n", + "| total_timesteps | 151351 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0129 |\n", + "| n_updates | 25337 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13112 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2262 |\n", + "| total_timesteps | 151420 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00399 |\n", + "| n_updates | 25354 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 530 |\n", + "| ep_rew_mean | 6.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13116 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2264 |\n", + "| total_timesteps | 151530 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0074 |\n", + "| n_updates | 25382 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13120 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2267 |\n", + "| total_timesteps | 151673 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00554 |\n", + "| n_updates | 25418 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13124 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2269 |\n", + "| total_timesteps | 151765 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00481 |\n", + "| n_updates | 25441 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13128 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2270 |\n", + "| total_timesteps | 151833 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0045 |\n", + "| n_updates | 25458 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13132 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2272 |\n", + "| total_timesteps | 151928 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0129 |\n", + "| n_updates | 25481 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13136 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2275 |\n", + "| total_timesteps | 152090 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00676 |\n", + "| n_updates | 25522 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13140 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2278 |\n", + "| total_timesteps | 152221 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0105 |\n", + "| n_updates | 25555 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13144 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2279 |\n", + "| total_timesteps | 152268 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.005 |\n", + "| n_updates | 25566 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 6.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13148 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2281 |\n", + "| total_timesteps | 152341 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00601 |\n", + "| n_updates | 25585 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 6.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13152 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2283 |\n", + "| total_timesteps | 152451 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00681 |\n", + "| n_updates | 25612 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 6.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13156 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2286 |\n", + "| total_timesteps | 152541 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0046 |\n", + "| n_updates | 25635 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13160 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2287 |\n", + "| total_timesteps | 152586 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00387 |\n", + "| n_updates | 25646 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13164 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2288 |\n", + "| total_timesteps | 152677 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0029 |\n", + "| n_updates | 25669 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13168 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2290 |\n", + "| total_timesteps | 152738 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00693 |\n", + "| n_updates | 25684 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13172 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2291 |\n", + "| total_timesteps | 152828 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00239 |\n", + "| n_updates | 25706 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13176 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2292 |\n", + "| total_timesteps | 152863 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0118 |\n", + "| n_updates | 25715 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13180 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2295 |\n", + "| total_timesteps | 152996 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00529 |\n", + "| n_updates | 25748 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13184 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2297 |\n", + "| total_timesteps | 153089 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00228 |\n", + "| n_updates | 25772 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13188 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2300 |\n", + "| total_timesteps | 153241 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00638 |\n", + "| n_updates | 25810 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 6.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13192 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2301 |\n", + "| total_timesteps | 153336 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00508 |\n", + "| n_updates | 25833 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13196 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2303 |\n", + "| total_timesteps | 153408 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00327 |\n", + "| n_updates | 25851 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13200 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2304 |\n", + "| total_timesteps | 153456 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0095 |\n", + "| n_updates | 25863 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13204 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2305 |\n", + "| total_timesteps | 153546 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0114 |\n", + "| n_updates | 25886 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13208 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2307 |\n", + "| total_timesteps | 153638 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00405 |\n", + "| n_updates | 25909 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13212 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2309 |\n", + "| total_timesteps | 153713 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00661 |\n", + "| n_updates | 25928 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 530 |\n", + "| ep_rew_mean | 6.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13216 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2310 |\n", + "| total_timesteps | 153766 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00611 |\n", + "| n_updates | 25941 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 527 |\n", + "| ep_rew_mean | 6.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13220 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2311 |\n", + "| total_timesteps | 153848 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00488 |\n", + "| n_updates | 25961 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 527 |\n", + "| ep_rew_mean | 6.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13224 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2313 |\n", + "| total_timesteps | 153946 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00667 |\n", + "| n_updates | 25986 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 527 |\n", + "| ep_rew_mean | 6.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13228 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2315 |\n", + "| total_timesteps | 154032 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00662 |\n", + "| n_updates | 26007 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 526 |\n", + "| ep_rew_mean | 6.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13232 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2316 |\n", + "| total_timesteps | 154088 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0101 |\n", + "| n_updates | 26021 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 526 |\n", + "| ep_rew_mean | 6.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13236 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2319 |\n", + "| total_timesteps | 154239 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0129 |\n", + "| n_updates | 26059 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 525 |\n", + "| ep_rew_mean | 6.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13240 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2320 |\n", + "| total_timesteps | 154294 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00799 |\n", + "| n_updates | 26073 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 525 |\n", + "| ep_rew_mean | 6.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13244 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2322 |\n", + "| total_timesteps | 154349 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00384 |\n", + "| n_updates | 26087 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 527 |\n", + "| ep_rew_mean | 6.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13248 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2325 |\n", + "| total_timesteps | 154505 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00368 |\n", + "| n_updates | 26126 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 530 |\n", + "| ep_rew_mean | 6.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13252 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2327 |\n", + "| total_timesteps | 154650 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0027 |\n", + "| n_updates | 26162 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13256 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2329 |\n", + "| total_timesteps | 154750 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0141 |\n", + "| n_updates | 26187 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13260 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2332 |\n", + "| total_timesteps | 154889 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.015 |\n", + "| n_updates | 26222 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13264 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2335 |\n", + "| total_timesteps | 155048 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00944 |\n", + "| n_updates | 26261 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13268 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2337 |\n", + "| total_timesteps | 155140 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0115 |\n", + "| n_updates | 26284 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 6.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13272 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2339 |\n", + "| total_timesteps | 155224 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0114 |\n", + "| n_updates | 26305 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 7.01 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13276 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2341 |\n", + "| total_timesteps | 155335 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00429 |\n", + "| n_updates | 26333 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13280 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2343 |\n", + "| total_timesteps | 155423 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00899 |\n", + "| n_updates | 26355 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13284 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2345 |\n", + "| total_timesteps | 155537 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0157 |\n", + "| n_updates | 26384 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13288 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2347 |\n", + "| total_timesteps | 155624 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00508 |\n", + "| n_updates | 26405 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13292 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2348 |\n", + "| total_timesteps | 155702 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0103 |\n", + "| n_updates | 26425 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 540 |\n", + "| ep_rew_mean | 7.03 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13296 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2351 |\n", + "| total_timesteps | 155816 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00515 |\n", + "| n_updates | 26453 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 6.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13300 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2352 |\n", + "| total_timesteps | 155886 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00495 |\n", + "| n_updates | 26471 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 6.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13304 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2354 |\n", + "| total_timesteps | 155958 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0116 |\n", + "| n_updates | 26489 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13308 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2356 |\n", + "| total_timesteps | 156077 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00341 |\n", + "| n_updates | 26519 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 6.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13312 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2358 |\n", + "| total_timesteps | 156161 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00878 |\n", + "| n_updates | 26540 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 535 |\n", + "| ep_rew_mean | 6.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13316 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2360 |\n", + "| total_timesteps | 156265 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00395 |\n", + "| n_updates | 26566 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13320 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2363 |\n", + "| total_timesteps | 156384 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0133 |\n", + "| n_updates | 26595 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13324 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2365 |\n", + "| total_timesteps | 156490 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00729 |\n", + "| n_updates | 26622 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13328 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2366 |\n", + "| total_timesteps | 156563 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00569 |\n", + "| n_updates | 26640 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 7.01 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13332 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2370 |\n", + "| total_timesteps | 156731 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0056 |\n", + "| n_updates | 26682 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 540 |\n", + "| ep_rew_mean | 7.06 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13336 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2371 |\n", + "| total_timesteps | 156772 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00254 |\n", + "| n_updates | 26692 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 541 |\n", + "| ep_rew_mean | 7.07 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13340 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2372 |\n", + "| total_timesteps | 156866 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00554 |\n", + "| n_updates | 26716 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 541 |\n", + "| ep_rew_mean | 7.07 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13344 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2373 |\n", + "| total_timesteps | 156910 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00398 |\n", + "| n_updates | 26727 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 535 |\n", + "| ep_rew_mean | 6.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13348 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2376 |\n", + "| total_timesteps | 157007 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00425 |\n", + "| n_updates | 26751 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 535 |\n", + "| ep_rew_mean | 6.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13352 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2378 |\n", + "| total_timesteps | 157134 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00293 |\n", + "| n_updates | 26783 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13356 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2381 |\n", + "| total_timesteps | 157250 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00553 |\n", + "| n_updates | 26812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13360 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2382 |\n", + "| total_timesteps | 157323 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0108 |\n", + "| n_updates | 26830 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13364 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2383 |\n", + "| total_timesteps | 157363 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00411 |\n", + "| n_updates | 26840 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 6.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13368 |\n", + "| fps | 66 |\n", + "| time_elapsed | 2385 |\n", + "| total_timesteps | 157451 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0043 |\n", + "| n_updates | 26862 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 535 |\n", + "| ep_rew_mean | 6.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13372 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2387 |\n", + "| total_timesteps | 157565 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00552 |\n", + "| n_updates | 26891 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13376 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2389 |\n", + "| total_timesteps | 157655 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.012 |\n", + "| n_updates | 26913 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13380 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2391 |\n", + "| total_timesteps | 157756 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0116 |\n", + "| n_updates | 26938 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13384 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2392 |\n", + "| total_timesteps | 157820 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00513 |\n", + "| n_updates | 26954 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13388 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2394 |\n", + "| total_timesteps | 157914 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00487 |\n", + "| n_updates | 26978 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13392 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2396 |\n", + "| total_timesteps | 157985 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00787 |\n", + "| n_updates | 26996 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13396 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2398 |\n", + "| total_timesteps | 158086 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00589 |\n", + "| n_updates | 27021 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 535 |\n", + "| ep_rew_mean | 6.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13400 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2399 |\n", + "| total_timesteps | 158164 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00278 |\n", + "| n_updates | 27040 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 535 |\n", + "| ep_rew_mean | 6.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13404 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2401 |\n", + "| total_timesteps | 158248 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00245 |\n", + "| n_updates | 27061 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13408 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2403 |\n", + "| total_timesteps | 158351 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00256 |\n", + "| n_updates | 27087 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13412 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2406 |\n", + "| total_timesteps | 158482 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 27120 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13416 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2407 |\n", + "| total_timesteps | 158554 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0156 |\n", + "| n_updates | 27138 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13420 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2409 |\n", + "| total_timesteps | 158628 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00644 |\n", + "| n_updates | 27156 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13424 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2412 |\n", + "| total_timesteps | 158749 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00755 |\n", + "| n_updates | 27187 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13428 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2413 |\n", + "| total_timesteps | 158835 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00717 |\n", + "| n_updates | 27208 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13432 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2415 |\n", + "| total_timesteps | 158909 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00296 |\n", + "| n_updates | 27227 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13436 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2417 |\n", + "| total_timesteps | 159022 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00917 |\n", + "| n_updates | 27255 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13440 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2419 |\n", + "| total_timesteps | 159120 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0232 |\n", + "| n_updates | 27279 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13444 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2420 |\n", + "| total_timesteps | 159168 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0104 |\n", + "| n_updates | 27291 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13448 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2421 |\n", + "| total_timesteps | 159220 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00293 |\n", + "| n_updates | 27304 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.87 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13452 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2424 |\n", + "| total_timesteps | 159335 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00594 |\n", + "| n_updates | 27333 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13456 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2426 |\n", + "| total_timesteps | 159433 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00859 |\n", + "| n_updates | 27358 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13460 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2428 |\n", + "| total_timesteps | 159548 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0184 |\n", + "| n_updates | 27386 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13464 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2429 |\n", + "| total_timesteps | 159600 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00517 |\n", + "| n_updates | 27399 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13468 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2432 |\n", + "| total_timesteps | 159719 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00495 |\n", + "| n_updates | 27429 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13472 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2434 |\n", + "| total_timesteps | 159828 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0139 |\n", + "| n_updates | 27456 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13476 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2437 |\n", + "| total_timesteps | 159946 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00495 |\n", + "| n_updates | 27486 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13480 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2439 |\n", + "| total_timesteps | 160051 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00403 |\n", + "| n_updates | 27512 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13484 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2441 |\n", + "| total_timesteps | 160150 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00834 |\n", + "| n_updates | 27537 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13488 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2443 |\n", + "| total_timesteps | 160256 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0087 |\n", + "| n_updates | 27563 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13492 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2445 |\n", + "| total_timesteps | 160347 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00553 |\n", + "| n_updates | 27586 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13496 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2447 |\n", + "| total_timesteps | 160417 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00781 |\n", + "| n_updates | 27604 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13500 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2449 |\n", + "| total_timesteps | 160505 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00699 |\n", + "| n_updates | 27626 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13504 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2449 |\n", + "| total_timesteps | 160531 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0031 |\n", + "| n_updates | 27632 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13508 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2451 |\n", + "| total_timesteps | 160630 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00937 |\n", + "| n_updates | 27657 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13512 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2453 |\n", + "| total_timesteps | 160694 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0029 |\n", + "| n_updates | 27673 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13516 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2455 |\n", + "| total_timesteps | 160805 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00266 |\n", + "| n_updates | 27701 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13520 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2457 |\n", + "| total_timesteps | 160907 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00831 |\n", + "| n_updates | 27726 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13524 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2459 |\n", + "| total_timesteps | 161028 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00862 |\n", + "| n_updates | 27756 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 7.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13528 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2462 |\n", + "| total_timesteps | 161150 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00378 |\n", + "| n_updates | 27787 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 7.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13532 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2463 |\n", + "| total_timesteps | 161209 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00737 |\n", + "| n_updates | 27802 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 535 |\n", + "| ep_rew_mean | 7.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13536 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2465 |\n", + "| total_timesteps | 161286 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.015 |\n", + "| n_updates | 27821 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 535 |\n", + "| ep_rew_mean | 7.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13540 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2467 |\n", + "| total_timesteps | 161396 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00597 |\n", + "| n_updates | 27848 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 535 |\n", + "| ep_rew_mean | 7.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13544 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2469 |\n", + "| total_timesteps | 161493 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00889 |\n", + "| n_updates | 27873 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13548 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2472 |\n", + "| total_timesteps | 161628 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00455 |\n", + "| n_updates | 27906 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 535 |\n", + "| ep_rew_mean | 7.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13552 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2474 |\n", + "| total_timesteps | 161711 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00466 |\n", + "| n_updates | 27927 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 7.06 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13556 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2478 |\n", + "| total_timesteps | 161871 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00494 |\n", + "| n_updates | 27967 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 7.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13560 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2479 |\n", + "| total_timesteps | 161943 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00416 |\n", + "| n_updates | 27985 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 7.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13564 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2483 |\n", + "| total_timesteps | 162099 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00613 |\n", + "| n_updates | 28024 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 542 |\n", + "| ep_rew_mean | 7.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13568 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2486 |\n", + "| total_timesteps | 162245 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00795 |\n", + "| n_updates | 28061 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 541 |\n", + "| ep_rew_mean | 7.27 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13572 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2488 |\n", + "| total_timesteps | 162313 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00523 |\n", + "| n_updates | 28078 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 7.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13576 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2490 |\n", + "| total_timesteps | 162403 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.014 |\n", + "| n_updates | 28100 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 7.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13580 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2492 |\n", + "| total_timesteps | 162506 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00341 |\n", + "| n_updates | 28126 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 7.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13584 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2493 |\n", + "| total_timesteps | 162579 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0103 |\n", + "| n_updates | 28144 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 535 |\n", + "| ep_rew_mean | 7.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13588 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2496 |\n", + "| total_timesteps | 162722 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0114 |\n", + "| n_updates | 28180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 540 |\n", + "| ep_rew_mean | 7.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13592 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2498 |\n", + "| total_timesteps | 162835 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00775 |\n", + "| n_updates | 28208 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 542 |\n", + "| ep_rew_mean | 7.26 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13596 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2500 |\n", + "| total_timesteps | 162934 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00828 |\n", + "| n_updates | 28233 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 546 |\n", + "| ep_rew_mean | 7.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13600 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2503 |\n", + "| total_timesteps | 163089 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00558 |\n", + "| n_updates | 28272 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 546 |\n", + "| ep_rew_mean | 7.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13604 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2506 |\n", + "| total_timesteps | 163212 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00589 |\n", + "| n_updates | 28302 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 550 |\n", + "| ep_rew_mean | 7.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13608 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2509 |\n", + "| total_timesteps | 163371 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0083 |\n", + "| n_updates | 28342 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 551 |\n", + "| ep_rew_mean | 7.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13612 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2511 |\n", + "| total_timesteps | 163468 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00332 |\n", + "| n_updates | 28366 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 549 |\n", + "| ep_rew_mean | 7.43 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13616 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2512 |\n", + "| total_timesteps | 163523 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00636 |\n", + "| n_updates | 28380 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 547 |\n", + "| ep_rew_mean | 7.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13620 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2515 |\n", + "| total_timesteps | 163640 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0138 |\n", + "| n_updates | 28409 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 547 |\n", + "| ep_rew_mean | 7.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13624 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2517 |\n", + "| total_timesteps | 163752 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00248 |\n", + "| n_updates | 28437 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 548 |\n", + "| ep_rew_mean | 7.41 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13628 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2519 |\n", + "| total_timesteps | 163867 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00881 |\n", + "| n_updates | 28466 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 550 |\n", + "| ep_rew_mean | 7.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13632 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2521 |\n", + "| total_timesteps | 163959 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00359 |\n", + "| n_updates | 28489 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 547 |\n", + "| ep_rew_mean | 7.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13636 |\n", + "| fps | 65 |\n", + "| time_elapsed | 2523 |\n", + "| total_timesteps | 164058 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00852 |\n", + "| n_updates | 28514 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 546 |\n", + "| ep_rew_mean | 7.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13640 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2526 |\n", + "| total_timesteps | 164173 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00598 |\n", + "| n_updates | 28543 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 546 |\n", + "| ep_rew_mean | 7.38 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13644 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2526 |\n", + "| total_timesteps | 164215 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0112 |\n", + "| n_updates | 28553 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 547 |\n", + "| ep_rew_mean | 7.39 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13648 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2530 |\n", + "| total_timesteps | 164358 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00755 |\n", + "| n_updates | 28589 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 550 |\n", + "| ep_rew_mean | 7.44 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13652 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2533 |\n", + "| total_timesteps | 164512 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0115 |\n", + "| n_updates | 28627 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 550 |\n", + "| ep_rew_mean | 7.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13656 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2535 |\n", + "| total_timesteps | 164615 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00799 |\n", + "| n_updates | 28653 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 554 |\n", + "| ep_rew_mean | 7.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13660 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2537 |\n", + "| total_timesteps | 164736 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00501 |\n", + "| n_updates | 28683 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 554 |\n", + "| ep_rew_mean | 7.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13664 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2539 |\n", + "| total_timesteps | 164830 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0197 |\n", + "| n_updates | 28707 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 554 |\n", + "| ep_rew_mean | 7.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13668 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2541 |\n", + "| total_timesteps | 164937 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00422 |\n", + "| n_updates | 28734 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 556 |\n", + "| ep_rew_mean | 7.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13672 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2543 |\n", + "| total_timesteps | 164999 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00562 |\n", + "| n_updates | 28749 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 557 |\n", + "| ep_rew_mean | 7.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13676 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2545 |\n", + "| total_timesteps | 165087 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00381 |\n", + "| n_updates | 28771 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13680 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2550 |\n", + "| total_timesteps | 165280 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0121 |\n", + "| n_updates | 28819 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13684 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2552 |\n", + "| total_timesteps | 165379 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00428 |\n", + "| n_updates | 28844 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13688 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2553 |\n", + "| total_timesteps | 165425 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0119 |\n", + "| n_updates | 28856 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 556 |\n", + "| ep_rew_mean | 7.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13692 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2555 |\n", + "| total_timesteps | 165520 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00729 |\n", + "| n_updates | 28879 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13696 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2557 |\n", + "| total_timesteps | 165616 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00264 |\n", + "| n_updates | 28903 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13700 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2559 |\n", + "| total_timesteps | 165703 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00715 |\n", + "| n_updates | 28925 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13704 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2561 |\n", + "| total_timesteps | 165796 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00313 |\n", + "| n_updates | 28948 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13708 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2562 |\n", + "| total_timesteps | 165831 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00569 |\n", + "| n_updates | 28957 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13712 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2564 |\n", + "| total_timesteps | 165970 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 28992 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13716 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2566 |\n", + "| total_timesteps | 166051 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00861 |\n", + "| n_updates | 29012 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13720 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2568 |\n", + "| total_timesteps | 166145 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0155 |\n", + "| n_updates | 29036 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13724 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2569 |\n", + "| total_timesteps | 166232 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00901 |\n", + "| n_updates | 29057 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 562 |\n", + "| ep_rew_mean | 7.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13728 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2573 |\n", + "| total_timesteps | 166424 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00436 |\n", + "| n_updates | 29105 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 565 |\n", + "| ep_rew_mean | 7.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13732 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2577 |\n", + "| total_timesteps | 166602 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00535 |\n", + "| n_updates | 29150 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 569 |\n", + "| ep_rew_mean | 7.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13736 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2579 |\n", + "| total_timesteps | 166716 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00413 |\n", + "| n_updates | 29178 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 566 |\n", + "| ep_rew_mean | 7.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13740 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2580 |\n", + "| total_timesteps | 166754 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0161 |\n", + "| n_updates | 29188 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 566 |\n", + "| ep_rew_mean | 7.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13744 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2582 |\n", + "| total_timesteps | 166859 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00954 |\n", + "| n_updates | 29214 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 567 |\n", + "| ep_rew_mean | 7.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13748 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2585 |\n", + "| total_timesteps | 166980 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00809 |\n", + "| n_updates | 29244 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 567 |\n", + "| ep_rew_mean | 7.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13752 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2587 |\n", + "| total_timesteps | 167098 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00348 |\n", + "| n_updates | 29274 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 565 |\n", + "| ep_rew_mean | 7.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13756 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2589 |\n", + "| total_timesteps | 167181 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00162 |\n", + "| n_updates | 29295 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 563 |\n", + "| ep_rew_mean | 7.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13760 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2591 |\n", + "| total_timesteps | 167261 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0133 |\n", + "| n_updates | 29315 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 563 |\n", + "| ep_rew_mean | 7.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13764 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2592 |\n", + "| total_timesteps | 167355 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00779 |\n", + "| n_updates | 29338 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13768 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2593 |\n", + "| total_timesteps | 167397 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.011 |\n", + "| n_updates | 29349 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 556 |\n", + "| ep_rew_mean | 7.46 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13772 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2594 |\n", + "| total_timesteps | 167457 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0087 |\n", + "| n_updates | 29364 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13776 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2597 |\n", + "| total_timesteps | 167592 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00314 |\n", + "| n_updates | 29397 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13780 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2599 |\n", + "| total_timesteps | 167672 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00628 |\n", + "| n_updates | 29417 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13784 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2602 |\n", + "| total_timesteps | 167820 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0226 |\n", + "| n_updates | 29454 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13788 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2605 |\n", + "| total_timesteps | 167946 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00242 |\n", + "| n_updates | 29486 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13792 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2607 |\n", + "| total_timesteps | 168023 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00408 |\n", + "| n_updates | 29505 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13796 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2608 |\n", + "| total_timesteps | 168085 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00811 |\n", + "| n_updates | 29521 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 561 |\n", + "| ep_rew_mean | 7.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13800 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2611 |\n", + "| total_timesteps | 168203 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00377 |\n", + "| n_updates | 29550 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 561 |\n", + "| ep_rew_mean | 7.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13804 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2614 |\n", + "| total_timesteps | 168340 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0046 |\n", + "| n_updates | 29584 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 561 |\n", + "| ep_rew_mean | 7.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13808 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2615 |\n", + "| total_timesteps | 168408 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0023 |\n", + "| n_updates | 29601 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 561 |\n", + "| ep_rew_mean | 7.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13812 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2618 |\n", + "| total_timesteps | 168556 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00175 |\n", + "| n_updates | 29638 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 564 |\n", + "| ep_rew_mean | 7.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13816 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2621 |\n", + "| total_timesteps | 168671 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00712 |\n", + "| n_updates | 29667 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 562 |\n", + "| ep_rew_mean | 7.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13820 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2622 |\n", + "| total_timesteps | 168746 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00519 |\n", + "| n_updates | 29686 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 562 |\n", + "| ep_rew_mean | 7.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13824 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2625 |\n", + "| total_timesteps | 168894 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00267 |\n", + "| n_updates | 29723 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 564 |\n", + "| ep_rew_mean | 7.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13828 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2627 |\n", + "| total_timesteps | 168974 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00403 |\n", + "| n_updates | 29743 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 563 |\n", + "| ep_rew_mean | 7.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13832 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2628 |\n", + "| total_timesteps | 169038 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00567 |\n", + "| n_updates | 29759 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 561 |\n", + "| ep_rew_mean | 7.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13836 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2630 |\n", + "| total_timesteps | 169111 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00351 |\n", + "| n_updates | 29777 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13840 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2631 |\n", + "| total_timesteps | 169162 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00192 |\n", + "| n_updates | 29790 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13844 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2633 |\n", + "| total_timesteps | 169285 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00427 |\n", + "| n_updates | 29821 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 563 |\n", + "| ep_rew_mean | 7.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13848 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2635 |\n", + "| total_timesteps | 169379 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00477 |\n", + "| n_updates | 29844 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 564 |\n", + "| ep_rew_mean | 7.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13852 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2637 |\n", + "| total_timesteps | 169470 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00476 |\n", + "| n_updates | 29867 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.56 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13856 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2638 |\n", + "| total_timesteps | 169526 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00964 |\n", + "| n_updates | 29881 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13860 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2640 |\n", + "| total_timesteps | 169595 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0136 |\n", + "| n_updates | 29898 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13864 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2640 |\n", + "| total_timesteps | 169629 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00557 |\n", + "| n_updates | 29907 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13868 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2643 |\n", + "| total_timesteps | 169760 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0171 |\n", + "| n_updates | 29939 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.63 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13872 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2645 |\n", + "| total_timesteps | 169878 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00981 |\n", + "| n_updates | 29969 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13876 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2647 |\n", + "| total_timesteps | 169984 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0156 |\n", + "| n_updates | 29995 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 562 |\n", + "| ep_rew_mean | 7.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13880 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2650 |\n", + "| total_timesteps | 170126 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00597 |\n", + "| n_updates | 30031 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 562 |\n", + "| ep_rew_mean | 7.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13884 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2653 |\n", + "| total_timesteps | 170254 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0196 |\n", + "| n_updates | 30063 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 564 |\n", + "| ep_rew_mean | 7.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13888 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2655 |\n", + "| total_timesteps | 170371 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0142 |\n", + "| n_updates | 30092 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 569 |\n", + "| ep_rew_mean | 7.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13892 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2658 |\n", + "| total_timesteps | 170547 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0213 |\n", + "| n_updates | 30136 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 571 |\n", + "| ep_rew_mean | 7.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13896 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2661 |\n", + "| total_timesteps | 170686 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0175 |\n", + "| n_updates | 30171 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 571 |\n", + "| ep_rew_mean | 7.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13900 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2663 |\n", + "| total_timesteps | 170762 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0117 |\n", + "| n_updates | 30190 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 571 |\n", + "| ep_rew_mean | 7.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13904 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2664 |\n", + "| total_timesteps | 170831 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00595 |\n", + "| n_updates | 30207 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 570 |\n", + "| ep_rew_mean | 7.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13908 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2667 |\n", + "| total_timesteps | 170979 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0166 |\n", + "| n_updates | 30244 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 572 |\n", + "| ep_rew_mean | 7.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13912 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2670 |\n", + "| total_timesteps | 171098 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00667 |\n", + "| n_updates | 30274 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 571 |\n", + "| ep_rew_mean | 7.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13916 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2671 |\n", + "| total_timesteps | 171151 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00347 |\n", + "| n_updates | 30287 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 571 |\n", + "| ep_rew_mean | 7.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13920 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2672 |\n", + "| total_timesteps | 171214 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0187 |\n", + "| n_updates | 30303 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 571 |\n", + "| ep_rew_mean | 7.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13924 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2674 |\n", + "| total_timesteps | 171328 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00957 |\n", + "| n_updates | 30331 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 571 |\n", + "| ep_rew_mean | 7.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13928 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2677 |\n", + "| total_timesteps | 171487 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00861 |\n", + "| n_updates | 30371 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 574 |\n", + "| ep_rew_mean | 8.01 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13932 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2679 |\n", + "| total_timesteps | 171587 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00277 |\n", + "| n_updates | 30396 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 573 |\n", + "| ep_rew_mean | 7.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13936 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2681 |\n", + "| total_timesteps | 171678 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0202 |\n", + "| n_updates | 30419 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 574 |\n", + "| ep_rew_mean | 8.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13940 |\n", + "| fps | 64 |\n", + "| time_elapsed | 2684 |\n", + "| total_timesteps | 171802 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.015 |\n", + "| n_updates | 30450 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 574 |\n", + "| ep_rew_mean | 8.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13944 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2686 |\n", + "| total_timesteps | 171901 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00478 |\n", + "| n_updates | 30475 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 579 |\n", + "| ep_rew_mean | 8.12 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13948 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2689 |\n", + "| total_timesteps | 172075 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0055 |\n", + "| n_updates | 30518 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 580 |\n", + "| ep_rew_mean | 8.13 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13952 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2692 |\n", + "| total_timesteps | 172191 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00695 |\n", + "| n_updates | 30547 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 583 |\n", + "| ep_rew_mean | 8.22 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13956 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2694 |\n", + "| total_timesteps | 172295 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0183 |\n", + "| n_updates | 30573 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13960 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2697 |\n", + "| total_timesteps | 172428 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0057 |\n", + "| n_updates | 30606 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13964 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2699 |\n", + "| total_timesteps | 172563 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0164 |\n", + "| n_updates | 30640 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 584 |\n", + "| ep_rew_mean | 8.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13968 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2701 |\n", + "| total_timesteps | 172634 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00429 |\n", + "| n_updates | 30658 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 580 |\n", + "| ep_rew_mean | 8.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13972 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2701 |\n", + "| total_timesteps | 172660 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0168 |\n", + "| n_updates | 30664 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 580 |\n", + "| ep_rew_mean | 8.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13976 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2703 |\n", + "| total_timesteps | 172748 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00544 |\n", + "| n_updates | 30686 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 583 |\n", + "| ep_rew_mean | 8.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13980 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2707 |\n", + "| total_timesteps | 172939 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0174 |\n", + "| n_updates | 30734 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 583 |\n", + "| ep_rew_mean | 8.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13984 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2708 |\n", + "| total_timesteps | 172994 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00632 |\n", + "| n_updates | 30748 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 580 |\n", + "| ep_rew_mean | 8.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13988 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2711 |\n", + "| total_timesteps | 173112 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0194 |\n", + "| n_updates | 30777 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.09 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13992 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2712 |\n", + "| total_timesteps | 173170 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0124 |\n", + "| n_updates | 30792 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 580 |\n", + "| ep_rew_mean | 8.05 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 13996 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2715 |\n", + "| total_timesteps | 173281 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00777 |\n", + "| n_updates | 30820 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14000 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2716 |\n", + "| total_timesteps | 173376 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.011 |\n", + "| n_updates | 30843 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.08 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14004 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2719 |\n", + "| total_timesteps | 173510 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00841 |\n", + "| n_updates | 30877 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 586 |\n", + "| ep_rew_mean | 8.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14008 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2721 |\n", + "| total_timesteps | 173587 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00511 |\n", + "| n_updates | 30896 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 586 |\n", + "| ep_rew_mean | 8.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14012 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2722 |\n", + "| total_timesteps | 173660 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00931 |\n", + "| n_updates | 30914 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 587 |\n", + "| ep_rew_mean | 8.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14016 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2724 |\n", + "| total_timesteps | 173738 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0126 |\n", + "| n_updates | 30934 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 583 |\n", + "| ep_rew_mean | 8.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14020 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2725 |\n", + "| total_timesteps | 173799 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00829 |\n", + "| n_updates | 30949 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 583 |\n", + "| ep_rew_mean | 8.1 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14024 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2727 |\n", + "| total_timesteps | 173891 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00419 |\n", + "| n_updates | 30972 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.09 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14028 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2730 |\n", + "| total_timesteps | 174024 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00434 |\n", + "| n_updates | 31005 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 585 |\n", + "| ep_rew_mean | 8.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14032 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2732 |\n", + "| total_timesteps | 174135 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0134 |\n", + "| n_updates | 31033 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 586 |\n", + "| ep_rew_mean | 8.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14036 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2735 |\n", + "| total_timesteps | 174268 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00985 |\n", + "| n_updates | 31066 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 587 |\n", + "| ep_rew_mean | 8.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14040 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2737 |\n", + "| total_timesteps | 174388 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00639 |\n", + "| n_updates | 31096 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 587 |\n", + "| ep_rew_mean | 8.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14044 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2739 |\n", + "| total_timesteps | 174492 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00721 |\n", + "| n_updates | 31122 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 587 |\n", + "| ep_rew_mean | 8.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14048 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2741 |\n", + "| total_timesteps | 174558 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00313 |\n", + "| n_updates | 31139 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 586 |\n", + "| ep_rew_mean | 8.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14052 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2742 |\n", + "| total_timesteps | 174594 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00329 |\n", + "| n_updates | 31148 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.09 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14056 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2744 |\n", + "| total_timesteps | 174682 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0068 |\n", + "| n_updates | 31170 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14060 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2747 |\n", + "| total_timesteps | 174804 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0101 |\n", + "| n_updates | 31200 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14064 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2749 |\n", + "| total_timesteps | 174856 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00704 |\n", + "| n_updates | 31213 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 577 |\n", + "| ep_rew_mean | 7.88 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14068 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2751 |\n", + "| total_timesteps | 174911 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0091 |\n", + "| n_updates | 31227 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 576 |\n", + "| ep_rew_mean | 7.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14072 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2755 |\n", + "| total_timesteps | 175042 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0133 |\n", + "| n_updates | 31260 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 580 |\n", + "| ep_rew_mean | 7.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14076 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2758 |\n", + "| total_timesteps | 175186 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00601 |\n", + "| n_updates | 31296 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 581 |\n", + "| ep_rew_mean | 8.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14080 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2762 |\n", + "| total_timesteps | 175324 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0127 |\n", + "| n_updates | 31330 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 581 |\n", + "| ep_rew_mean | 8.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14084 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2766 |\n", + "| total_timesteps | 175492 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00885 |\n", + "| n_updates | 31372 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 586 |\n", + "| ep_rew_mean | 8.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14088 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2767 |\n", + "| total_timesteps | 175548 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00775 |\n", + "| n_updates | 31386 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 581 |\n", + "| ep_rew_mean | 8.09 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14092 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2770 |\n", + "| total_timesteps | 175654 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00435 |\n", + "| n_updates | 31413 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 580 |\n", + "| ep_rew_mean | 8.05 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14096 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2772 |\n", + "| total_timesteps | 175714 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0129 |\n", + "| n_updates | 31428 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 577 |\n", + "| ep_rew_mean | 7.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14100 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2774 |\n", + "| total_timesteps | 175816 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0236 |\n", + "| n_updates | 31453 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 577 |\n", + "| ep_rew_mean | 7.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14104 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2777 |\n", + "| total_timesteps | 175909 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.01 |\n", + "| n_updates | 31477 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 575 |\n", + "| ep_rew_mean | 7.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14108 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2780 |\n", + "| total_timesteps | 176019 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0113 |\n", + "| n_updates | 31504 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 573 |\n", + "| ep_rew_mean | 7.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14112 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2783 |\n", + "| total_timesteps | 176108 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00409 |\n", + "| n_updates | 31526 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 576 |\n", + "| ep_rew_mean | 7.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14116 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2786 |\n", + "| total_timesteps | 176226 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0163 |\n", + "| n_updates | 31556 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 578 |\n", + "| ep_rew_mean | 8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14120 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2790 |\n", + "| total_timesteps | 176371 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00453 |\n", + "| n_updates | 31592 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 578 |\n", + "| ep_rew_mean | 8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14124 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2793 |\n", + "| total_timesteps | 176471 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0203 |\n", + "| n_updates | 31617 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 577 |\n", + "| ep_rew_mean | 7.98 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14128 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2796 |\n", + "| total_timesteps | 176600 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00656 |\n", + "| n_updates | 31649 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 579 |\n", + "| ep_rew_mean | 8.03 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14132 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2798 |\n", + "| total_timesteps | 176705 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00327 |\n", + "| n_updates | 31676 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 578 |\n", + "| ep_rew_mean | 8.01 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14136 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2800 |\n", + "| total_timesteps | 176767 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00832 |\n", + "| n_updates | 31691 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 574 |\n", + "| ep_rew_mean | 7.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14140 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2801 |\n", + "| total_timesteps | 176790 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00456 |\n", + "| n_updates | 31697 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 574 |\n", + "| ep_rew_mean | 7.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14144 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2806 |\n", + "| total_timesteps | 176977 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00826 |\n", + "| n_updates | 31744 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 578 |\n", + "| ep_rew_mean | 8.01 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14148 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2809 |\n", + "| total_timesteps | 177096 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00707 |\n", + "| n_updates | 31773 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 577 |\n", + "| ep_rew_mean | 7.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14152 |\n", + "| fps | 63 |\n", + "| time_elapsed | 2811 |\n", + "| total_timesteps | 177196 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0025 |\n", + "| n_updates | 31798 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 575 |\n", + "| ep_rew_mean | 7.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14156 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2814 |\n", + "| total_timesteps | 177284 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00743 |\n", + "| n_updates | 31820 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 574 |\n", + "| ep_rew_mean | 7.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14160 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2816 |\n", + "| total_timesteps | 177365 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00589 |\n", + "| n_updates | 31841 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 574 |\n", + "| ep_rew_mean | 7.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14164 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2818 |\n", + "| total_timesteps | 177436 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00478 |\n", + "| n_updates | 31858 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 574 |\n", + "| ep_rew_mean | 7.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14168 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2820 |\n", + "| total_timesteps | 177497 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0136 |\n", + "| n_updates | 31874 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 574 |\n", + "| ep_rew_mean | 7.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14172 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2822 |\n", + "| total_timesteps | 177593 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0159 |\n", + "| n_updates | 31898 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 572 |\n", + "| ep_rew_mean | 7.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14176 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2824 |\n", + "| total_timesteps | 177680 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00488 |\n", + "| n_updates | 31919 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 572 |\n", + "| ep_rew_mean | 7.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14180 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2828 |\n", + "| total_timesteps | 177857 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00338 |\n", + "| n_updates | 31964 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 572 |\n", + "| ep_rew_mean | 7.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14184 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2830 |\n", + "| total_timesteps | 177959 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00415 |\n", + "| n_updates | 31989 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 573 |\n", + "| ep_rew_mean | 7.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14188 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2833 |\n", + "| total_timesteps | 178075 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0156 |\n", + "| n_updates | 32018 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 575 |\n", + "| ep_rew_mean | 8.01 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14192 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2835 |\n", + "| total_timesteps | 178193 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00666 |\n", + "| n_updates | 32048 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 576 |\n", + "| ep_rew_mean | 8.03 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14196 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2838 |\n", + "| total_timesteps | 178293 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00967 |\n", + "| n_updates | 32073 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 575 |\n", + "| ep_rew_mean | 8.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14200 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2839 |\n", + "| total_timesteps | 178365 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00731 |\n", + "| n_updates | 32091 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 575 |\n", + "| ep_rew_mean | 8.02 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14204 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2841 |\n", + "| total_timesteps | 178426 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00174 |\n", + "| n_updates | 32106 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 576 |\n", + "| ep_rew_mean | 8.05 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14208 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2844 |\n", + "| total_timesteps | 178579 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0116 |\n", + "| n_updates | 32144 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 577 |\n", + "| ep_rew_mean | 8.06 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14212 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2846 |\n", + "| total_timesteps | 178681 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00889 |\n", + "| n_updates | 32170 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 578 |\n", + "| ep_rew_mean | 8.07 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14216 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2849 |\n", + "| total_timesteps | 178809 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0106 |\n", + "| n_updates | 32202 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 578 |\n", + "| ep_rew_mean | 8.06 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14220 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2850 |\n", + "| total_timesteps | 178859 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00344 |\n", + "| n_updates | 32214 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 578 |\n", + "| ep_rew_mean | 8.06 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14224 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2852 |\n", + "| total_timesteps | 178948 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00458 |\n", + "| n_updates | 32236 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 576 |\n", + "| ep_rew_mean | 8.03 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14228 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2854 |\n", + "| total_timesteps | 179057 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00545 |\n", + "| n_updates | 32264 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 572 |\n", + "| ep_rew_mean | 7.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14232 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2857 |\n", + "| total_timesteps | 179178 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0157 |\n", + "| n_updates | 32294 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 571 |\n", + "| ep_rew_mean | 7.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14236 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2859 |\n", + "| total_timesteps | 179294 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00847 |\n", + "| n_updates | 32323 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 577 |\n", + "| ep_rew_mean | 8.03 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14240 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2863 |\n", + "| total_timesteps | 179436 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00521 |\n", + "| n_updates | 32358 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 577 |\n", + "| ep_rew_mean | 8.03 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14244 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2865 |\n", + "| total_timesteps | 179530 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00261 |\n", + "| n_updates | 32382 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 577 |\n", + "| ep_rew_mean | 8.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14248 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2868 |\n", + "| total_timesteps | 179653 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00345 |\n", + "| n_updates | 32413 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 577 |\n", + "| ep_rew_mean | 8.03 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14252 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2871 |\n", + "| total_timesteps | 179776 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00565 |\n", + "| n_updates | 32443 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 578 |\n", + "| ep_rew_mean | 8.05 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14256 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2874 |\n", + "| total_timesteps | 179854 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0115 |\n", + "| n_updates | 32463 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 578 |\n", + "| ep_rew_mean | 8.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14260 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2877 |\n", + "| total_timesteps | 179963 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.01 |\n", + "| n_updates | 32490 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 578 |\n", + "| ep_rew_mean | 8.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14264 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2880 |\n", + "| total_timesteps | 180114 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00615 |\n", + "| n_updates | 32528 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 580 |\n", + "| ep_rew_mean | 8.09 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14268 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2884 |\n", + "| total_timesteps | 180266 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00463 |\n", + "| n_updates | 32566 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 585 |\n", + "| ep_rew_mean | 8.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14272 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2885 |\n", + "| total_timesteps | 180318 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00821 |\n", + "| n_updates | 32579 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 583 |\n", + "| ep_rew_mean | 8.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14276 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2889 |\n", + "| total_timesteps | 180474 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0336 |\n", + "| n_updates | 32618 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 584 |\n", + "| ep_rew_mean | 8.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14280 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2890 |\n", + "| total_timesteps | 180526 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00441 |\n", + "| n_updates | 32631 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 584 |\n", + "| ep_rew_mean | 8.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14284 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2891 |\n", + "| total_timesteps | 180594 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00773 |\n", + "| n_updates | 32648 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.13 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14288 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2893 |\n", + "| total_timesteps | 180687 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0111 |\n", + "| n_updates | 32671 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 581 |\n", + "| ep_rew_mean | 8.13 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14292 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2897 |\n", + "| total_timesteps | 180832 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0106 |\n", + "| n_updates | 32707 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 583 |\n", + "| ep_rew_mean | 8.17 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14296 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2899 |\n", + "| total_timesteps | 180944 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00693 |\n", + "| n_updates | 32735 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 581 |\n", + "| ep_rew_mean | 8.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14300 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2900 |\n", + "| total_timesteps | 181004 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00509 |\n", + "| n_updates | 32750 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 581 |\n", + "| ep_rew_mean | 8.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14304 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2903 |\n", + "| total_timesteps | 181150 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0132 |\n", + "| n_updates | 32787 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14308 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2905 |\n", + "| total_timesteps | 181219 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0261 |\n", + "| n_updates | 32804 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14312 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2908 |\n", + "| total_timesteps | 181343 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00992 |\n", + "| n_updates | 32835 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 578 |\n", + "| ep_rew_mean | 8.09 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14316 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2909 |\n", + "| total_timesteps | 181402 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00898 |\n", + "| n_updates | 32850 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 581 |\n", + "| ep_rew_mean | 8.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14320 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2912 |\n", + "| total_timesteps | 181537 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00505 |\n", + "| n_updates | 32884 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 581 |\n", + "| ep_rew_mean | 8.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14324 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2914 |\n", + "| total_timesteps | 181646 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00644 |\n", + "| n_updates | 32911 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 579 |\n", + "| ep_rew_mean | 8.12 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14328 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2916 |\n", + "| total_timesteps | 181735 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00219 |\n", + "| n_updates | 32933 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 580 |\n", + "| ep_rew_mean | 8.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14332 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2918 |\n", + "| total_timesteps | 181819 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00401 |\n", + "| n_updates | 32954 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 581 |\n", + "| ep_rew_mean | 8.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14336 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2919 |\n", + "| total_timesteps | 181898 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0139 |\n", + "| n_updates | 32974 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 583 |\n", + "| ep_rew_mean | 8.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14340 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2921 |\n", + "| total_timesteps | 181986 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00587 |\n", + "| n_updates | 32996 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 583 |\n", + "| ep_rew_mean | 8.19 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14344 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2925 |\n", + "| total_timesteps | 182136 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00322 |\n", + "| n_updates | 33033 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 584 |\n", + "| ep_rew_mean | 8.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14348 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2927 |\n", + "| total_timesteps | 182257 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0167 |\n", + "| n_updates | 33064 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 585 |\n", + "| ep_rew_mean | 8.18 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14352 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2930 |\n", + "| total_timesteps | 182389 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00698 |\n", + "| n_updates | 33097 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 587 |\n", + "| ep_rew_mean | 8.23 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14356 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2932 |\n", + "| total_timesteps | 182470 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00408 |\n", + "| n_updates | 33117 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 588 |\n", + "| ep_rew_mean | 8.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14360 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2933 |\n", + "| total_timesteps | 182542 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00701 |\n", + "| n_updates | 33135 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 588 |\n", + "| ep_rew_mean | 8.24 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14364 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2936 |\n", + "| total_timesteps | 182666 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00799 |\n", + "| n_updates | 33166 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 593 |\n", + "| ep_rew_mean | 8.33 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14368 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2939 |\n", + "| total_timesteps | 182791 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.008 |\n", + "| n_updates | 33197 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 592 |\n", + "| ep_rew_mean | 8.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14372 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2941 |\n", + "| total_timesteps | 182888 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00206 |\n", + "| n_updates | 33221 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 592 |\n", + "| ep_rew_mean | 8.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14376 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2943 |\n", + "| total_timesteps | 182992 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00813 |\n", + "| n_updates | 33247 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 590 |\n", + "| ep_rew_mean | 8.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14380 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2946 |\n", + "| total_timesteps | 183131 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00535 |\n", + "| n_updates | 33282 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 590 |\n", + "| ep_rew_mean | 8.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14384 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2949 |\n", + "| total_timesteps | 183249 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00689 |\n", + "| n_updates | 33312 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 590 |\n", + "| ep_rew_mean | 8.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14388 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2951 |\n", + "| total_timesteps | 183338 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0149 |\n", + "| n_updates | 33334 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 587 |\n", + "| ep_rew_mean | 8.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14392 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2953 |\n", + "| total_timesteps | 183472 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00339 |\n", + "| n_updates | 33367 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 587 |\n", + "| ep_rew_mean | 8.13 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14396 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2956 |\n", + "| total_timesteps | 183558 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00557 |\n", + "| n_updates | 33389 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 585 |\n", + "| ep_rew_mean | 8.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14400 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2958 |\n", + "| total_timesteps | 183632 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.007 |\n", + "| n_updates | 33407 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 585 |\n", + "| ep_rew_mean | 8.11 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14404 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2961 |\n", + "| total_timesteps | 183782 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0105 |\n", + "| n_updates | 33445 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 588 |\n", + "| ep_rew_mean | 8.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14408 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2963 |\n", + "| total_timesteps | 183881 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00749 |\n", + "| n_updates | 33470 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 587 |\n", + "| ep_rew_mean | 8.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14412 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2966 |\n", + "| total_timesteps | 184000 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0172 |\n", + "| n_updates | 33499 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 588 |\n", + "| ep_rew_mean | 8.15 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14416 |\n", + "| fps | 62 |\n", + "| time_elapsed | 2969 |\n", + "| total_timesteps | 184139 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00607 |\n", + "| n_updates | 33534 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 594 |\n", + "| ep_rew_mean | 8.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14420 |\n", + "| fps | 61 |\n", + "| time_elapsed | 2972 |\n", + "| total_timesteps | 184299 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0161 |\n", + "| n_updates | 33574 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 594 |\n", + "| ep_rew_mean | 8.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14424 |\n", + "| fps | 61 |\n", + "| time_elapsed | 2975 |\n", + "| total_timesteps | 184417 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0226 |\n", + "| n_updates | 33604 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 594 |\n", + "| ep_rew_mean | 8.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14428 |\n", + "| fps | 61 |\n", + "| time_elapsed | 2979 |\n", + "| total_timesteps | 184597 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00654 |\n", + "| n_updates | 33649 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 596 |\n", + "| ep_rew_mean | 8.25 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14432 |\n", + "| fps | 61 |\n", + "| time_elapsed | 2981 |\n", + "| total_timesteps | 184701 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00933 |\n", + "| n_updates | 33675 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 594 |\n", + "| ep_rew_mean | 8.22 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14436 |\n", + "| fps | 61 |\n", + "| time_elapsed | 2982 |\n", + "| total_timesteps | 184748 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00804 |\n", + "| n_updates | 33686 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 593 |\n", + "| ep_rew_mean | 8.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14440 |\n", + "| fps | 61 |\n", + "| time_elapsed | 2984 |\n", + "| total_timesteps | 184858 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00459 |\n", + "| n_updates | 33714 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 593 |\n", + "| ep_rew_mean | 8.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14444 |\n", + "| fps | 61 |\n", + "| time_elapsed | 2986 |\n", + "| total_timesteps | 184960 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0125 |\n", + "| n_updates | 33739 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 590 |\n", + "| ep_rew_mean | 8.14 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14448 |\n", + "| fps | 61 |\n", + "| time_elapsed | 2989 |\n", + "| total_timesteps | 185069 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0151 |\n", + "| n_updates | 33767 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 589 |\n", + "| ep_rew_mean | 8.12 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14452 |\n", + "| fps | 61 |\n", + "| time_elapsed | 2990 |\n", + "| total_timesteps | 185142 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0114 |\n", + "| n_updates | 33785 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 590 |\n", + "| ep_rew_mean | 8.16 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14456 |\n", + "| fps | 61 |\n", + "| time_elapsed | 2993 |\n", + "| total_timesteps | 185315 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00816 |\n", + "| n_updates | 33828 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 592 |\n", + "| ep_rew_mean | 8.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14460 |\n", + "| fps | 61 |\n", + "| time_elapsed | 2997 |\n", + "| total_timesteps | 185447 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00952 |\n", + "| n_updates | 33861 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 592 |\n", + "| ep_rew_mean | 8.21 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14464 |\n", + "| fps | 61 |\n", + "| time_elapsed | 2998 |\n", + "| total_timesteps | 185510 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.023 |\n", + "| n_updates | 33877 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 591 |\n", + "| ep_rew_mean | 8.2 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14468 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3001 |\n", + "| total_timesteps | 185666 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0153 |\n", + "| n_updates | 33916 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 594 |\n", + "| ep_rew_mean | 8.34 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14472 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3003 |\n", + "| total_timesteps | 185750 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0128 |\n", + "| n_updates | 33937 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 595 |\n", + "| ep_rew_mean | 8.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14476 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3005 |\n", + "| total_timesteps | 185825 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0159 |\n", + "| n_updates | 33956 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 591 |\n", + "| ep_rew_mean | 8.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14480 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3007 |\n", + "| total_timesteps | 185946 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00317 |\n", + "| n_updates | 33986 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 591 |\n", + "| ep_rew_mean | 8.28 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14484 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3010 |\n", + "| total_timesteps | 186075 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0119 |\n", + "| n_updates | 34018 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 595 |\n", + "| ep_rew_mean | 8.36 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14488 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3013 |\n", + "| total_timesteps | 186200 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0113 |\n", + "| n_updates | 34049 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 595 |\n", + "| ep_rew_mean | 8.37 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14492 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3016 |\n", + "| total_timesteps | 186342 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00461 |\n", + "| n_updates | 34085 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 598 |\n", + "| ep_rew_mean | 8.45 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14496 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3018 |\n", + "| total_timesteps | 186450 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0104 |\n", + "| n_updates | 34112 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 601 |\n", + "| ep_rew_mean | 8.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14500 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3022 |\n", + "| total_timesteps | 186615 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0163 |\n", + "| n_updates | 34153 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 601 |\n", + "| ep_rew_mean | 8.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14504 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3024 |\n", + "| total_timesteps | 186734 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.009 |\n", + "| n_updates | 34183 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 599 |\n", + "| ep_rew_mean | 8.49 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14508 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3025 |\n", + "| total_timesteps | 186771 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00586 |\n", + "| n_updates | 34192 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 598 |\n", + "| ep_rew_mean | 8.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14512 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3027 |\n", + "| total_timesteps | 186882 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0188 |\n", + "| n_updates | 34220 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 600 |\n", + "| ep_rew_mean | 8.51 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14516 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3029 |\n", + "| total_timesteps | 186969 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00408 |\n", + "| n_updates | 34242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 602 |\n", + "| ep_rew_mean | 8.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14520 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3031 |\n", + "| total_timesteps | 187072 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00303 |\n", + "| n_updates | 34267 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 602 |\n", + "| ep_rew_mean | 8.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14524 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3035 |\n", + "| total_timesteps | 187246 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0171 |\n", + "| n_updates | 34311 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 605 |\n", + "| ep_rew_mean | 8.64 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14528 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3037 |\n", + "| total_timesteps | 187344 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.023 |\n", + "| n_updates | 34335 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 604 |\n", + "| ep_rew_mean | 8.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14532 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3040 |\n", + "| total_timesteps | 187468 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0194 |\n", + "| n_updates | 34366 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 604 |\n", + "| ep_rew_mean | 8.59 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14536 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3042 |\n", + "| total_timesteps | 187574 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00651 |\n", + "| n_updates | 34393 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 602 |\n", + "| ep_rew_mean | 8.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14540 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3045 |\n", + "| total_timesteps | 187681 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00492 |\n", + "| n_updates | 34420 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 602 |\n", + "| ep_rew_mean | 8.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14544 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3047 |\n", + "| total_timesteps | 187778 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0294 |\n", + "| n_updates | 34444 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 602 |\n", + "| ep_rew_mean | 8.55 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14548 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3050 |\n", + "| total_timesteps | 187917 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0114 |\n", + "| n_updates | 34479 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 606 |\n", + "| ep_rew_mean | 8.62 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14552 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3051 |\n", + "| total_timesteps | 187995 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00198 |\n", + "| n_updates | 34498 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 608 |\n", + "| ep_rew_mean | 8.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14556 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3054 |\n", + "| total_timesteps | 188113 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00592 |\n", + "| n_updates | 34528 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 607 |\n", + "| ep_rew_mean | 8.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14560 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3057 |\n", + "| total_timesteps | 188224 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0096 |\n", + "| n_updates | 34555 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 607 |\n", + "| ep_rew_mean | 8.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14564 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3059 |\n", + "| total_timesteps | 188325 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0045 |\n", + "| n_updates | 34581 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 610 |\n", + "| ep_rew_mean | 8.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14568 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3061 |\n", + "| total_timesteps | 188398 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0192 |\n", + "| n_updates | 34599 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 610 |\n", + "| ep_rew_mean | 8.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14572 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3063 |\n", + "| total_timesteps | 188505 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0165 |\n", + "| n_updates | 34626 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 607 |\n", + "| ep_rew_mean | 8.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14576 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3065 |\n", + "| total_timesteps | 188628 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00473 |\n", + "| n_updates | 34656 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 607 |\n", + "| ep_rew_mean | 8.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14580 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3068 |\n", + "| total_timesteps | 188739 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00733 |\n", + "| n_updates | 34684 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 607 |\n", + "| ep_rew_mean | 8.61 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14584 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3070 |\n", + "| total_timesteps | 188855 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00812 |\n", + "| n_updates | 34713 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 603 |\n", + "| ep_rew_mean | 8.48 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14588 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3071 |\n", + "| total_timesteps | 188909 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0126 |\n", + "| n_updates | 34727 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 603 |\n", + "| ep_rew_mean | 8.47 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14592 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3073 |\n", + "| total_timesteps | 189001 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0121 |\n", + "| n_updates | 34750 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 606 |\n", + "| ep_rew_mean | 8.53 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14596 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3077 |\n", + "| total_timesteps | 189164 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0107 |\n", + "| n_updates | 34790 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 607 |\n", + "| ep_rew_mean | 8.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14600 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3079 |\n", + "| total_timesteps | 189239 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00913 |\n", + "| n_updates | 34809 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 607 |\n", + "| ep_rew_mean | 8.54 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14604 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3082 |\n", + "| total_timesteps | 189397 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00363 |\n", + "| n_updates | 34849 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 609 |\n", + "| ep_rew_mean | 8.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14608 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3085 |\n", + "| total_timesteps | 189529 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00713 |\n", + "| n_updates | 34882 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 610 |\n", + "| ep_rew_mean | 8.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14612 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3087 |\n", + "| total_timesteps | 189615 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0204 |\n", + "| n_updates | 34903 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 609 |\n", + "| ep_rew_mean | 8.58 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14616 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3090 |\n", + "| total_timesteps | 189735 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 34933 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 609 |\n", + "| ep_rew_mean | 8.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14620 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3093 |\n", + "| total_timesteps | 189850 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00386 |\n", + "| n_updates | 34962 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 609 |\n", + "| ep_rew_mean | 8.57 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14624 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3095 |\n", + "| total_timesteps | 189985 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00305 |\n", + "| n_updates | 34996 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 611 |\n", + "| ep_rew_mean | 8.6 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14628 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3098 |\n", + "| total_timesteps | 190128 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0196 |\n", + "| n_updates | 35031 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 612 |\n", + "| ep_rew_mean | 8.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14632 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3100 |\n", + "| total_timesteps | 190229 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0209 |\n", + "| n_updates | 35057 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 612 |\n", + "| ep_rew_mean | 8.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14636 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3103 |\n", + "| total_timesteps | 190352 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00861 |\n", + "| n_updates | 35087 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 617 |\n", + "| ep_rew_mean | 8.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14640 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3106 |\n", + "| total_timesteps | 190482 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0022 |\n", + "| n_updates | 35120 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 617 |\n", + "| ep_rew_mean | 8.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14644 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3109 |\n", + "| total_timesteps | 190636 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00283 |\n", + "| n_updates | 35158 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 616 |\n", + "| ep_rew_mean | 8.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14648 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3112 |\n", + "| total_timesteps | 190776 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0117 |\n", + "| n_updates | 35193 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 617 |\n", + "| ep_rew_mean | 8.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14652 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3114 |\n", + "| total_timesteps | 190837 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00692 |\n", + "| n_updates | 35209 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 618 |\n", + "| ep_rew_mean | 8.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14656 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3117 |\n", + "| total_timesteps | 190984 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0159 |\n", + "| n_updates | 35245 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 619 |\n", + "| ep_rew_mean | 8.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14660 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3119 |\n", + "| total_timesteps | 191100 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00586 |\n", + "| n_updates | 35274 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 619 |\n", + "| ep_rew_mean | 8.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14664 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3122 |\n", + "| total_timesteps | 191217 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.012 |\n", + "| n_updates | 35304 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 620 |\n", + "| ep_rew_mean | 8.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14668 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3125 |\n", + "| total_timesteps | 191338 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 35334 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 623 |\n", + "| ep_rew_mean | 8.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14672 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3127 |\n", + "| total_timesteps | 191462 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00352 |\n", + "| n_updates | 35365 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 624 |\n", + "| ep_rew_mean | 8.9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14676 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3129 |\n", + "| total_timesteps | 191549 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00516 |\n", + "| n_updates | 35387 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 620 |\n", + "| ep_rew_mean | 8.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14680 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3131 |\n", + "| total_timesteps | 191622 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0109 |\n", + "| n_updates | 35405 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 620 |\n", + "| ep_rew_mean | 8.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14684 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3132 |\n", + "| total_timesteps | 191687 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0187 |\n", + "| n_updates | 35421 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 619 |\n", + "| ep_rew_mean | 8.76 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14688 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3134 |\n", + "| total_timesteps | 191780 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0221 |\n", + "| n_updates | 35444 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 616 |\n", + "| ep_rew_mean | 8.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14692 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3135 |\n", + "| total_timesteps | 191864 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00974 |\n", + "| n_updates | 35465 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 614 |\n", + "| ep_rew_mean | 8.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14696 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3137 |\n", + "| total_timesteps | 191947 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00672 |\n", + "| n_updates | 35486 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 615 |\n", + "| ep_rew_mean | 8.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14700 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3138 |\n", + "| total_timesteps | 192004 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00589 |\n", + "| n_updates | 35500 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 615 |\n", + "| ep_rew_mean | 8.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14704 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3141 |\n", + "| total_timesteps | 192095 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00376 |\n", + "| n_updates | 35523 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 615 |\n", + "| ep_rew_mean | 8.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14708 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3143 |\n", + "| total_timesteps | 192208 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00432 |\n", + "| n_updates | 35551 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 615 |\n", + "| ep_rew_mean | 8.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14712 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3146 |\n", + "| total_timesteps | 192340 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.023 |\n", + "| n_updates | 35584 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 617 |\n", + "| ep_rew_mean | 8.71 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14716 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3148 |\n", + "| total_timesteps | 192437 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00669 |\n", + "| n_updates | 35609 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 616 |\n", + "| ep_rew_mean | 8.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14720 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3150 |\n", + "| total_timesteps | 192524 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0103 |\n", + "| n_updates | 35630 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 616 |\n", + "| ep_rew_mean | 8.7 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14724 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3153 |\n", + "| total_timesteps | 192638 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00641 |\n", + "| n_updates | 35659 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 618 |\n", + "| ep_rew_mean | 8.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14728 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3156 |\n", + "| total_timesteps | 192788 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.014 |\n", + "| n_updates | 35696 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 620 |\n", + "| ep_rew_mean | 8.77 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14732 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3159 |\n", + "| total_timesteps | 192915 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0109 |\n", + "| n_updates | 35728 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 618 |\n", + "| ep_rew_mean | 8.74 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14736 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3160 |\n", + "| total_timesteps | 192985 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0102 |\n", + "| n_updates | 35746 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 615 |\n", + "| ep_rew_mean | 8.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14740 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3162 |\n", + "| total_timesteps | 193063 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00394 |\n", + "| n_updates | 35765 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 615 |\n", + "| ep_rew_mean | 8.66 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14744 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3164 |\n", + "| total_timesteps | 193157 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00509 |\n", + "| n_updates | 35789 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 615 |\n", + "| ep_rew_mean | 8.67 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14748 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3167 |\n", + "| total_timesteps | 193297 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0228 |\n", + "| n_updates | 35824 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 615 |\n", + "| ep_rew_mean | 8.68 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14752 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3169 |\n", + "| total_timesteps | 193400 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00922 |\n", + "| n_updates | 35849 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 616 |\n", + "| ep_rew_mean | 8.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14756 |\n", + "| fps | 61 |\n", + "| time_elapsed | 3172 |\n", + "| total_timesteps | 193561 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0226 |\n", + "| n_updates | 35890 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 617 |\n", + "| ep_rew_mean | 8.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14760 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3174 |\n", + "| total_timesteps | 193654 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0159 |\n", + "| n_updates | 35913 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 617 |\n", + "| ep_rew_mean | 8.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14764 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3176 |\n", + "| total_timesteps | 193718 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00643 |\n", + "| n_updates | 35929 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 613 |\n", + "| ep_rew_mean | 8.69 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14768 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3178 |\n", + "| total_timesteps | 193804 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00767 |\n", + "| n_updates | 35950 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 611 |\n", + "| ep_rew_mean | 8.65 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14772 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3180 |\n", + "| total_timesteps | 193908 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00718 |\n", + "| n_updates | 35976 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 614 |\n", + "| ep_rew_mean | 8.73 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14776 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3182 |\n", + "| total_timesteps | 194029 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00763 |\n", + "| n_updates | 36007 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 615 |\n", + "| ep_rew_mean | 8.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14780 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3185 |\n", + "| total_timesteps | 194150 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0109 |\n", + "| n_updates | 36037 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 615 |\n", + "| ep_rew_mean | 8.75 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14784 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3189 |\n", + "| total_timesteps | 194323 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00383 |\n", + "| n_updates | 36080 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 618 |\n", + "| ep_rew_mean | 8.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14788 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3190 |\n", + "| total_timesteps | 194380 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0123 |\n", + "| n_updates | 36094 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 617 |\n", + "| ep_rew_mean | 8.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14792 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3193 |\n", + "| total_timesteps | 194496 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0112 |\n", + "| n_updates | 36123 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 618 |\n", + "| ep_rew_mean | 8.83 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14796 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3196 |\n", + "| total_timesteps | 194656 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00896 |\n", + "| n_updates | 36163 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 621 |\n", + "| ep_rew_mean | 8.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14800 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3200 |\n", + "| total_timesteps | 194789 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0125 |\n", + "| n_updates | 36197 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 621 |\n", + "| ep_rew_mean | 8.89 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14804 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3202 |\n", + "| total_timesteps | 194867 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0192 |\n", + "| n_updates | 36216 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 619 |\n", + "| ep_rew_mean | 8.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14808 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3206 |\n", + "| total_timesteps | 195035 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0128 |\n", + "| n_updates | 36258 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 621 |\n", + "| ep_rew_mean | 8.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14812 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3207 |\n", + "| total_timesteps | 195077 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0179 |\n", + "| n_updates | 36269 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 621 |\n", + "| ep_rew_mean | 8.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14816 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3209 |\n", + "| total_timesteps | 195169 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00755 |\n", + "| n_updates | 36292 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 618 |\n", + "| ep_rew_mean | 8.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14820 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3211 |\n", + "| total_timesteps | 195244 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0118 |\n", + "| n_updates | 36310 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 618 |\n", + "| ep_rew_mean | 8.79 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14824 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3214 |\n", + "| total_timesteps | 195353 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0345 |\n", + "| n_updates | 36338 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 619 |\n", + "| ep_rew_mean | 8.81 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14828 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3217 |\n", + "| total_timesteps | 195463 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00943 |\n", + "| n_updates | 36365 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 619 |\n", + "| ep_rew_mean | 8.82 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14832 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3218 |\n", + "| total_timesteps | 195514 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0156 |\n", + "| n_updates | 36378 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 617 |\n", + "| ep_rew_mean | 8.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14836 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3221 |\n", + "| total_timesteps | 195639 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0219 |\n", + "| n_updates | 36409 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 620 |\n", + "| ep_rew_mean | 8.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14840 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3223 |\n", + "| total_timesteps | 195738 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00588 |\n", + "| n_updates | 36434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 620 |\n", + "| ep_rew_mean | 8.84 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14844 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3226 |\n", + "| total_timesteps | 195871 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00715 |\n", + "| n_updates | 36467 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 619 |\n", + "| ep_rew_mean | 8.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14848 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3228 |\n", + "| total_timesteps | 195972 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0119 |\n", + "| n_updates | 36492 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 618 |\n", + "| ep_rew_mean | 8.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14852 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3234 |\n", + "| total_timesteps | 196195 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00715 |\n", + "| n_updates | 36548 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 622 |\n", + "| ep_rew_mean | 8.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14856 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3235 |\n", + "| total_timesteps | 196248 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0158 |\n", + "| n_updates | 36561 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 622 |\n", + "| ep_rew_mean | 8.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14860 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3237 |\n", + "| total_timesteps | 196360 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0219 |\n", + "| n_updates | 36589 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 622 |\n", + "| ep_rew_mean | 8.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14864 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3238 |\n", + "| total_timesteps | 196418 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0033 |\n", + "| n_updates | 36604 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 618 |\n", + "| ep_rew_mean | 8.85 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14868 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3241 |\n", + "| total_timesteps | 196554 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.028 |\n", + "| n_updates | 36638 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 623 |\n", + "| ep_rew_mean | 8.94 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14872 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3245 |\n", + "| total_timesteps | 196713 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00677 |\n", + "| n_updates | 36678 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 625 |\n", + "| ep_rew_mean | 9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14876 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3250 |\n", + "| total_timesteps | 196897 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00396 |\n", + "| n_updates | 36724 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 625 |\n", + "| ep_rew_mean | 9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14880 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3252 |\n", + "| total_timesteps | 197006 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0052 |\n", + "| n_updates | 36751 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 625 |\n", + "| ep_rew_mean | 9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14884 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3255 |\n", + "| total_timesteps | 197131 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0202 |\n", + "| n_updates | 36782 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 625 |\n", + "| ep_rew_mean | 9.01 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14888 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3258 |\n", + "| total_timesteps | 197235 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0115 |\n", + "| n_updates | 36808 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 622 |\n", + "| ep_rew_mean | 8.95 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14892 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3259 |\n", + "| total_timesteps | 197281 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0159 |\n", + "| n_updates | 36820 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 624 |\n", + "| ep_rew_mean | 8.97 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14896 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3262 |\n", + "| total_timesteps | 197402 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.01 |\n", + "| n_updates | 36850 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 626 |\n", + "| ep_rew_mean | 9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14900 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3265 |\n", + "| total_timesteps | 197523 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0111 |\n", + "| n_updates | 36880 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 626 |\n", + "| ep_rew_mean | 9 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14904 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3269 |\n", + "| total_timesteps | 197682 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00235 |\n", + "| n_updates | 36920 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 627 |\n", + "| ep_rew_mean | 9.05 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14908 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3271 |\n", + "| total_timesteps | 197771 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0069 |\n", + "| n_updates | 36942 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 623 |\n", + "| ep_rew_mean | 8.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14912 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3273 |\n", + "| total_timesteps | 197868 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00592 |\n", + "| n_updates | 36966 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 625 |\n", + "| ep_rew_mean | 9.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14916 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3275 |\n", + "| total_timesteps | 197960 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00621 |\n", + "| n_updates | 36989 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 622 |\n", + "| ep_rew_mean | 8.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14920 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3278 |\n", + "| total_timesteps | 198106 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0211 |\n", + "| n_updates | 37026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 622 |\n", + "| ep_rew_mean | 8.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14924 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3280 |\n", + "| total_timesteps | 198166 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00251 |\n", + "| n_updates | 37041 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 620 |\n", + "| ep_rew_mean | 8.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14928 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3283 |\n", + "| total_timesteps | 198320 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00488 |\n", + "| n_updates | 37079 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 619 |\n", + "| ep_rew_mean | 8.91 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14932 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3286 |\n", + "| total_timesteps | 198428 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.015 |\n", + "| n_updates | 37106 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 620 |\n", + "| ep_rew_mean | 8.93 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14936 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3288 |\n", + "| total_timesteps | 198494 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00643 |\n", + "| n_updates | 37123 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 619 |\n", + "| ep_rew_mean | 8.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14940 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3290 |\n", + "| total_timesteps | 198588 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00438 |\n", + "| n_updates | 37146 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 619 |\n", + "| ep_rew_mean | 8.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14944 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3294 |\n", + "| total_timesteps | 198745 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00928 |\n", + "| n_updates | 37186 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 622 |\n", + "| ep_rew_mean | 8.99 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14948 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3296 |\n", + "| total_timesteps | 198834 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00395 |\n", + "| n_updates | 37208 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 624 |\n", + "| ep_rew_mean | 9.04 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14952 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3300 |\n", + "| total_timesteps | 199016 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00669 |\n", + "| n_updates | 37253 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 622 |\n", + "| ep_rew_mean | 8.96 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14956 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3303 |\n", + "| total_timesteps | 199114 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00263 |\n", + "| n_updates | 37278 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 619 |\n", + "| ep_rew_mean | 8.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14960 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3304 |\n", + "| total_timesteps | 199156 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00404 |\n", + "| n_updates | 37288 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 619 |\n", + "| ep_rew_mean | 8.86 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14964 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3307 |\n", + "| total_timesteps | 199294 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00876 |\n", + "| n_updates | 37323 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 620 |\n", + "| ep_rew_mean | 8.92 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14968 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3309 |\n", + "| total_timesteps | 199383 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0054 |\n", + "| n_updates | 37345 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 618 |\n", + "| ep_rew_mean | 8.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14972 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3311 |\n", + "| total_timesteps | 199462 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0147 |\n", + "| n_updates | 37365 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 618 |\n", + "| ep_rew_mean | 8.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14976 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3314 |\n", + "| total_timesteps | 199516 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0129 |\n", + "| n_updates | 37378 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 618 |\n", + "| ep_rew_mean | 8.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14980 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3316 |\n", + "| total_timesteps | 199629 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00581 |\n", + "| n_updates | 37407 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 618 |\n", + "| ep_rew_mean | 8.8 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14984 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3319 |\n", + "| total_timesteps | 199738 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.0201 |\n", + "| n_updates | 37434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 617 |\n", + "| ep_rew_mean | 8.78 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14988 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3321 |\n", + "| total_timesteps | 199818 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00665 |\n", + "| n_updates | 37454 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 614 |\n", + "| ep_rew_mean | 8.72 |\n", + "| exploration_rate | 0.05 |\n", + "| time/ | |\n", + "| episodes | 14992 |\n", + "| fps | 60 |\n", + "| time_elapsed | 3323 |\n", + "| total_timesteps | 199928 |\n", + "| train/ | |\n", + "| learning_rate | 0.0001 |\n", + "| loss | 0.00565 |\n", + "| n_updates | 37481 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "******* Training A2C *******\n", + "Using cuda device\n", + "Wrapping the env in a VecTransposeImage.\n", + "Logging to Breakout-v0\\A2C_200000\\logs\\A2C_1\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.38 |\n", + "| time/ | |\n", + "| fps | 61 |\n", + "| iterations | 100 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.38 |\n", + "| explained_variance | 0.431 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 99 |\n", + "| policy_loss | -0.0169 |\n", + "| value_loss | 0.000148 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.42 |\n", + "| time/ | |\n", + "| fps | 81 |\n", + "| iterations | 200 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 1000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.39 |\n", + "| explained_variance | -158 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 199 |\n", + "| policy_loss | 0.0358 |\n", + "| value_loss | 0.00154 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.33 |\n", + "| time/ | |\n", + "| fps | 89 |\n", + "| iterations | 300 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 1500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.34 |\n", + "| explained_variance | -144 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 299 |\n", + "| policy_loss | 0.281 |\n", + "| value_loss | 0.241 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| time/ | |\n", + "| fps | 95 |\n", + "| iterations | 400 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 2000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.39 |\n", + "| explained_variance | -45.1 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 399 |\n", + "| policy_loss | 0.106 |\n", + "| value_loss | 0.00641 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.49 |\n", + "| time/ | |\n", + "| fps | 97 |\n", + "| iterations | 500 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 2500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.38 |\n", + "| explained_variance | -3.19 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 499 |\n", + "| policy_loss | -0.0491 |\n", + "| value_loss | 0.00238 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.56 |\n", + "| time/ | |\n", + "| fps | 101 |\n", + "| iterations | 600 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 3000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.34 |\n", + "| explained_variance | 0.302 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 599 |\n", + "| policy_loss | 0.277 |\n", + "| value_loss | 0.176 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.49 |\n", + "| time/ | |\n", + "| fps | 103 |\n", + "| iterations | 700 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 3500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.37 |\n", + "| explained_variance | 0.695 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 699 |\n", + "| policy_loss | 0.0781 |\n", + "| value_loss | 0.0501 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| time/ | |\n", + "| fps | 105 |\n", + "| iterations | 800 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 4000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.26 |\n", + "| explained_variance | -152 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 799 |\n", + "| policy_loss | 0.0551 |\n", + "| value_loss | 0.00174 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| time/ | |\n", + "| fps | 106 |\n", + "| iterations | 900 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 4500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.39 |\n", + "| explained_variance | -168 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 899 |\n", + "| policy_loss | -0.0546 |\n", + "| value_loss | 0.00353 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| time/ | |\n", + "| fps | 108 |\n", + "| iterations | 1000 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 5000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.38 |\n", + "| explained_variance | -565 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 999 |\n", + "| policy_loss | -0.0288 |\n", + "| value_loss | 0.00594 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| time/ | |\n", + "| fps | 108 |\n", + "| iterations | 1100 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 5500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.3 |\n", + "| explained_variance | 0.926 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 1099 |\n", + "| policy_loss | -0.0426 |\n", + "| value_loss | 0.0172 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.52 |\n", + "| time/ | |\n", + "| fps | 109 |\n", + "| iterations | 1200 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 6000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.22 |\n", + "| explained_variance | -133 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 1199 |\n", + "| policy_loss | 0.491 |\n", + "| value_loss | 0.197 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| time/ | |\n", + "| fps | 110 |\n", + "| iterations | 1300 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 6500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.678 |\n", + "| explained_variance | -72.1 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 1299 |\n", + "| policy_loss | -0.0134 |\n", + "| value_loss | 0.107 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.74 |\n", + "| time/ | |\n", + "| fps | 111 |\n", + "| iterations | 1400 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 7000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.38 |\n", + "| explained_variance | -109 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 1399 |\n", + "| policy_loss | 0.013 |\n", + "| value_loss | 0.000111 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.64 |\n", + "| time/ | |\n", + "| fps | 111 |\n", + "| iterations | 1500 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 7500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.33 |\n", + "| explained_variance | 0.953 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 1499 |\n", + "| policy_loss | -0.169 |\n", + "| value_loss | 0.0329 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.74 |\n", + "| time/ | |\n", + "| fps | 112 |\n", + "| iterations | 1600 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 8000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.36 |\n", + "| explained_variance | -1.57e+03 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 1599 |\n", + "| policy_loss | -0.314 |\n", + "| value_loss | 0.0848 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.75 |\n", + "| time/ | |\n", + "| fps | 112 |\n", + "| iterations | 1700 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 8500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.37 |\n", + "| explained_variance | -581 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 1699 |\n", + "| policy_loss | 0.023 |\n", + "| value_loss | 0.000288 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.82 |\n", + "| time/ | |\n", + "| fps | 112 |\n", + "| iterations | 1800 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 9000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.38 |\n", + "| explained_variance | 0.37 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 1799 |\n", + "| policy_loss | 0.133 |\n", + "| value_loss | 0.111 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.93 |\n", + "| time/ | |\n", + "| fps | 113 |\n", + "| iterations | 1900 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 9500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.35 |\n", + "| explained_variance | 0.783 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 1899 |\n", + "| policy_loss | -0.0277 |\n", + "| value_loss | 0.0368 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.01 |\n", + "| time/ | |\n", + "| fps | 113 |\n", + "| iterations | 2000 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 10000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.37 |\n", + "| explained_variance | 0.446 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 1999 |\n", + "| policy_loss | 0.422 |\n", + "| value_loss | 0.205 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.01 |\n", + "| time/ | |\n", + "| fps | 114 |\n", + "| iterations | 2100 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 10500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.11 |\n", + "| explained_variance | -333 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 2099 |\n", + "| policy_loss | -0.0415 |\n", + "| value_loss | 0.1 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 1.98 |\n", + "| time/ | |\n", + "| fps | 114 |\n", + "| iterations | 2200 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 11000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.38 |\n", + "| explained_variance | -5.69e+12 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 2199 |\n", + "| policy_loss | -0.0534 |\n", + "| value_loss | 0.00156 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.04 |\n", + "| time/ | |\n", + "| fps | 114 |\n", + "| iterations | 2300 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 11500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.19 |\n", + "| explained_variance | 0.983 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 2299 |\n", + "| policy_loss | -0.203 |\n", + "| value_loss | 0.0278 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 312 |\n", + "| ep_rew_mean | 2.11 |\n", + "| time/ | |\n", + "| fps | 114 |\n", + "| iterations | 2400 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 12000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.38 |\n", + "| explained_variance | -4.82 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 2399 |\n", + "| policy_loss | -0.0282 |\n", + "| value_loss | 0.00188 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 313 |\n", + "| ep_rew_mean | 2.15 |\n", + "| time/ | |\n", + "| fps | 115 |\n", + "| iterations | 2500 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 12500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.3 |\n", + "| explained_variance | 0.647 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 2499 |\n", + "| policy_loss | 0.0815 |\n", + "| value_loss | 0.0591 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 314 |\n", + "| ep_rew_mean | 2.12 |\n", + "| time/ | |\n", + "| fps | 115 |\n", + "| iterations | 2600 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 13000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.07 |\n", + "| explained_variance | 0.533 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 2599 |\n", + "| policy_loss | -0.578 |\n", + "| value_loss | 0.237 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 317 |\n", + "| ep_rew_mean | 2.19 |\n", + "| time/ | |\n", + "| fps | 115 |\n", + "| iterations | 2700 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 13500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.38 |\n", + "| explained_variance | nan |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 2699 |\n", + "| policy_loss | -0.0742 |\n", + "| value_loss | 0.00349 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 324 |\n", + "| ep_rew_mean | 2.32 |\n", + "| time/ | |\n", + "| fps | 116 |\n", + "| iterations | 2800 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 14000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.18 |\n", + "| explained_variance | 0.654 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 2799 |\n", + "| policy_loss | 0.0865 |\n", + "| value_loss | 0.0911 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 321 |\n", + "| ep_rew_mean | 2.27 |\n", + "| time/ | |\n", + "| fps | 116 |\n", + "| iterations | 2900 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 14500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.35 |\n", + "| explained_variance | -1.31e+14 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 2899 |\n", + "| policy_loss | -0.0282 |\n", + "| value_loss | 0.000549 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 327 |\n", + "| ep_rew_mean | 2.41 |\n", + "| time/ | |\n", + "| fps | 116 |\n", + "| iterations | 3000 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 15000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.36 |\n", + "| explained_variance | -172 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 2999 |\n", + "| policy_loss | 0.129 |\n", + "| value_loss | 0.0106 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 328 |\n", + "| ep_rew_mean | 2.42 |\n", + "| time/ | |\n", + "| fps | 116 |\n", + "| iterations | 3100 |\n", + "| time_elapsed | 133 |\n", + "| total_timesteps | 15500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.36 |\n", + "| explained_variance | -4.42 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 3099 |\n", + "| policy_loss | -0.0824 |\n", + "| value_loss | 0.00542 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 325 |\n", + "| ep_rew_mean | 2.35 |\n", + "| time/ | |\n", + "| fps | 116 |\n", + "| iterations | 3200 |\n", + "| time_elapsed | 137 |\n", + "| total_timesteps | 16000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.37 |\n", + "| explained_variance | -1.58e+03 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 3199 |\n", + "| policy_loss | 0.0442 |\n", + "| value_loss | 0.00107 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 325 |\n", + "| ep_rew_mean | 2.33 |\n", + "| time/ | |\n", + "| fps | 116 |\n", + "| iterations | 3300 |\n", + "| time_elapsed | 141 |\n", + "| total_timesteps | 16500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.484 |\n", + "| explained_variance | -26.7 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 3299 |\n", + "| policy_loss | 0.0549 |\n", + "| value_loss | 0.0116 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 328 |\n", + "| ep_rew_mean | 2.39 |\n", + "| time/ | |\n", + "| fps | 116 |\n", + "| iterations | 3400 |\n", + "| time_elapsed | 145 |\n", + "| total_timesteps | 17000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.579 |\n", + "| explained_variance | -22.8 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 3399 |\n", + "| policy_loss | 0.136 |\n", + "| value_loss | 0.121 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 331 |\n", + "| ep_rew_mean | 2.44 |\n", + "| time/ | |\n", + "| fps | 116 |\n", + "| iterations | 3500 |\n", + "| time_elapsed | 149 |\n", + "| total_timesteps | 17500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.158 |\n", + "| explained_variance | -5.08 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 3499 |\n", + "| policy_loss | 0.00928 |\n", + "| value_loss | 0.0803 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 337 |\n", + "| ep_rew_mean | 2.56 |\n", + "| time/ | |\n", + "| fps | 117 |\n", + "| iterations | 3600 |\n", + "| time_elapsed | 153 |\n", + "| total_timesteps | 18000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.855 |\n", + "| explained_variance | -19.5 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 3599 |\n", + "| policy_loss | 0.0255 |\n", + "| value_loss | 0.00623 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 342 |\n", + "| ep_rew_mean | 2.67 |\n", + "| time/ | |\n", + "| fps | 117 |\n", + "| iterations | 3700 |\n", + "| time_elapsed | 156 |\n", + "| total_timesteps | 18500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.37 |\n", + "| explained_variance | nan |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 3699 |\n", + "| policy_loss | -0.157 |\n", + "| value_loss | 0.0113 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 342 |\n", + "| ep_rew_mean | 2.7 |\n", + "| time/ | |\n", + "| fps | 117 |\n", + "| iterations | 3800 |\n", + "| time_elapsed | 161 |\n", + "| total_timesteps | 19000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.01 |\n", + "| explained_variance | 0.94 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 3799 |\n", + "| policy_loss | 0.219 |\n", + "| value_loss | 0.0417 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 345 |\n", + "| ep_rew_mean | 2.77 |\n", + "| time/ | |\n", + "| fps | 118 |\n", + "| iterations | 3900 |\n", + "| time_elapsed | 165 |\n", + "| total_timesteps | 19500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.35 |\n", + "| explained_variance | -5.57e+03 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 3899 |\n", + "| policy_loss | -0.114 |\n", + "| value_loss | 0.0597 |\n", + "-------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 347 |\n", + "| ep_rew_mean | 2.82 |\n", + "| time/ | |\n", + "| fps | 118 |\n", + "| iterations | 4000 |\n", + "| time_elapsed | 169 |\n", + "| total_timesteps | 20000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.34 |\n", + "| explained_variance | -2.67 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 3999 |\n", + "| policy_loss | 0.793 |\n", + "| value_loss | 0.405 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 351 |\n", + "| ep_rew_mean | 2.9 |\n", + "| time/ | |\n", + "| fps | 118 |\n", + "| iterations | 4100 |\n", + "| time_elapsed | 173 |\n", + "| total_timesteps | 20500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.38 |\n", + "| explained_variance | -139 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 4099 |\n", + "| policy_loss | 0.35 |\n", + "| value_loss | 0.0788 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 346 |\n", + "| ep_rew_mean | 2.83 |\n", + "| time/ | |\n", + "| fps | 118 |\n", + "| iterations | 4200 |\n", + "| time_elapsed | 177 |\n", + "| total_timesteps | 21000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.969 |\n", + "| explained_variance | 0.693 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 4199 |\n", + "| policy_loss | -0.0455 |\n", + "| value_loss | 0.106 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 352 |\n", + "| ep_rew_mean | 2.92 |\n", + "| time/ | |\n", + "| fps | 118 |\n", + "| iterations | 4300 |\n", + "| time_elapsed | 181 |\n", + "| total_timesteps | 21500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.25 |\n", + "| explained_variance | 0.962 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 4299 |\n", + "| policy_loss | -0.107 |\n", + "| value_loss | 0.0118 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 351 |\n", + "| ep_rew_mean | 2.91 |\n", + "| time/ | |\n", + "| fps | 118 |\n", + "| iterations | 4400 |\n", + "| time_elapsed | 185 |\n", + "| total_timesteps | 22000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.3 |\n", + "| explained_variance | -0.758 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 4399 |\n", + "| policy_loss | 0.456 |\n", + "| value_loss | 0.37 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 359 |\n", + "| ep_rew_mean | 3.06 |\n", + "| time/ | |\n", + "| fps | 118 |\n", + "| iterations | 4500 |\n", + "| time_elapsed | 189 |\n", + "| total_timesteps | 22500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.19 |\n", + "| explained_variance | -84.6 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 4499 |\n", + "| policy_loss | 0.353 |\n", + "| value_loss | 0.125 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 364 |\n", + "| ep_rew_mean | 3.15 |\n", + "| time/ | |\n", + "| fps | 119 |\n", + "| iterations | 4600 |\n", + "| time_elapsed | 193 |\n", + "| total_timesteps | 23000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.24 |\n", + "| explained_variance | -469 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 4599 |\n", + "| policy_loss | -0.283 |\n", + "| value_loss | 0.0721 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 370 |\n", + "| ep_rew_mean | 3.31 |\n", + "| time/ | |\n", + "| fps | 119 |\n", + "| iterations | 4700 |\n", + "| time_elapsed | 197 |\n", + "| total_timesteps | 23500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.1 |\n", + "| explained_variance | 0.13 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 4699 |\n", + "| policy_loss | 0.634 |\n", + "| value_loss | 0.634 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 376 |\n", + "| ep_rew_mean | 3.42 |\n", + "| time/ | |\n", + "| fps | 119 |\n", + "| iterations | 4800 |\n", + "| time_elapsed | 201 |\n", + "| total_timesteps | 24000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.468 |\n", + "| explained_variance | -92.4 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 4799 |\n", + "| policy_loss | 0.0134 |\n", + "| value_loss | 0.00518 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 380 |\n", + "| ep_rew_mean | 3.6 |\n", + "| time/ | |\n", + "| fps | 119 |\n", + "| iterations | 4900 |\n", + "| time_elapsed | 205 |\n", + "| total_timesteps | 24500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.17 |\n", + "| explained_variance | -93.3 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 4899 |\n", + "| policy_loss | -0.102 |\n", + "| value_loss | 0.00795 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 386 |\n", + "| ep_rew_mean | 3.72 |\n", + "| time/ | |\n", + "| fps | 119 |\n", + "| iterations | 5000 |\n", + "| time_elapsed | 209 |\n", + "| total_timesteps | 25000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.643 |\n", + "| explained_variance | 0.723 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 4999 |\n", + "| policy_loss | -0.115 |\n", + "| value_loss | 0.0284 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 383 |\n", + "| ep_rew_mean | 3.68 |\n", + "| time/ | |\n", + "| fps | 119 |\n", + "| iterations | 5100 |\n", + "| time_elapsed | 213 |\n", + "| total_timesteps | 25500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.19 |\n", + "| explained_variance | -2.02e+03 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 5099 |\n", + "| policy_loss | -0.168 |\n", + "| value_loss | 0.0234 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 384 |\n", + "| ep_rew_mean | 3.73 |\n", + "| time/ | |\n", + "| fps | 119 |\n", + "| iterations | 5200 |\n", + "| time_elapsed | 217 |\n", + "| total_timesteps | 26000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.03 |\n", + "| explained_variance | -21.1 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 5199 |\n", + "| policy_loss | 0.157 |\n", + "| value_loss | 0.0735 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 388 |\n", + "| ep_rew_mean | 3.81 |\n", + "| time/ | |\n", + "| fps | 119 |\n", + "| iterations | 5300 |\n", + "| time_elapsed | 221 |\n", + "| total_timesteps | 26500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.355 |\n", + "| explained_variance | -1.19e+05 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 5299 |\n", + "| policy_loss | -0.000796 |\n", + "| value_loss | 0.000292 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 391 |\n", + "| ep_rew_mean | 3.89 |\n", + "| time/ | |\n", + "| fps | 119 |\n", + "| iterations | 5400 |\n", + "| time_elapsed | 225 |\n", + "| total_timesteps | 27000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.7 |\n", + "| explained_variance | -28.4 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 5399 |\n", + "| policy_loss | -0.13 |\n", + "| value_loss | 0.0372 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 394 |\n", + "| ep_rew_mean | 3.96 |\n", + "| time/ | |\n", + "| fps | 119 |\n", + "| iterations | 5500 |\n", + "| time_elapsed | 229 |\n", + "| total_timesteps | 27500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.596 |\n", + "| explained_variance | -60 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 5499 |\n", + "| policy_loss | 0.0286 |\n", + "| value_loss | 0.00444 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 395 |\n", + "| ep_rew_mean | 4 |\n", + "| time/ | |\n", + "| fps | 120 |\n", + "| iterations | 5600 |\n", + "| time_elapsed | 233 |\n", + "| total_timesteps | 28000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.379 |\n", + "| explained_variance | -22.3 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 5599 |\n", + "| policy_loss | 0.113 |\n", + "| value_loss | 0.195 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 400 |\n", + "| ep_rew_mean | 4.11 |\n", + "| time/ | |\n", + "| fps | 120 |\n", + "| iterations | 5700 |\n", + "| time_elapsed | 237 |\n", + "| total_timesteps | 28500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.839 |\n", + "| explained_variance | -41.1 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 5699 |\n", + "| policy_loss | 0.316 |\n", + "| value_loss | 0.222 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 404 |\n", + "| ep_rew_mean | 4.2 |\n", + "| time/ | |\n", + "| fps | 120 |\n", + "| iterations | 5800 |\n", + "| time_elapsed | 241 |\n", + "| total_timesteps | 29000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.09 |\n", + "| explained_variance | -106 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 5799 |\n", + "| policy_loss | 0.0756 |\n", + "| value_loss | 0.0833 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 406 |\n", + "| ep_rew_mean | 4.26 |\n", + "| time/ | |\n", + "| fps | 120 |\n", + "| iterations | 5900 |\n", + "| time_elapsed | 245 |\n", + "| total_timesteps | 29500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.05 |\n", + "| explained_variance | 0.836 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 5899 |\n", + "| policy_loss | 0.133 |\n", + "| value_loss | 0.059 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 408 |\n", + "| ep_rew_mean | 4.33 |\n", + "| time/ | |\n", + "| fps | 120 |\n", + "| iterations | 6000 |\n", + "| time_elapsed | 249 |\n", + "| total_timesteps | 30000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.901 |\n", + "| explained_variance | 0.725 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 5999 |\n", + "| policy_loss | -0.257 |\n", + "| value_loss | 0.0977 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 411 |\n", + "| ep_rew_mean | 4.39 |\n", + "| time/ | |\n", + "| fps | 120 |\n", + "| iterations | 6100 |\n", + "| time_elapsed | 253 |\n", + "| total_timesteps | 30500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.04 |\n", + "| explained_variance | 0.585 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 6099 |\n", + "| policy_loss | 0.00204 |\n", + "| value_loss | 0.218 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 413 |\n", + "| ep_rew_mean | 4.44 |\n", + "| time/ | |\n", + "| fps | 120 |\n", + "| iterations | 6200 |\n", + "| time_elapsed | 257 |\n", + "| total_timesteps | 31000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.725 |\n", + "| explained_variance | 0.768 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 6199 |\n", + "| policy_loss | 0.0224 |\n", + "| value_loss | 0.0463 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 417 |\n", + "| ep_rew_mean | 4.52 |\n", + "| time/ | |\n", + "| fps | 120 |\n", + "| iterations | 6300 |\n", + "| time_elapsed | 261 |\n", + "| total_timesteps | 31500 |\n", + "| train/ | |\n", + "| entropy_loss | -1.32 |\n", + "| explained_variance | -124 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 6299 |\n", + "| policy_loss | 0.0183 |\n", + "| value_loss | 0.0135 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 423 |\n", + "| ep_rew_mean | 4.67 |\n", + "| time/ | |\n", + "| fps | 120 |\n", + "| iterations | 6400 |\n", + "| time_elapsed | 265 |\n", + "| total_timesteps | 32000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.338 |\n", + "| explained_variance | -27.6 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 6399 |\n", + "| policy_loss | 0.428 |\n", + "| value_loss | 0.681 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 414 |\n", + "| ep_rew_mean | 4.52 |\n", + "| time/ | |\n", + "| fps | 120 |\n", + "| iterations | 6500 |\n", + "| time_elapsed | 269 |\n", + "| total_timesteps | 32500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.628 |\n", + "| explained_variance | 0.75 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 6499 |\n", + "| policy_loss | -0.226 |\n", + "| value_loss | 0.398 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 421 |\n", + "| ep_rew_mean | 4.68 |\n", + "| time/ | |\n", + "| fps | 120 |\n", + "| iterations | 6600 |\n", + "| time_elapsed | 273 |\n", + "| total_timesteps | 33000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.577 |\n", + "| explained_variance | -9.6 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 6599 |\n", + "| policy_loss | -0.0411 |\n", + "| value_loss | 0.00639 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 415 |\n", + "| ep_rew_mean | 4.51 |\n", + "| time/ | |\n", + "| fps | 120 |\n", + "| iterations | 6700 |\n", + "| time_elapsed | 276 |\n", + "| total_timesteps | 33500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.737 |\n", + "| explained_variance | 0.949 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 6699 |\n", + "| policy_loss | -0.283 |\n", + "| value_loss | 0.358 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 420 |\n", + "| ep_rew_mean | 4.59 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 6800 |\n", + "| time_elapsed | 280 |\n", + "| total_timesteps | 34000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.313 |\n", + "| explained_variance | -212 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 6799 |\n", + "| policy_loss | 0.00876 |\n", + "| value_loss | 0.0252 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 425 |\n", + "| ep_rew_mean | 4.72 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 6900 |\n", + "| time_elapsed | 284 |\n", + "| total_timesteps | 34500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.41 |\n", + "| explained_variance | 0.996 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 6899 |\n", + "| policy_loss | -0.0296 |\n", + "| value_loss | 0.00355 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 427 |\n", + "| ep_rew_mean | 4.79 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 7000 |\n", + "| time_elapsed | 288 |\n", + "| total_timesteps | 35000 |\n", + "| train/ | |\n", + "| entropy_loss | -1.14 |\n", + "| explained_variance | 0.936 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 6999 |\n", + "| policy_loss | -0.0454 |\n", + "| value_loss | 0.00183 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 430 |\n", + "| ep_rew_mean | 4.86 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 7100 |\n", + "| time_elapsed | 292 |\n", + "| total_timesteps | 35500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.844 |\n", + "| explained_variance | 0.323 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 7099 |\n", + "| policy_loss | 0.188 |\n", + "| value_loss | 0.13 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 430 |\n", + "| ep_rew_mean | 4.88 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 7200 |\n", + "| time_elapsed | 296 |\n", + "| total_timesteps | 36000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000147 |\n", + "| explained_variance | -18.6 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 7199 |\n", + "| policy_loss | -1.77e-06 |\n", + "| value_loss | 0.0214 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 433 |\n", + "| ep_rew_mean | 4.94 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 7300 |\n", + "| time_elapsed | 300 |\n", + "| total_timesteps | 36500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.142 |\n", + "| explained_variance | -8.86 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 7299 |\n", + "| policy_loss | 0.00275 |\n", + "| value_loss | 0.0185 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 436 |\n", + "| ep_rew_mean | 5.01 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 7400 |\n", + "| time_elapsed | 304 |\n", + "| total_timesteps | 37000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.581 |\n", + "| explained_variance | nan |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 7399 |\n", + "| policy_loss | -7.58e-05 |\n", + "| value_loss | 0.000285 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 435 |\n", + "| ep_rew_mean | 4.97 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 7500 |\n", + "| time_elapsed | 308 |\n", + "| total_timesteps | 37500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.865 |\n", + "| explained_variance | 0.979 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 7499 |\n", + "| policy_loss | -0.0644 |\n", + "| value_loss | 0.0122 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 434 |\n", + "| ep_rew_mean | 4.95 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 7600 |\n", + "| time_elapsed | 312 |\n", + "| total_timesteps | 38000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.415 |\n", + "| explained_variance | -128 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 7599 |\n", + "| policy_loss | 0.0316 |\n", + "| value_loss | 0.0865 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 433 |\n", + "| ep_rew_mean | 4.92 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 7700 |\n", + "| time_elapsed | 316 |\n", + "| total_timesteps | 38500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.402 |\n", + "| explained_variance | -4.93 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 7699 |\n", + "| policy_loss | 0.0676 |\n", + "| value_loss | 0.0324 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 436 |\n", + "| ep_rew_mean | 4.96 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 7800 |\n", + "| time_elapsed | 320 |\n", + "| total_timesteps | 39000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.455 |\n", + "| explained_variance | -1.03e+04 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 7799 |\n", + "| policy_loss | 0.014 |\n", + "| value_loss | 0.00507 |\n", + "-------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 438 |\n", + "| ep_rew_mean | 5.03 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 7900 |\n", + "| time_elapsed | 324 |\n", + "| total_timesteps | 39500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.798 |\n", + "| explained_variance | 0.797 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 7899 |\n", + "| policy_loss | 0.0318 |\n", + "| value_loss | 0.0564 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 437 |\n", + "| ep_rew_mean | 5.02 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 8000 |\n", + "| time_elapsed | 328 |\n", + "| total_timesteps | 40000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.796 |\n", + "| explained_variance | -537 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 7999 |\n", + "| policy_loss | -0.0313 |\n", + "| value_loss | 0.00465 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 439 |\n", + "| ep_rew_mean | 5.04 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 8100 |\n", + "| time_elapsed | 332 |\n", + "| total_timesteps | 40500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0931 |\n", + "| explained_variance | -16.2 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 8099 |\n", + "| policy_loss | -0.00705 |\n", + "| value_loss | 0.169 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 441 |\n", + "| ep_rew_mean | 5.08 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 8200 |\n", + "| time_elapsed | 336 |\n", + "| total_timesteps | 41000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.596 |\n", + "| explained_variance | -4.31e+08 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 8199 |\n", + "| policy_loss | 0.00427 |\n", + "| value_loss | 0.0142 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 440 |\n", + "| ep_rew_mean | 5.03 |\n", + "| time/ | |\n", + "| fps | 121 |\n", + "| iterations | 8300 |\n", + "| time_elapsed | 340 |\n", + "| total_timesteps | 41500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.715 |\n", + "| explained_variance | -3.97e+14 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 8299 |\n", + "| policy_loss | -0.00422 |\n", + "| value_loss | 0.00664 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 449 |\n", + "| ep_rew_mean | 5.18 |\n", + "| time/ | |\n", + "| fps | 122 |\n", + "| iterations | 8400 |\n", + "| time_elapsed | 344 |\n", + "| total_timesteps | 42000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.539 |\n", + "| explained_variance | -171 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 8399 |\n", + "| policy_loss | 0.454 |\n", + "| value_loss | 0.559 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 451 |\n", + "| ep_rew_mean | 5.21 |\n", + "| time/ | |\n", + "| fps | 122 |\n", + "| iterations | 8500 |\n", + "| time_elapsed | 348 |\n", + "| total_timesteps | 42500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.786 |\n", + "| explained_variance | -1.87e+04 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 8499 |\n", + "| policy_loss | -0.321 |\n", + "| value_loss | 0.202 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 452 |\n", + "| ep_rew_mean | 5.24 |\n", + "| time/ | |\n", + "| fps | 122 |\n", + "| iterations | 8600 |\n", + "| time_elapsed | 351 |\n", + "| total_timesteps | 43000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.916 |\n", + "| explained_variance | -287 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 8599 |\n", + "| policy_loss | 1.2 |\n", + "| value_loss | 0.496 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 456 |\n", + "| ep_rew_mean | 5.35 |\n", + "| time/ | |\n", + "| fps | 122 |\n", + "| iterations | 8700 |\n", + "| time_elapsed | 354 |\n", + "| total_timesteps | 43500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.653 |\n", + "| explained_variance | -3.17e+14 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 8699 |\n", + "| policy_loss | -0.0184 |\n", + "| value_loss | 0.00249 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 459 |\n", + "| ep_rew_mean | 5.41 |\n", + "| time/ | |\n", + "| fps | 122 |\n", + "| iterations | 8800 |\n", + "| time_elapsed | 358 |\n", + "| total_timesteps | 44000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.767 |\n", + "| explained_variance | 0.888 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 8799 |\n", + "| policy_loss | -0.15 |\n", + "| value_loss | 0.0295 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 463 |\n", + "| ep_rew_mean | 5.46 |\n", + "| time/ | |\n", + "| fps | 122 |\n", + "| iterations | 8900 |\n", + "| time_elapsed | 362 |\n", + "| total_timesteps | 44500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0506 |\n", + "| explained_variance | -2.26e+15 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 8899 |\n", + "| policy_loss | -9.94e-05 |\n", + "| value_loss | 0.00136 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 463 |\n", + "| ep_rew_mean | 5.44 |\n", + "| time/ | |\n", + "| fps | 122 |\n", + "| iterations | 9000 |\n", + "| time_elapsed | 366 |\n", + "| total_timesteps | 45000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000602 |\n", + "| explained_variance | -1.71 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 8999 |\n", + "| policy_loss | 6.21e-06 |\n", + "| value_loss | 0.0204 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 463 |\n", + "| ep_rew_mean | 5.42 |\n", + "| time/ | |\n", + "| fps | 122 |\n", + "| iterations | 9100 |\n", + "| time_elapsed | 370 |\n", + "| total_timesteps | 45500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.225 |\n", + "| explained_variance | -86.6 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 9099 |\n", + "| policy_loss | 0.00748 |\n", + "| value_loss | 0.0954 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 465 |\n", + "| ep_rew_mean | 5.44 |\n", + "| time/ | |\n", + "| fps | 122 |\n", + "| iterations | 9200 |\n", + "| time_elapsed | 374 |\n", + "| total_timesteps | 46000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.782 |\n", + "| explained_variance | nan |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 9199 |\n", + "| policy_loss | -0.0518 |\n", + "| value_loss | 0.0141 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 462 |\n", + "| ep_rew_mean | 5.4 |\n", + "| time/ | |\n", + "| fps | 122 |\n", + "| iterations | 9300 |\n", + "| time_elapsed | 378 |\n", + "| total_timesteps | 46500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.417 |\n", + "| explained_variance | 0.577 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 9299 |\n", + "| policy_loss | 0.142 |\n", + "| value_loss | 0.649 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 466 |\n", + "| ep_rew_mean | 5.46 |\n", + "| time/ | |\n", + "| fps | 122 |\n", + "| iterations | 9400 |\n", + "| time_elapsed | 382 |\n", + "| total_timesteps | 47000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.346 |\n", + "| explained_variance | -8.12 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 9399 |\n", + "| policy_loss | 0.132 |\n", + "| value_loss | 0.44 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 473 |\n", + "| ep_rew_mean | 5.59 |\n", + "| time/ | |\n", + "| fps | 122 |\n", + "| iterations | 9500 |\n", + "| time_elapsed | 386 |\n", + "| total_timesteps | 47500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.525 |\n", + "| explained_variance | -346 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 9499 |\n", + "| policy_loss | 0.357 |\n", + "| value_loss | 0.2 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 472 |\n", + "| ep_rew_mean | 5.57 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 9600 |\n", + "| time_elapsed | 390 |\n", + "| total_timesteps | 48000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.27 |\n", + "| explained_variance | -495 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 9599 |\n", + "| policy_loss | -0.025 |\n", + "| value_loss | 0.0475 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 474 |\n", + "| ep_rew_mean | 5.62 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 9700 |\n", + "| time_elapsed | 394 |\n", + "| total_timesteps | 48500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.336 |\n", + "| explained_variance | -19.3 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 9699 |\n", + "| policy_loss | -0.0273 |\n", + "| value_loss | 0.0335 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 471 |\n", + "| ep_rew_mean | 5.56 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 9800 |\n", + "| time_elapsed | 398 |\n", + "| total_timesteps | 49000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0581 |\n", + "| explained_variance | -56.2 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 9799 |\n", + "| policy_loss | -0.00118 |\n", + "| value_loss | 0.135 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 475 |\n", + "| ep_rew_mean | 5.66 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 9900 |\n", + "| time_elapsed | 402 |\n", + "| total_timesteps | 49500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.417 |\n", + "| explained_variance | 0.691 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 9899 |\n", + "| policy_loss | 0.00864 |\n", + "| value_loss | 0.141 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 471 |\n", + "| ep_rew_mean | 5.59 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 10000 |\n", + "| time_elapsed | 406 |\n", + "| total_timesteps | 50000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00192 |\n", + "| explained_variance | -3.39 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 9999 |\n", + "| policy_loss | -3.82e-06 |\n", + "| value_loss | 0.00289 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 468 |\n", + "| ep_rew_mean | 5.57 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 10100 |\n", + "| time_elapsed | 409 |\n", + "| total_timesteps | 50500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.238 |\n", + "| explained_variance | -215 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 10099 |\n", + "| policy_loss | 0.0646 |\n", + "| value_loss | 0.00962 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 464 |\n", + "| ep_rew_mean | 5.52 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 10200 |\n", + "| time_elapsed | 413 |\n", + "| total_timesteps | 51000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.102 |\n", + "| explained_variance | -109 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 10199 |\n", + "| policy_loss | 0.00401 |\n", + "| value_loss | 0.0973 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 464 |\n", + "| ep_rew_mean | 5.54 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 10300 |\n", + "| time_elapsed | 417 |\n", + "| total_timesteps | 51500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.147 |\n", + "| explained_variance | 0.894 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 10299 |\n", + "| policy_loss | 0.0056 |\n", + "| value_loss | 0.0207 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 462 |\n", + "| ep_rew_mean | 5.51 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 10400 |\n", + "| time_elapsed | 421 |\n", + "| total_timesteps | 52000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00015 |\n", + "| explained_variance | -48 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 10399 |\n", + "| policy_loss | 3.53e-06 |\n", + "| value_loss | 0.0486 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 463 |\n", + "| ep_rew_mean | 5.51 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 10500 |\n", + "| time_elapsed | 425 |\n", + "| total_timesteps | 52500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.283 |\n", + "| explained_variance | -16 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 10499 |\n", + "| policy_loss | -0.00312 |\n", + "| value_loss | 0.0199 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 462 |\n", + "| ep_rew_mean | 5.47 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 10600 |\n", + "| time_elapsed | 429 |\n", + "| total_timesteps | 53000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.478 |\n", + "| explained_variance | -971 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 10599 |\n", + "| policy_loss | -0.0175 |\n", + "| value_loss | 0.0238 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 457 |\n", + "| ep_rew_mean | 5.34 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 10700 |\n", + "| time_elapsed | 433 |\n", + "| total_timesteps | 53500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.605 |\n", + "| explained_variance | 0.708 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 10699 |\n", + "| policy_loss | -0.0298 |\n", + "| value_loss | 0.0031 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 453 |\n", + "| ep_rew_mean | 5.28 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 10800 |\n", + "| time_elapsed | 437 |\n", + "| total_timesteps | 54000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.551 |\n", + "| explained_variance | 0.622 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 10799 |\n", + "| policy_loss | 0.022 |\n", + "| value_loss | 0.0634 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 454 |\n", + "| ep_rew_mean | 5.3 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 10900 |\n", + "| time_elapsed | 441 |\n", + "| total_timesteps | 54500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.637 |\n", + "| explained_variance | -309 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 10899 |\n", + "| policy_loss | 0.623 |\n", + "| value_loss | 1.31 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 458 |\n", + "| ep_rew_mean | 5.42 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 11000 |\n", + "| time_elapsed | 445 |\n", + "| total_timesteps | 55000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0814 |\n", + "| explained_variance | -22 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 10999 |\n", + "| policy_loss | 0.000305 |\n", + "| value_loss | 0.00271 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 462 |\n", + "| ep_rew_mean | 5.51 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 11100 |\n", + "| time_elapsed | 449 |\n", + "| total_timesteps | 55500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.315 |\n", + "| explained_variance | 0.975 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 11099 |\n", + "| policy_loss | -0.0165 |\n", + "| value_loss | 0.00964 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 457 |\n", + "| ep_rew_mean | 5.4 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 11200 |\n", + "| time_elapsed | 453 |\n", + "| total_timesteps | 56000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.352 |\n", + "| explained_variance | -2.15e+03 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 11199 |\n", + "| policy_loss | 0.00299 |\n", + "| value_loss | 0.0314 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 459 |\n", + "| ep_rew_mean | 5.42 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 11300 |\n", + "| time_elapsed | 456 |\n", + "| total_timesteps | 56500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.209 |\n", + "| explained_variance | -4.63e+13 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 11299 |\n", + "| policy_loss | -0.0118 |\n", + "| value_loss | 0.0901 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 458 |\n", + "| ep_rew_mean | 5.41 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 11400 |\n", + "| time_elapsed | 461 |\n", + "| total_timesteps | 57000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.27 |\n", + "| explained_variance | -12.6 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 11399 |\n", + "| policy_loss | -0.0566 |\n", + "| value_loss | 0.0629 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 459 |\n", + "| ep_rew_mean | 5.43 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 11500 |\n", + "| time_elapsed | 465 |\n", + "| total_timesteps | 57500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.396 |\n", + "| explained_variance | -3.27 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 11499 |\n", + "| policy_loss | -0.0127 |\n", + "| value_loss | 0.00557 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 456 |\n", + "| ep_rew_mean | 5.38 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 11600 |\n", + "| time_elapsed | 469 |\n", + "| total_timesteps | 58000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.192 |\n", + "| explained_variance | -711 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 11599 |\n", + "| policy_loss | 0.0142 |\n", + "| value_loss | 0.277 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 455 |\n", + "| ep_rew_mean | 5.34 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 11700 |\n", + "| time_elapsed | 473 |\n", + "| total_timesteps | 58500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.249 |\n", + "| explained_variance | -6.55 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 11699 |\n", + "| policy_loss | 0.00418 |\n", + "| value_loss | 0.00337 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 458 |\n", + "| ep_rew_mean | 5.4 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 11800 |\n", + "| time_elapsed | 477 |\n", + "| total_timesteps | 59000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.255 |\n", + "| explained_variance | 0.575 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 11799 |\n", + "| policy_loss | -0.0104 |\n", + "| value_loss | 0.295 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 462 |\n", + "| ep_rew_mean | 5.45 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 11900 |\n", + "| time_elapsed | 481 |\n", + "| total_timesteps | 59500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00326 |\n", + "| explained_variance | -22.8 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 11899 |\n", + "| policy_loss | 3.13e-05 |\n", + "| value_loss | 0.00384 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 466 |\n", + "| ep_rew_mean | 5.55 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 12000 |\n", + "| time_elapsed | 485 |\n", + "| total_timesteps | 60000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.317 |\n", + "| explained_variance | 0.798 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 11999 |\n", + "| policy_loss | -0.0277 |\n", + "| value_loss | 0.0567 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 468 |\n", + "| ep_rew_mean | 5.59 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 12100 |\n", + "| time_elapsed | 489 |\n", + "| total_timesteps | 60500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.442 |\n", + "| explained_variance | -0.642 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 12099 |\n", + "| policy_loss | 0.00757 |\n", + "| value_loss | 0.00172 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 471 |\n", + "| ep_rew_mean | 5.59 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 12200 |\n", + "| time_elapsed | 493 |\n", + "| total_timesteps | 61000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.287 |\n", + "| explained_variance | -15.6 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 12199 |\n", + "| policy_loss | -0.0282 |\n", + "| value_loss | 0.0115 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 466 |\n", + "| ep_rew_mean | 5.5 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 12300 |\n", + "| time_elapsed | 498 |\n", + "| total_timesteps | 61500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.437 |\n", + "| explained_variance | 0.287 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 12299 |\n", + "| policy_loss | -0.268 |\n", + "| value_loss | 0.152 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 465 |\n", + "| ep_rew_mean | 5.48 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 12400 |\n", + "| time_elapsed | 502 |\n", + "| total_timesteps | 62000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.133 |\n", + "| explained_variance | 0.702 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 12399 |\n", + "| policy_loss | 0.00454 |\n", + "| value_loss | 0.0748 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 460 |\n", + "| ep_rew_mean | 5.39 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 12500 |\n", + "| time_elapsed | 506 |\n", + "| total_timesteps | 62500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0167 |\n", + "| explained_variance | -2.72e+03 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 12499 |\n", + "| policy_loss | -0.000189 |\n", + "| value_loss | 0.00829 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 465 |\n", + "| ep_rew_mean | 5.48 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 12600 |\n", + "| time_elapsed | 509 |\n", + "| total_timesteps | 63000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.749 |\n", + "| explained_variance | 0.592 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 12599 |\n", + "| policy_loss | 0.0684 |\n", + "| value_loss | 0.0956 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 468 |\n", + "| ep_rew_mean | 5.55 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 12700 |\n", + "| time_elapsed | 513 |\n", + "| total_timesteps | 63500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.76 |\n", + "| explained_variance | nan |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 12699 |\n", + "| policy_loss | -0.234 |\n", + "| value_loss | 0.142 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 473 |\n", + "| ep_rew_mean | 5.7 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 12800 |\n", + "| time_elapsed | 517 |\n", + "| total_timesteps | 64000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.753 |\n", + "| explained_variance | -41 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 12799 |\n", + "| policy_loss | 0.0277 |\n", + "| value_loss | 0.043 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 472 |\n", + "| ep_rew_mean | 5.67 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 12900 |\n", + "| time_elapsed | 522 |\n", + "| total_timesteps | 64500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.213 |\n", + "| explained_variance | -5.95 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 12899 |\n", + "| policy_loss | 0.0291 |\n", + "| value_loss | 0.0812 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 466 |\n", + "| ep_rew_mean | 5.51 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 13000 |\n", + "| time_elapsed | 526 |\n", + "| total_timesteps | 65000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.42 |\n", + "| explained_variance | -54 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 12999 |\n", + "| policy_loss | -0.0321 |\n", + "| value_loss | 0.00705 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 469 |\n", + "| ep_rew_mean | 5.51 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 13100 |\n", + "| time_elapsed | 530 |\n", + "| total_timesteps | 65500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00717 |\n", + "| explained_variance | -1.36e+14 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 13099 |\n", + "| policy_loss | -5.44e-05 |\n", + "| value_loss | 0.00527 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 467 |\n", + "| ep_rew_mean | 5.49 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 13200 |\n", + "| time_elapsed | 534 |\n", + "| total_timesteps | 66000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.741 |\n", + "| explained_variance | -5.93 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 13199 |\n", + "| policy_loss | -0.191 |\n", + "| value_loss | 0.0686 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 467 |\n", + "| ep_rew_mean | 5.53 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 13300 |\n", + "| time_elapsed | 538 |\n", + "| total_timesteps | 66500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0991 |\n", + "| explained_variance | -23 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 13299 |\n", + "| policy_loss | 0.00915 |\n", + "| value_loss | 0.0875 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 469 |\n", + "| ep_rew_mean | 5.55 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 13400 |\n", + "| time_elapsed | 542 |\n", + "| total_timesteps | 67000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.653 |\n", + "| explained_variance | -6.64e+04 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 13399 |\n", + "| policy_loss | -0.0357 |\n", + "| value_loss | 0.00395 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 473 |\n", + "| ep_rew_mean | 5.69 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 13500 |\n", + "| time_elapsed | 546 |\n", + "| total_timesteps | 67500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.194 |\n", + "| explained_variance | -0.0144 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 13499 |\n", + "| policy_loss | -0.0748 |\n", + "| value_loss | 0.0134 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 479 |\n", + "| ep_rew_mean | 5.8 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 13600 |\n", + "| time_elapsed | 550 |\n", + "| total_timesteps | 68000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0254 |\n", + "| explained_variance | -0.147 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 13599 |\n", + "| policy_loss | 0.00346 |\n", + "| value_loss | 0.587 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 481 |\n", + "| ep_rew_mean | 5.83 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 13700 |\n", + "| time_elapsed | 554 |\n", + "| total_timesteps | 68500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.394 |\n", + "| explained_variance | -126 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 13699 |\n", + "| policy_loss | 0.0396 |\n", + "| value_loss | 0.0415 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 485 |\n", + "| ep_rew_mean | 5.89 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 13800 |\n", + "| time_elapsed | 558 |\n", + "| total_timesteps | 69000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.109 |\n", + "| explained_variance | -32.8 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 13799 |\n", + "| policy_loss | 0.0104 |\n", + "| value_loss | 0.116 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 484 |\n", + "| ep_rew_mean | 5.88 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 13900 |\n", + "| time_elapsed | 562 |\n", + "| total_timesteps | 69500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0463 |\n", + "| explained_variance | -9.72 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 13899 |\n", + "| policy_loss | 0.00047 |\n", + "| value_loss | 0.0208 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 485 |\n", + "| ep_rew_mean | 5.89 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 14000 |\n", + "| time_elapsed | 566 |\n", + "| total_timesteps | 70000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.473 |\n", + "| explained_variance | 0.92 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 13999 |\n", + "| policy_loss | -0.129 |\n", + "| value_loss | 0.0123 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 479 |\n", + "| ep_rew_mean | 5.75 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 14100 |\n", + "| time_elapsed | 570 |\n", + "| total_timesteps | 70500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0151 |\n", + "| explained_variance | 0.95 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 14099 |\n", + "| policy_loss | -0.00057 |\n", + "| value_loss | 0.0259 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 475 |\n", + "| ep_rew_mean | 5.66 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 14200 |\n", + "| time_elapsed | 574 |\n", + "| total_timesteps | 71000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0128 |\n", + "| explained_variance | -19.7 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 14199 |\n", + "| policy_loss | 7.99e-05 |\n", + "| value_loss | 0.00733 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 478 |\n", + "| ep_rew_mean | 5.68 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 14300 |\n", + "| time_elapsed | 579 |\n", + "| total_timesteps | 71500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.469 |\n", + "| explained_variance | 0.796 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 14299 |\n", + "| policy_loss | -0.0892 |\n", + "| value_loss | 0.0796 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 482 |\n", + "| ep_rew_mean | 5.75 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 14400 |\n", + "| time_elapsed | 583 |\n", + "| total_timesteps | 72000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.498 |\n", + "| explained_variance | -6.32 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 14399 |\n", + "| policy_loss | 0.0373 |\n", + "| value_loss | 0.0237 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 486 |\n", + "| ep_rew_mean | 5.8 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 14500 |\n", + "| time_elapsed | 587 |\n", + "| total_timesteps | 72500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.306 |\n", + "| explained_variance | -17.3 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 14499 |\n", + "| policy_loss | -0.0178 |\n", + "| value_loss | 0.0636 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 490 |\n", + "| ep_rew_mean | 5.83 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 14600 |\n", + "| time_elapsed | 591 |\n", + "| total_timesteps | 73000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.232 |\n", + "| explained_variance | -520 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 14599 |\n", + "| policy_loss | 0.00765 |\n", + "| value_loss | 0.0106 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 484 |\n", + "| ep_rew_mean | 5.73 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 14700 |\n", + "| time_elapsed | 595 |\n", + "| total_timesteps | 73500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.066 |\n", + "| explained_variance | -95.5 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 14699 |\n", + "| policy_loss | 0.00206 |\n", + "| value_loss | 0.0155 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 480 |\n", + "| ep_rew_mean | 5.6 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 14800 |\n", + "| time_elapsed | 599 |\n", + "| total_timesteps | 74000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.544 |\n", + "| explained_variance | 0.878 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 14799 |\n", + "| policy_loss | -0.348 |\n", + "| value_loss | 0.0918 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 479 |\n", + "| ep_rew_mean | 5.56 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 14900 |\n", + "| time_elapsed | 603 |\n", + "| total_timesteps | 74500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000567 |\n", + "| explained_variance | -44.3 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 14899 |\n", + "| policy_loss | 1.57e-05 |\n", + "| value_loss | 0.0757 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 482 |\n", + "| ep_rew_mean | 5.61 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 15000 |\n", + "| time_elapsed | 607 |\n", + "| total_timesteps | 75000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.571 |\n", + "| explained_variance | -30.3 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 14999 |\n", + "| policy_loss | -0.161 |\n", + "| value_loss | 0.168 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 488 |\n", + "| ep_rew_mean | 5.75 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 15100 |\n", + "| time_elapsed | 611 |\n", + "| total_timesteps | 75500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.315 |\n", + "| explained_variance | 0.534 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 15099 |\n", + "| policy_loss | 0.111 |\n", + "| value_loss | 0.072 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 490 |\n", + "| ep_rew_mean | 5.81 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 15200 |\n", + "| time_elapsed | 615 |\n", + "| total_timesteps | 76000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.158 |\n", + "| explained_variance | -360 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 15199 |\n", + "| policy_loss | -0.0121 |\n", + "| value_loss | 0.0617 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 492 |\n", + "| ep_rew_mean | 5.84 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 15300 |\n", + "| time_elapsed | 619 |\n", + "| total_timesteps | 76500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0457 |\n", + "| explained_variance | -2.54 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 15299 |\n", + "| policy_loss | -1.15e-05 |\n", + "| value_loss | 0.00264 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 495 |\n", + "| ep_rew_mean | 5.88 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 15400 |\n", + "| time_elapsed | 623 |\n", + "| total_timesteps | 77000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0143 |\n", + "| explained_variance | -313 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 15399 |\n", + "| policy_loss | -0.00187 |\n", + "| value_loss | 0.303 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 490 |\n", + "| ep_rew_mean | 5.71 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 15500 |\n", + "| time_elapsed | 627 |\n", + "| total_timesteps | 77500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0831 |\n", + "| explained_variance | -2.18 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 15499 |\n", + "| policy_loss | -0.00581 |\n", + "| value_loss | 0.0361 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 472 |\n", + "| ep_rew_mean | 5.34 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 15600 |\n", + "| time_elapsed | 631 |\n", + "| total_timesteps | 78000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.237 |\n", + "| explained_variance | -6.73e+14 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 15599 |\n", + "| policy_loss | -0.0073 |\n", + "| value_loss | 0.00282 |\n", + "-------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 471 |\n", + "| ep_rew_mean | 5.33 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 15700 |\n", + "| time_elapsed | 635 |\n", + "| total_timesteps | 78500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0449 |\n", + "| explained_variance | -5.33e+04 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 15699 |\n", + "| policy_loss | -0.00465 |\n", + "| value_loss | 0.572 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 468 |\n", + "| ep_rew_mean | 5.28 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 15800 |\n", + "| time_elapsed | 639 |\n", + "| total_timesteps | 79000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.216 |\n", + "| explained_variance | 0.779 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 15799 |\n", + "| policy_loss | -0.035 |\n", + "| value_loss | 0.083 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 468 |\n", + "| ep_rew_mean | 5.25 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 15900 |\n", + "| time_elapsed | 643 |\n", + "| total_timesteps | 79500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.232 |\n", + "| explained_variance | -20.6 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 15899 |\n", + "| policy_loss | 0.035 |\n", + "| value_loss | 0.0346 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 472 |\n", + "| ep_rew_mean | 5.36 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 16000 |\n", + "| time_elapsed | 647 |\n", + "| total_timesteps | 80000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.3 |\n", + "| explained_variance | -1.04e+03 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 15999 |\n", + "| policy_loss | 0.00996 |\n", + "| value_loss | 0.0632 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 478 |\n", + "| ep_rew_mean | 5.45 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 16100 |\n", + "| time_elapsed | 650 |\n", + "| total_timesteps | 80500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.248 |\n", + "| explained_variance | -98 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 16099 |\n", + "| policy_loss | 0.0126 |\n", + "| value_loss | 0.0196 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 482 |\n", + "| ep_rew_mean | 5.56 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 16200 |\n", + "| time_elapsed | 653 |\n", + "| total_timesteps | 81000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.531 |\n", + "| explained_variance | -1.04e+15 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 16199 |\n", + "| policy_loss | -0.0429 |\n", + "| value_loss | 0.0275 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 485 |\n", + "| ep_rew_mean | 5.61 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 16300 |\n", + "| time_elapsed | 657 |\n", + "| total_timesteps | 81500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.185 |\n", + "| explained_variance | -23.9 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 16299 |\n", + "| policy_loss | 0.0238 |\n", + "| value_loss | 0.0449 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 479 |\n", + "| ep_rew_mean | 5.56 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 16400 |\n", + "| time_elapsed | 661 |\n", + "| total_timesteps | 82000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.334 |\n", + "| explained_variance | -475 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 16399 |\n", + "| policy_loss | 0.117 |\n", + "| value_loss | 0.0136 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 484 |\n", + "| ep_rew_mean | 5.71 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 16500 |\n", + "| time_elapsed | 665 |\n", + "| total_timesteps | 82500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000527 |\n", + "| explained_variance | -10.2 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 16499 |\n", + "| policy_loss | -3e-06 |\n", + "| value_loss | 0.0177 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 476 |\n", + "| ep_rew_mean | 5.6 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 16600 |\n", + "| time_elapsed | 670 |\n", + "| total_timesteps | 83000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.19 |\n", + "| explained_variance | -891 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 16599 |\n", + "| policy_loss | -0.00452 |\n", + "| value_loss | 0.00371 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 481 |\n", + "| ep_rew_mean | 5.71 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 16700 |\n", + "| time_elapsed | 674 |\n", + "| total_timesteps | 83500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.211 |\n", + "| explained_variance | -5.89 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 16699 |\n", + "| policy_loss | 0.0306 |\n", + "| value_loss | 0.141 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 488 |\n", + "| ep_rew_mean | 5.84 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 16800 |\n", + "| time_elapsed | 677 |\n", + "| total_timesteps | 84000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.384 |\n", + "| explained_variance | -18.2 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 16799 |\n", + "| policy_loss | 0.248 |\n", + "| value_loss | 0.108 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 489 |\n", + "| ep_rew_mean | 5.85 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 16900 |\n", + "| time_elapsed | 682 |\n", + "| total_timesteps | 84500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.477 |\n", + "| explained_variance | -5.82 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 16899 |\n", + "| policy_loss | 0.0215 |\n", + "| value_loss | 0.0131 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 489 |\n", + "| ep_rew_mean | 5.82 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 17000 |\n", + "| time_elapsed | 685 |\n", + "| total_timesteps | 85000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00669 |\n", + "| explained_variance | 0.752 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 16999 |\n", + "| policy_loss | -0.000434 |\n", + "| value_loss | 0.127 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 486 |\n", + "| ep_rew_mean | 5.79 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 17100 |\n", + "| time_elapsed | 690 |\n", + "| total_timesteps | 85500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00451 |\n", + "| explained_variance | -7.59 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 17099 |\n", + "| policy_loss | 6.27e-05 |\n", + "| value_loss | 0.00679 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 487 |\n", + "| ep_rew_mean | 5.8 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 17200 |\n", + "| time_elapsed | 693 |\n", + "| total_timesteps | 86000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00539 |\n", + "| explained_variance | -6.25 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 17199 |\n", + "| policy_loss | 5.78e-05 |\n", + "| value_loss | 0.00678 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 491 |\n", + "| ep_rew_mean | 5.85 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 17300 |\n", + "| time_elapsed | 697 |\n", + "| total_timesteps | 86500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.315 |\n", + "| explained_variance | 0.939 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 17299 |\n", + "| policy_loss | -7.17e-05 |\n", + "| value_loss | 0.016 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 500 |\n", + "| ep_rew_mean | 6.02 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 17400 |\n", + "| time_elapsed | 701 |\n", + "| total_timesteps | 87000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.367 |\n", + "| explained_variance | -72.6 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 17399 |\n", + "| policy_loss | 0.0928 |\n", + "| value_loss | 0.226 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 499 |\n", + "| ep_rew_mean | 6.02 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 17500 |\n", + "| time_elapsed | 706 |\n", + "| total_timesteps | 87500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000296 |\n", + "| explained_variance | -14.2 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 17499 |\n", + "| policy_loss | 9.45e-07 |\n", + "| value_loss | 0.0377 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 498 |\n", + "| ep_rew_mean | 6.02 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 17600 |\n", + "| time_elapsed | 710 |\n", + "| total_timesteps | 88000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0805 |\n", + "| explained_variance | -7.63e+13 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 17599 |\n", + "| policy_loss | 0.000702 |\n", + "| value_loss | 0.00263 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 504 |\n", + "| ep_rew_mean | 6.13 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 17700 |\n", + "| time_elapsed | 714 |\n", + "| total_timesteps | 88500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.667 |\n", + "| explained_variance | -31.1 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 17699 |\n", + "| policy_loss | 0.162 |\n", + "| value_loss | 0.286 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 516 |\n", + "| ep_rew_mean | 6.43 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 17800 |\n", + "| time_elapsed | 718 |\n", + "| total_timesteps | 89000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00193 |\n", + "| explained_variance | -1.97 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 17799 |\n", + "| policy_loss | -1.19e-06 |\n", + "| value_loss | 0.00072 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 519 |\n", + "| ep_rew_mean | 6.53 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 17900 |\n", + "| time_elapsed | 722 |\n", + "| total_timesteps | 89500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.364 |\n", + "| explained_variance | 0.606 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 17899 |\n", + "| policy_loss | 0.0072 |\n", + "| value_loss | 0.00668 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 522 |\n", + "| ep_rew_mean | 6.61 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 18000 |\n", + "| time_elapsed | 726 |\n", + "| total_timesteps | 90000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.37 |\n", + "| explained_variance | -289 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 17999 |\n", + "| policy_loss | 0.066 |\n", + "| value_loss | 0.0934 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 528 |\n", + "| ep_rew_mean | 6.76 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 18100 |\n", + "| time_elapsed | 730 |\n", + "| total_timesteps | 90500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.281 |\n", + "| explained_variance | -262 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 18099 |\n", + "| policy_loss | 0.0676 |\n", + "| value_loss | 0.0274 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 525 |\n", + "| ep_rew_mean | 6.7 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 18200 |\n", + "| time_elapsed | 734 |\n", + "| total_timesteps | 91000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.284 |\n", + "| explained_variance | 0.994 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 18199 |\n", + "| policy_loss | 0.000836 |\n", + "| value_loss | 0.00164 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 520 |\n", + "| ep_rew_mean | 6.61 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 18300 |\n", + "| time_elapsed | 738 |\n", + "| total_timesteps | 91500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.322 |\n", + "| explained_variance | -162 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 18299 |\n", + "| policy_loss | -0.00292 |\n", + "| value_loss | 0.0045 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 524 |\n", + "| ep_rew_mean | 6.66 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 18400 |\n", + "| time_elapsed | 742 |\n", + "| total_timesteps | 92000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.227 |\n", + "| explained_variance | -51.5 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 18399 |\n", + "| policy_loss | 0.0374 |\n", + "| value_loss | 0.218 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 526 |\n", + "| ep_rew_mean | 6.73 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 18500 |\n", + "| time_elapsed | 746 |\n", + "| total_timesteps | 92500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.111 |\n", + "| explained_variance | -445 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 18499 |\n", + "| policy_loss | -0.155 |\n", + "| value_loss | 0.104 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 529 |\n", + "| ep_rew_mean | 6.78 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 18600 |\n", + "| time_elapsed | 750 |\n", + "| total_timesteps | 93000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.515 |\n", + "| explained_variance | -94.7 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 18599 |\n", + "| policy_loss | -0.0394 |\n", + "| value_loss | 0.0131 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 525 |\n", + "| ep_rew_mean | 6.68 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 18700 |\n", + "| time_elapsed | 754 |\n", + "| total_timesteps | 93500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.671 |\n", + "| explained_variance | 0.937 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 18699 |\n", + "| policy_loss | 0.00634 |\n", + "| value_loss | 0.0101 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 527 |\n", + "| ep_rew_mean | 6.69 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 18800 |\n", + "| time_elapsed | 758 |\n", + "| total_timesteps | 94000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.389 |\n", + "| explained_variance | -1.14e+03 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 18799 |\n", + "| policy_loss | -0.0853 |\n", + "| value_loss | 0.0175 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.79 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 18900 |\n", + "| time_elapsed | 762 |\n", + "| total_timesteps | 94500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.132 |\n", + "| explained_variance | -149 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 18899 |\n", + "| policy_loss | 0.00268 |\n", + "| value_loss | 0.00778 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.82 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 19000 |\n", + "| time_elapsed | 766 |\n", + "| total_timesteps | 95000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.763 |\n", + "| explained_variance | 0.96 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 18999 |\n", + "| policy_loss | 0.13 |\n", + "| value_loss | 0.0558 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 528 |\n", + "| ep_rew_mean | 6.75 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 19100 |\n", + "| time_elapsed | 770 |\n", + "| total_timesteps | 95500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.166 |\n", + "| explained_variance | -4.08 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 19099 |\n", + "| policy_loss | 0.00422 |\n", + "| value_loss | 0.00858 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 525 |\n", + "| ep_rew_mean | 6.73 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 19200 |\n", + "| time_elapsed | 775 |\n", + "| total_timesteps | 96000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.393 |\n", + "| explained_variance | -14.1 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 19199 |\n", + "| policy_loss | -0.00969 |\n", + "| value_loss | 0.0284 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 524 |\n", + "| ep_rew_mean | 6.69 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 19300 |\n", + "| time_elapsed | 780 |\n", + "| total_timesteps | 96500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.653 |\n", + "| explained_variance | -44.7 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 19299 |\n", + "| policy_loss | -0.0116 |\n", + "| value_loss | 0.0399 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 526 |\n", + "| ep_rew_mean | 6.71 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 19400 |\n", + "| time_elapsed | 783 |\n", + "| total_timesteps | 97000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.13 |\n", + "| explained_variance | -116 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 19399 |\n", + "| policy_loss | 0.00318 |\n", + "| value_loss | 0.00726 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 518 |\n", + "| ep_rew_mean | 6.57 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 19500 |\n", + "| time_elapsed | 787 |\n", + "| total_timesteps | 97500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.377 |\n", + "| explained_variance | 0.754 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 19499 |\n", + "| policy_loss | 0.0181 |\n", + "| value_loss | 0.0554 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 511 |\n", + "| ep_rew_mean | 6.46 |\n", + "| time/ | |\n", + "| fps | 123 |\n", + "| iterations | 19600 |\n", + "| time_elapsed | 790 |\n", + "| total_timesteps | 98000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.333 |\n", + "| explained_variance | 0.448 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 19599 |\n", + "| policy_loss | 0.203 |\n", + "| value_loss | 0.526 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 510 |\n", + "| ep_rew_mean | 6.44 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 19700 |\n", + "| time_elapsed | 794 |\n", + "| total_timesteps | 98500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.661 |\n", + "| explained_variance | -73.2 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 19699 |\n", + "| policy_loss | -0.0536 |\n", + "| value_loss | 0.0363 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 505 |\n", + "| ep_rew_mean | 6.38 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 19800 |\n", + "| time_elapsed | 797 |\n", + "| total_timesteps | 99000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.34 |\n", + "| explained_variance | -384 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 19799 |\n", + "| policy_loss | 0.0167 |\n", + "| value_loss | 0.0104 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 505 |\n", + "| ep_rew_mean | 6.4 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 19900 |\n", + "| time_elapsed | 800 |\n", + "| total_timesteps | 99500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.625 |\n", + "| explained_variance | 0.798 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 19899 |\n", + "| policy_loss | -0.0141 |\n", + "| value_loss | 0.0601 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 503 |\n", + "| ep_rew_mean | 6.25 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 20000 |\n", + "| time_elapsed | 804 |\n", + "| total_timesteps | 100000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.146 |\n", + "| explained_variance | 0.782 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 19999 |\n", + "| policy_loss | -0.233 |\n", + "| value_loss | 0.114 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 500 |\n", + "| ep_rew_mean | 6.21 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 20100 |\n", + "| time_elapsed | 807 |\n", + "| total_timesteps | 100500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.227 |\n", + "| explained_variance | -135 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 20099 |\n", + "| policy_loss | 0.0517 |\n", + "| value_loss | 0.306 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 497 |\n", + "| ep_rew_mean | 6.07 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 20200 |\n", + "| time_elapsed | 812 |\n", + "| total_timesteps | 101000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.102 |\n", + "| explained_variance | 0.115 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 20199 |\n", + "| policy_loss | 0.00323 |\n", + "| value_loss | 0.181 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 502 |\n", + "| ep_rew_mean | 6.19 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 20300 |\n", + "| time_elapsed | 816 |\n", + "| total_timesteps | 101500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.209 |\n", + "| explained_variance | 0.934 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 20299 |\n", + "| policy_loss | 0.00132 |\n", + "| value_loss | 0.0315 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 501 |\n", + "| ep_rew_mean | 6.17 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 20400 |\n", + "| time_elapsed | 820 |\n", + "| total_timesteps | 102000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00543 |\n", + "| explained_variance | -0.0244 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 20399 |\n", + "| policy_loss | -1.34e-05 |\n", + "| value_loss | 0.191 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 492 |\n", + "| ep_rew_mean | 5.98 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 20500 |\n", + "| time_elapsed | 824 |\n", + "| total_timesteps | 102500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.191 |\n", + "| explained_variance | nan |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 20499 |\n", + "| policy_loss | 0.0997 |\n", + "| value_loss | 0.0106 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 492 |\n", + "| ep_rew_mean | 6.01 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 20600 |\n", + "| time_elapsed | 828 |\n", + "| total_timesteps | 103000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.239 |\n", + "| explained_variance | -7.64e+13 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 20599 |\n", + "| policy_loss | -0.0643 |\n", + "| value_loss | 0.101 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 486 |\n", + "| ep_rew_mean | 5.88 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 20700 |\n", + "| time_elapsed | 832 |\n", + "| total_timesteps | 103500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0218 |\n", + "| explained_variance | 0.959 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 20699 |\n", + "| policy_loss | -0.000763 |\n", + "| value_loss | 0.0228 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 492 |\n", + "| ep_rew_mean | 5.96 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 20800 |\n", + "| time_elapsed | 836 |\n", + "| total_timesteps | 104000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.15 |\n", + "| explained_variance | -192 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 20799 |\n", + "| policy_loss | -0.0231 |\n", + "| value_loss | 0.186 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 491 |\n", + "| ep_rew_mean | 5.95 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 20900 |\n", + "| time_elapsed | 839 |\n", + "| total_timesteps | 104500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0405 |\n", + "| explained_variance | -9.69 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 20899 |\n", + "| policy_loss | -9.11e-05 |\n", + "| value_loss | 0.0124 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 495 |\n", + "| ep_rew_mean | 6.04 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 21000 |\n", + "| time_elapsed | 843 |\n", + "| total_timesteps | 105000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.186 |\n", + "| explained_variance | -7.09 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 20999 |\n", + "| policy_loss | 0.00576 |\n", + "| value_loss | 0.0204 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 492 |\n", + "| ep_rew_mean | 6 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 21100 |\n", + "| time_elapsed | 846 |\n", + "| total_timesteps | 105500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.162 |\n", + "| explained_variance | -643 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 21099 |\n", + "| policy_loss | -0.00428 |\n", + "| value_loss | 0.242 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 497 |\n", + "| ep_rew_mean | 6.04 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 21200 |\n", + "| time_elapsed | 849 |\n", + "| total_timesteps | 106000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.271 |\n", + "| explained_variance | -80.6 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 21199 |\n", + "| policy_loss | -0.0421 |\n", + "| value_loss | 0.0543 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 495 |\n", + "| ep_rew_mean | 5.99 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 21300 |\n", + "| time_elapsed | 853 |\n", + "| total_timesteps | 106500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.367 |\n", + "| explained_variance | 0.964 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 21299 |\n", + "| policy_loss | -0.13 |\n", + "| value_loss | 0.0247 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 498 |\n", + "| ep_rew_mean | 6.05 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 21400 |\n", + "| time_elapsed | 857 |\n", + "| total_timesteps | 107000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0177 |\n", + "| explained_variance | 0.966 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 21399 |\n", + "| policy_loss | -0.000582 |\n", + "| value_loss | 0.0697 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 507 |\n", + "| ep_rew_mean | 6.28 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 21500 |\n", + "| time_elapsed | 860 |\n", + "| total_timesteps | 107500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.122 |\n", + "| explained_variance | -14.5 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 21499 |\n", + "| policy_loss | -0.021 |\n", + "| value_loss | 0.185 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 510 |\n", + "| ep_rew_mean | 6.35 |\n", + "| time/ | |\n", + "| fps | 124 |\n", + "| iterations | 21600 |\n", + "| time_elapsed | 864 |\n", + "| total_timesteps | 108000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.157 |\n", + "| explained_variance | 0.766 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 21599 |\n", + "| policy_loss | -0.0883 |\n", + "| value_loss | 0.263 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 514 |\n", + "| ep_rew_mean | 6.39 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 21700 |\n", + "| time_elapsed | 867 |\n", + "| total_timesteps | 108500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.221 |\n", + "| explained_variance | -352 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 21699 |\n", + "| policy_loss | -0.0189 |\n", + "| value_loss | 0.0973 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 519 |\n", + "| ep_rew_mean | 6.5 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 21800 |\n", + "| time_elapsed | 870 |\n", + "| total_timesteps | 109000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.172 |\n", + "| explained_variance | 0.585 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 21799 |\n", + "| policy_loss | -0.0138 |\n", + "| value_loss | 0.026 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 522 |\n", + "| ep_rew_mean | 6.61 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 21900 |\n", + "| time_elapsed | 874 |\n", + "| total_timesteps | 109500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.302 |\n", + "| explained_variance | -2.66 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 21899 |\n", + "| policy_loss | 1.16 |\n", + "| value_loss | 1.27 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 524 |\n", + "| ep_rew_mean | 6.66 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 22000 |\n", + "| time_elapsed | 878 |\n", + "| total_timesteps | 110000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0548 |\n", + "| explained_variance | 0.319 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 21999 |\n", + "| policy_loss | 0.00147 |\n", + "| value_loss | 0.132 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 530 |\n", + "| ep_rew_mean | 6.71 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 22100 |\n", + "| time_elapsed | 881 |\n", + "| total_timesteps | 110500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0122 |\n", + "| explained_variance | -0.341 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 22099 |\n", + "| policy_loss | -0.00032 |\n", + "| value_loss | 0.367 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.69 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 22200 |\n", + "| time_elapsed | 885 |\n", + "| total_timesteps | 111000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0283 |\n", + "| explained_variance | 0.987 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 22199 |\n", + "| policy_loss | -0.00131 |\n", + "| value_loss | 0.0537 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 524 |\n", + "| ep_rew_mean | 6.56 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 22300 |\n", + "| time_elapsed | 889 |\n", + "| total_timesteps | 111500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.128 |\n", + "| explained_variance | -31.6 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 22299 |\n", + "| policy_loss | -0.00559 |\n", + "| value_loss | 0.0461 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 529 |\n", + "| ep_rew_mean | 6.66 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 22400 |\n", + "| time_elapsed | 893 |\n", + "| total_timesteps | 112000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0397 |\n", + "| explained_variance | 0.902 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 22399 |\n", + "| policy_loss | -0.00246 |\n", + "| value_loss | 0.033 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.8 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 22500 |\n", + "| time_elapsed | 897 |\n", + "| total_timesteps | 112500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.263 |\n", + "| explained_variance | -1.81e+13 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 22499 |\n", + "| policy_loss | -0.0491 |\n", + "| value_loss | 0.151 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.73 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 22600 |\n", + "| time_elapsed | 901 |\n", + "| total_timesteps | 113000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.139 |\n", + "| explained_variance | -4.1 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 22599 |\n", + "| policy_loss | -0.00369 |\n", + "| value_loss | 0.00562 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.79 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 22700 |\n", + "| time_elapsed | 905 |\n", + "| total_timesteps | 113500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.101 |\n", + "| explained_variance | -74.7 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 22699 |\n", + "| policy_loss | 0.00398 |\n", + "| value_loss | 0.0174 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 542 |\n", + "| ep_rew_mean | 6.93 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 22800 |\n", + "| time_elapsed | 909 |\n", + "| total_timesteps | 114000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.238 |\n", + "| explained_variance | -6.14e+14 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 22799 |\n", + "| policy_loss | -0.127 |\n", + "| value_loss | 0.032 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 541 |\n", + "| ep_rew_mean | 6.9 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 22900 |\n", + "| time_elapsed | 913 |\n", + "| total_timesteps | 114500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.173 |\n", + "| explained_variance | -50.7 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 22899 |\n", + "| policy_loss | -0.00432 |\n", + "| value_loss | 0.0236 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 542 |\n", + "| ep_rew_mean | 6.92 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 23000 |\n", + "| time_elapsed | 917 |\n", + "| total_timesteps | 115000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000932 |\n", + "| explained_variance | -64.1 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 22999 |\n", + "| policy_loss | 1.68e-05 |\n", + "| value_loss | 0.0342 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 547 |\n", + "| ep_rew_mean | 7.02 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 23100 |\n", + "| time_elapsed | 922 |\n", + "| total_timesteps | 115500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0568 |\n", + "| explained_variance | 0.823 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 23099 |\n", + "| policy_loss | -0.00147 |\n", + "| value_loss | 0.0628 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 550 |\n", + "| ep_rew_mean | 7.11 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 23200 |\n", + "| time_elapsed | 926 |\n", + "| total_timesteps | 116000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0183 |\n", + "| explained_variance | -4.57 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 23199 |\n", + "| policy_loss | -0.00108 |\n", + "| value_loss | 0.0454 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 553 |\n", + "| ep_rew_mean | 7.15 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 23300 |\n", + "| time_elapsed | 931 |\n", + "| total_timesteps | 116500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.252 |\n", + "| explained_variance | -394 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 23299 |\n", + "| policy_loss | -0.00375 |\n", + "| value_loss | 0.0207 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 556 |\n", + "| ep_rew_mean | 7.15 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 23400 |\n", + "| time_elapsed | 934 |\n", + "| total_timesteps | 117000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.613 |\n", + "| explained_variance | 0.277 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 23399 |\n", + "| policy_loss | 0.224 |\n", + "| value_loss | 0.838 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.2 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 23500 |\n", + "| time_elapsed | 938 |\n", + "| total_timesteps | 117500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.327 |\n", + "| explained_variance | 0.932 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 23499 |\n", + "| policy_loss | -0.0375 |\n", + "| value_loss | 0.035 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 564 |\n", + "| ep_rew_mean | 7.27 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 23600 |\n", + "| time_elapsed | 942 |\n", + "| total_timesteps | 118000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.191 |\n", + "| explained_variance | 0.986 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 23599 |\n", + "| policy_loss | -0.0247 |\n", + "| value_loss | 0.0656 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 566 |\n", + "| ep_rew_mean | 7.31 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 23700 |\n", + "| time_elapsed | 945 |\n", + "| total_timesteps | 118500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.294 |\n", + "| explained_variance | -4.17 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 23699 |\n", + "| policy_loss | 0.186 |\n", + "| value_loss | 0.14 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 570 |\n", + "| ep_rew_mean | 7.4 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 23800 |\n", + "| time_elapsed | 950 |\n", + "| total_timesteps | 119000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.397 |\n", + "| explained_variance | -5.29 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 23799 |\n", + "| policy_loss | 0.0873 |\n", + "| value_loss | 0.0117 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 569 |\n", + "| ep_rew_mean | 7.38 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 23900 |\n", + "| time_elapsed | 953 |\n", + "| total_timesteps | 119500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.346 |\n", + "| explained_variance | 0.85 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 23899 |\n", + "| policy_loss | 0.0037 |\n", + "| value_loss | 0.0648 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 566 |\n", + "| ep_rew_mean | 7.27 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 24000 |\n", + "| time_elapsed | 957 |\n", + "| total_timesteps | 120000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.276 |\n", + "| explained_variance | 0.932 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 23999 |\n", + "| policy_loss | 0.1 |\n", + "| value_loss | 0.048 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 566 |\n", + "| ep_rew_mean | 7.28 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 24100 |\n", + "| time_elapsed | 961 |\n", + "| total_timesteps | 120500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.312 |\n", + "| explained_variance | 0.863 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 24099 |\n", + "| policy_loss | -0.0149 |\n", + "| value_loss | 0.0239 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.18 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 24200 |\n", + "| time_elapsed | 965 |\n", + "| total_timesteps | 121000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.199 |\n", + "| explained_variance | 0.0769 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 24199 |\n", + "| policy_loss | 0.00543 |\n", + "| value_loss | 0.0236 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 553 |\n", + "| ep_rew_mean | 7.02 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 24300 |\n", + "| time_elapsed | 969 |\n", + "| total_timesteps | 121500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.346 |\n", + "| explained_variance | 0.961 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 24299 |\n", + "| policy_loss | -0.118 |\n", + "| value_loss | 0.0123 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 551 |\n", + "| ep_rew_mean | 6.99 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 24400 |\n", + "| time_elapsed | 973 |\n", + "| total_timesteps | 122000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.218 |\n", + "| explained_variance | -484 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 24399 |\n", + "| policy_loss | -0.00848 |\n", + "| value_loss | 0.0176 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 553 |\n", + "| ep_rew_mean | 7.06 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 24500 |\n", + "| time_elapsed | 977 |\n", + "| total_timesteps | 122500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.156 |\n", + "| explained_variance | -404 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 24499 |\n", + "| policy_loss | 0.0461 |\n", + "| value_loss | 0.577 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 556 |\n", + "| ep_rew_mean | 7.15 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 24600 |\n", + "| time_elapsed | 981 |\n", + "| total_timesteps | 123000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.166 |\n", + "| explained_variance | 0.934 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 24599 |\n", + "| policy_loss | -0.00832 |\n", + "| value_loss | 0.0127 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.23 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 24700 |\n", + "| time_elapsed | 985 |\n", + "| total_timesteps | 123500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.166 |\n", + "| explained_variance | 0.964 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 24699 |\n", + "| policy_loss | -0.064 |\n", + "| value_loss | 0.0126 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 568 |\n", + "| ep_rew_mean | 7.39 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 24800 |\n", + "| time_elapsed | 989 |\n", + "| total_timesteps | 124000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00301 |\n", + "| explained_variance | -1.8 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 24799 |\n", + "| policy_loss | 5.57e-06 |\n", + "| value_loss | 0.00199 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 567 |\n", + "| ep_rew_mean | 7.36 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 24900 |\n", + "| time_elapsed | 993 |\n", + "| total_timesteps | 124500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0619 |\n", + "| explained_variance | -19.8 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 24899 |\n", + "| policy_loss | -0.000763 |\n", + "| value_loss | 0.0267 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 571 |\n", + "| ep_rew_mean | 7.43 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 25000 |\n", + "| time_elapsed | 997 |\n", + "| total_timesteps | 125000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.114 |\n", + "| explained_variance | 0.103 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 24999 |\n", + "| policy_loss | 0.131 |\n", + "| value_loss | 1.12 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 572 |\n", + "| ep_rew_mean | 7.46 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 25100 |\n", + "| time_elapsed | 1001 |\n", + "| total_timesteps | 125500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.278 |\n", + "| explained_variance | -143 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 25099 |\n", + "| policy_loss | 0.0389 |\n", + "| value_loss | 0.236 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 579 |\n", + "| ep_rew_mean | 7.62 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 25200 |\n", + "| time_elapsed | 1005 |\n", + "| total_timesteps | 126000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.128 |\n", + "| explained_variance | 0.967 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 25199 |\n", + "| policy_loss | 0.0337 |\n", + "| value_loss | 0.00835 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 575 |\n", + "| ep_rew_mean | 7.56 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 25300 |\n", + "| time_elapsed | 1009 |\n", + "| total_timesteps | 126500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.14 |\n", + "| explained_variance | -72.3 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 25299 |\n", + "| policy_loss | 0.0162 |\n", + "| value_loss | 0.294 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 575 |\n", + "| ep_rew_mean | 7.55 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 25400 |\n", + "| time_elapsed | 1013 |\n", + "| total_timesteps | 127000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.567 |\n", + "| explained_variance | -96.9 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 25399 |\n", + "| policy_loss | 0.0498 |\n", + "| value_loss | 0.0712 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 575 |\n", + "| ep_rew_mean | 7.56 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 25500 |\n", + "| time_elapsed | 1018 |\n", + "| total_timesteps | 127500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.22 |\n", + "| explained_variance | -6.44e+04 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 25499 |\n", + "| policy_loss | 0.00348 |\n", + "| value_loss | 0.0167 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 572 |\n", + "| ep_rew_mean | 7.51 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 25600 |\n", + "| time_elapsed | 1022 |\n", + "| total_timesteps | 128000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.235 |\n", + "| explained_variance | 0.986 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 25599 |\n", + "| policy_loss | 0.00249 |\n", + "| value_loss | 0.003 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 564 |\n", + "| ep_rew_mean | 7.36 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 25700 |\n", + "| time_elapsed | 1027 |\n", + "| total_timesteps | 128500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0118 |\n", + "| explained_variance | 0.475 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 25699 |\n", + "| policy_loss | -1.19e-05 |\n", + "| value_loss | 0.00494 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 564 |\n", + "| ep_rew_mean | 7.38 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 25800 |\n", + "| time_elapsed | 1031 |\n", + "| total_timesteps | 129000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0913 |\n", + "| explained_variance | 0.219 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 25799 |\n", + "| policy_loss | 0.00604 |\n", + "| value_loss | 0.239 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 566 |\n", + "| ep_rew_mean | 7.43 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 25900 |\n", + "| time_elapsed | 1035 |\n", + "| total_timesteps | 129500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0252 |\n", + "| explained_variance | -83.4 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 25899 |\n", + "| policy_loss | 0.00214 |\n", + "| value_loss | 0.0465 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 563 |\n", + "| ep_rew_mean | 7.42 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 26000 |\n", + "| time_elapsed | 1039 |\n", + "| total_timesteps | 130000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0741 |\n", + "| explained_variance | 0.939 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 25999 |\n", + "| policy_loss | -0.00391 |\n", + "| value_loss | 0.0906 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 563 |\n", + "| ep_rew_mean | 7.4 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 26100 |\n", + "| time_elapsed | 1043 |\n", + "| total_timesteps | 130500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0753 |\n", + "| explained_variance | -28.3 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 26099 |\n", + "| policy_loss | 0.00398 |\n", + "| value_loss | 0.0161 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 553 |\n", + "| ep_rew_mean | 7.22 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 26200 |\n", + "| time_elapsed | 1047 |\n", + "| total_timesteps | 131000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.146 |\n", + "| explained_variance | 0.984 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 26199 |\n", + "| policy_loss | 3.88e-05 |\n", + "| value_loss | 0.00392 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 556 |\n", + "| ep_rew_mean | 7.29 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 26300 |\n", + "| time_elapsed | 1051 |\n", + "| total_timesteps | 131500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0087 |\n", + "| explained_variance | -0.89 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 26299 |\n", + "| policy_loss | -0.000762 |\n", + "| value_loss | 0.751 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 555 |\n", + "| ep_rew_mean | 7.29 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 26400 |\n", + "| time_elapsed | 1055 |\n", + "| total_timesteps | 132000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.147 |\n", + "| explained_variance | 0.653 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 26399 |\n", + "| policy_loss | 0.00651 |\n", + "| value_loss | 0.0581 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 552 |\n", + "| ep_rew_mean | 7.19 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 26500 |\n", + "| time_elapsed | 1059 |\n", + "| total_timesteps | 132500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00839 |\n", + "| explained_variance | -20.6 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 26499 |\n", + "| policy_loss | 0.000141 |\n", + "| value_loss | 0.0456 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 556 |\n", + "| ep_rew_mean | 7.22 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 26600 |\n", + "| time_elapsed | 1063 |\n", + "| total_timesteps | 133000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.412 |\n", + "| explained_variance | 0.988 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 26599 |\n", + "| policy_loss | -0.0418 |\n", + "| value_loss | 0.0343 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 561 |\n", + "| ep_rew_mean | 7.32 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 26700 |\n", + "| time_elapsed | 1067 |\n", + "| total_timesteps | 133500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.412 |\n", + "| explained_variance | -1.19e+03 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 26699 |\n", + "| policy_loss | -0.00513 |\n", + "| value_loss | 0.00419 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.24 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 26800 |\n", + "| time_elapsed | 1071 |\n", + "| total_timesteps | 134000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000303 |\n", + "| explained_variance | -30.4 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 26799 |\n", + "| policy_loss | -1.01e-06 |\n", + "| value_loss | 0.0114 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.22 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 26900 |\n", + "| time_elapsed | 1075 |\n", + "| total_timesteps | 134500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.159 |\n", + "| explained_variance | 0.963 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 26899 |\n", + "| policy_loss | 0.00241 |\n", + "| value_loss | 0.00628 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 555 |\n", + "| ep_rew_mean | 7.15 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 27000 |\n", + "| time_elapsed | 1079 |\n", + "| total_timesteps | 135000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00298 |\n", + "| explained_variance | -127 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 26999 |\n", + "| policy_loss | -5.38e-05 |\n", + "| value_loss | 0.0601 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 554 |\n", + "| ep_rew_mean | 7.12 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 27100 |\n", + "| time_elapsed | 1083 |\n", + "| total_timesteps | 135500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0305 |\n", + "| explained_variance | 0.674 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 27099 |\n", + "| policy_loss | -0.000973 |\n", + "| value_loss | 0.0489 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 551 |\n", + "| ep_rew_mean | 7.05 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 27200 |\n", + "| time_elapsed | 1087 |\n", + "| total_timesteps | 136000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.264 |\n", + "| explained_variance | -131 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 27199 |\n", + "| policy_loss | 0.014 |\n", + "| value_loss | 0.0497 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 545 |\n", + "| ep_rew_mean | 7.02 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 27300 |\n", + "| time_elapsed | 1091 |\n", + "| total_timesteps | 136500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.286 |\n", + "| explained_variance | -10.8 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 27299 |\n", + "| policy_loss | 0.112 |\n", + "| value_loss | 0.0141 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.77 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 27400 |\n", + "| time_elapsed | 1095 |\n", + "| total_timesteps | 137000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.167 |\n", + "| explained_variance | 0.964 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 27399 |\n", + "| policy_loss | -0.0152 |\n", + "| value_loss | 0.0172 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 529 |\n", + "| ep_rew_mean | 6.67 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 27500 |\n", + "| time_elapsed | 1099 |\n", + "| total_timesteps | 137500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0511 |\n", + "| explained_variance | -3.49 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 27499 |\n", + "| policy_loss | 0.00214 |\n", + "| value_loss | 0.0129 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 527 |\n", + "| ep_rew_mean | 6.61 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 27600 |\n", + "| time_elapsed | 1103 |\n", + "| total_timesteps | 138000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.291 |\n", + "| explained_variance | 0.993 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 27599 |\n", + "| policy_loss | -0.0156 |\n", + "| value_loss | 0.00485 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 520 |\n", + "| ep_rew_mean | 6.47 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 27700 |\n", + "| time_elapsed | 1106 |\n", + "| total_timesteps | 138500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0133 |\n", + "| explained_variance | -4 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 27699 |\n", + "| policy_loss | 0.000171 |\n", + "| value_loss | 0.0257 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 526 |\n", + "| ep_rew_mean | 6.59 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 27800 |\n", + "| time_elapsed | 1110 |\n", + "| total_timesteps | 139000 |\n", + "| train/ | |\n", + "| entropy_loss | -3.24e-05 |\n", + "| explained_variance | -3.92 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 27799 |\n", + "| policy_loss | 6e-08 |\n", + "| value_loss | 0.00319 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 529 |\n", + "| ep_rew_mean | 6.66 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 27900 |\n", + "| time_elapsed | 1114 |\n", + "| total_timesteps | 139500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.481 |\n", + "| explained_variance | -5.52e+14 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 27899 |\n", + "| policy_loss | -0.0441 |\n", + "| value_loss | 0.0466 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.76 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 28000 |\n", + "| time_elapsed | 1118 |\n", + "| total_timesteps | 140000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00197 |\n", + "| explained_variance | -25.7 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 27999 |\n", + "| policy_loss | 4.63e-05 |\n", + "| value_loss | 0.0415 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.82 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 28100 |\n", + "| time_elapsed | 1122 |\n", + "| total_timesteps | 140500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.443 |\n", + "| explained_variance | -48.4 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 28099 |\n", + "| policy_loss | 0.0547 |\n", + "| value_loss | 0.00797 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 6.8 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 28200 |\n", + "| time_elapsed | 1126 |\n", + "| total_timesteps | 141000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00124 |\n", + "| explained_variance | -6.87 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 28199 |\n", + "| policy_loss | 1.44e-06 |\n", + "| value_loss | 0.00232 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.76 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 28300 |\n", + "| time_elapsed | 1130 |\n", + "| total_timesteps | 141500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.258 |\n", + "| explained_variance | 0.991 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 28299 |\n", + "| policy_loss | 0.0142 |\n", + "| value_loss | 0.00926 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 530 |\n", + "| ep_rew_mean | 6.71 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 28400 |\n", + "| time_elapsed | 1134 |\n", + "| total_timesteps | 142000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00788 |\n", + "| explained_variance | -67.1 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 28399 |\n", + "| policy_loss | 0.000194 |\n", + "| value_loss | 0.0674 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.74 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 28500 |\n", + "| time_elapsed | 1137 |\n", + "| total_timesteps | 142500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.168 |\n", + "| explained_variance | 0.975 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 28499 |\n", + "| policy_loss | -0.00571 |\n", + "| value_loss | 0.0212 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 6.8 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 28600 |\n", + "| time_elapsed | 1141 |\n", + "| total_timesteps | 143000 |\n", + "| train/ | |\n", + "| entropy_loss | -4.22e-05 |\n", + "| explained_variance | -3.55 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 28599 |\n", + "| policy_loss | 1.88e-08 |\n", + "| value_loss | 0.00114 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.71 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 28700 |\n", + "| time_elapsed | 1145 |\n", + "| total_timesteps | 143500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0117 |\n", + "| explained_variance | 0.863 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 28699 |\n", + "| policy_loss | -2.06e-05 |\n", + "| value_loss | 0.0312 |\n", + "-------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 6.88 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 28800 |\n", + "| time_elapsed | 1149 |\n", + "| total_timesteps | 144000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.19 |\n", + "| explained_variance | 0.348 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 28799 |\n", + "| policy_loss | 0.0147 |\n", + "| value_loss | 0.405 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 544 |\n", + "| ep_rew_mean | 7.02 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 28900 |\n", + "| time_elapsed | 1153 |\n", + "| total_timesteps | 144500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.016 |\n", + "| explained_variance | -4.68 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 28899 |\n", + "| policy_loss | 0.000828 |\n", + "| value_loss | 0.132 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 535 |\n", + "| ep_rew_mean | 6.85 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 29000 |\n", + "| time_elapsed | 1157 |\n", + "| total_timesteps | 145000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00902 |\n", + "| explained_variance | -24 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 28999 |\n", + "| policy_loss | -0.000158 |\n", + "| value_loss | 0.0484 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 540 |\n", + "| ep_rew_mean | 6.99 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 29100 |\n", + "| time_elapsed | 1160 |\n", + "| total_timesteps | 145500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.309 |\n", + "| explained_variance | -1.24 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 29099 |\n", + "| policy_loss | -0.0731 |\n", + "| value_loss | 0.152 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 542 |\n", + "| ep_rew_mean | 7.02 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 29200 |\n", + "| time_elapsed | 1164 |\n", + "| total_timesteps | 146000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.365 |\n", + "| explained_variance | -6.48e+14 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 29199 |\n", + "| policy_loss | -0.0549 |\n", + "| value_loss | 0.0707 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 540 |\n", + "| ep_rew_mean | 6.97 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 29300 |\n", + "| time_elapsed | 1168 |\n", + "| total_timesteps | 146500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.44 |\n", + "| explained_variance | -25.7 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 29299 |\n", + "| policy_loss | 0.0284 |\n", + "| value_loss | 0.0204 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.92 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 29400 |\n", + "| time_elapsed | 1172 |\n", + "| total_timesteps | 147000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.182 |\n", + "| explained_variance | -9.27e+13 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 29399 |\n", + "| policy_loss | -0.0851 |\n", + "| value_loss | 0.666 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 540 |\n", + "| ep_rew_mean | 6.97 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 29500 |\n", + "| time_elapsed | 1176 |\n", + "| total_timesteps | 147500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.414 |\n", + "| explained_variance | -0.0354 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 29499 |\n", + "| policy_loss | -0.00474 |\n", + "| value_loss | 0.0441 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 545 |\n", + "| ep_rew_mean | 7.1 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 29600 |\n", + "| time_elapsed | 1180 |\n", + "| total_timesteps | 148000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.41 |\n", + "| explained_variance | -2.74e+03 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 29599 |\n", + "| policy_loss | 0.113 |\n", + "| value_loss | 0.0304 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 549 |\n", + "| ep_rew_mean | 7.11 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 29700 |\n", + "| time_elapsed | 1184 |\n", + "| total_timesteps | 148500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.283 |\n", + "| explained_variance | -0.952 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 29699 |\n", + "| policy_loss | 0.0285 |\n", + "| value_loss | 1.25 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 557 |\n", + "| ep_rew_mean | 7.27 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 29800 |\n", + "| time_elapsed | 1188 |\n", + "| total_timesteps | 149000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0458 |\n", + "| explained_variance | -1.61e+13 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 29799 |\n", + "| policy_loss | -0.0025 |\n", + "| value_loss | 0.133 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.29 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 29900 |\n", + "| time_elapsed | 1192 |\n", + "| total_timesteps | 149500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.105 |\n", + "| explained_variance | 0.902 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 29899 |\n", + "| policy_loss | -0.00329 |\n", + "| value_loss | 0.0185 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 561 |\n", + "| ep_rew_mean | 7.36 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 30000 |\n", + "| time_elapsed | 1196 |\n", + "| total_timesteps | 150000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.326 |\n", + "| explained_variance | 0.481 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 29999 |\n", + "| policy_loss | -0.0405 |\n", + "| value_loss | 0.211 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 567 |\n", + "| ep_rew_mean | 7.48 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 30100 |\n", + "| time_elapsed | 1200 |\n", + "| total_timesteps | 150500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000832 |\n", + "| explained_variance | -228 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 30099 |\n", + "| policy_loss | -4.57e-06 |\n", + "| value_loss | 0.119 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 575 |\n", + "| ep_rew_mean | 7.62 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 30200 |\n", + "| time_elapsed | 1203 |\n", + "| total_timesteps | 151000 |\n", + "| train/ | |\n", + "| entropy_loss | -7.16e-05 |\n", + "| explained_variance | -12.5 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 30199 |\n", + "| policy_loss | -5.94e-07 |\n", + "| value_loss | 0.0312 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 576 |\n", + "| ep_rew_mean | 7.72 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 30300 |\n", + "| time_elapsed | 1207 |\n", + "| total_timesteps | 151500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0554 |\n", + "| explained_variance | -39.3 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 30299 |\n", + "| policy_loss | -0.00437 |\n", + "| value_loss | 0.303 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 563 |\n", + "| ep_rew_mean | 7.44 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 30400 |\n", + "| time_elapsed | 1211 |\n", + "| total_timesteps | 152000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.537 |\n", + "| explained_variance | -165 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 30399 |\n", + "| policy_loss | 0.0695 |\n", + "| value_loss | 0.148 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.35 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 30500 |\n", + "| time_elapsed | 1215 |\n", + "| total_timesteps | 152500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.556 |\n", + "| explained_variance | nan |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 30499 |\n", + "| policy_loss | -0.0577 |\n", + "| value_loss | 0.188 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.31 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 30600 |\n", + "| time_elapsed | 1219 |\n", + "| total_timesteps | 153000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.242 |\n", + "| explained_variance | -64.2 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 30599 |\n", + "| policy_loss | 0.133 |\n", + "| value_loss | 0.262 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 557 |\n", + "| ep_rew_mean | 7.28 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 30700 |\n", + "| time_elapsed | 1223 |\n", + "| total_timesteps | 153500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.151 |\n", + "| explained_variance | -6.73 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 30699 |\n", + "| policy_loss | -0.0197 |\n", + "| value_loss | 0.16 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.33 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 30800 |\n", + "| time_elapsed | 1227 |\n", + "| total_timesteps | 154000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.39 |\n", + "| explained_variance | 0.195 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 30799 |\n", + "| policy_loss | 0.0513 |\n", + "| value_loss | 0.157 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 563 |\n", + "| ep_rew_mean | 7.39 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 30900 |\n", + "| time_elapsed | 1231 |\n", + "| total_timesteps | 154500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0105 |\n", + "| explained_variance | -154 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 30899 |\n", + "| policy_loss | 0.000146 |\n", + "| value_loss | 0.0862 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 567 |\n", + "| ep_rew_mean | 7.49 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 31000 |\n", + "| time_elapsed | 1235 |\n", + "| total_timesteps | 155000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.343 |\n", + "| explained_variance | -42.3 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 30999 |\n", + "| policy_loss | -0.0929 |\n", + "| value_loss | 0.359 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 567 |\n", + "| ep_rew_mean | 7.58 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 31100 |\n", + "| time_elapsed | 1239 |\n", + "| total_timesteps | 155500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.059 |\n", + "| explained_variance | -1.07e+03 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 31099 |\n", + "| policy_loss | -0.00254 |\n", + "| value_loss | 0.109 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 570 |\n", + "| ep_rew_mean | 7.65 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 31200 |\n", + "| time_elapsed | 1243 |\n", + "| total_timesteps | 156000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.167 |\n", + "| explained_variance | -3.21 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 31199 |\n", + "| policy_loss | 0.011 |\n", + "| value_loss | 0.0569 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.39 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 31300 |\n", + "| time_elapsed | 1247 |\n", + "| total_timesteps | 156500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0174 |\n", + "| explained_variance | -34.8 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 31299 |\n", + "| policy_loss | 0.00101 |\n", + "| value_loss | 0.205 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 561 |\n", + "| ep_rew_mean | 7.49 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 31400 |\n", + "| time_elapsed | 1250 |\n", + "| total_timesteps | 157000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.188 |\n", + "| explained_variance | -2.64e+03 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 31399 |\n", + "| policy_loss | -0.181 |\n", + "| value_loss | 0.248 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 569 |\n", + "| ep_rew_mean | 7.66 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 31500 |\n", + "| time_elapsed | 1253 |\n", + "| total_timesteps | 157500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0882 |\n", + "| explained_variance | -2.35 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 31499 |\n", + "| policy_loss | 0.00621 |\n", + "| value_loss | 0.0675 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 570 |\n", + "| ep_rew_mean | 7.64 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 31600 |\n", + "| time_elapsed | 1257 |\n", + "| total_timesteps | 158000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.388 |\n", + "| explained_variance | 0.989 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 31599 |\n", + "| policy_loss | -0.0202 |\n", + "| value_loss | 0.0209 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 571 |\n", + "| ep_rew_mean | 7.67 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 31700 |\n", + "| time_elapsed | 1261 |\n", + "| total_timesteps | 158500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.307 |\n", + "| explained_variance | -24.6 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 31699 |\n", + "| policy_loss | 0.0282 |\n", + "| value_loss | 0.102 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 575 |\n", + "| ep_rew_mean | 7.73 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 31800 |\n", + "| time_elapsed | 1265 |\n", + "| total_timesteps | 159000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.363 |\n", + "| explained_variance | 0.959 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 31799 |\n", + "| policy_loss | -0.00155 |\n", + "| value_loss | 0.0117 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 580 |\n", + "| ep_rew_mean | 7.87 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 31900 |\n", + "| time_elapsed | 1269 |\n", + "| total_timesteps | 159500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.279 |\n", + "| explained_variance | 0.898 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 31899 |\n", + "| policy_loss | 0.00931 |\n", + "| value_loss | 0.0216 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 584 |\n", + "| ep_rew_mean | 7.97 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 32000 |\n", + "| time_elapsed | 1273 |\n", + "| total_timesteps | 160000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.608 |\n", + "| explained_variance | 0.991 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 31999 |\n", + "| policy_loss | -0.0423 |\n", + "| value_loss | 0.0215 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 7.95 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 32100 |\n", + "| time_elapsed | 1277 |\n", + "| total_timesteps | 160500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.357 |\n", + "| explained_variance | -415 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 32099 |\n", + "| policy_loss | -0.0489 |\n", + "| value_loss | 0.00677 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 576 |\n", + "| ep_rew_mean | 7.76 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 32200 |\n", + "| time_elapsed | 1281 |\n", + "| total_timesteps | 161000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.229 |\n", + "| explained_variance | 0.678 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 32199 |\n", + "| policy_loss | -0.00707 |\n", + "| value_loss | 0.0787 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 568 |\n", + "| ep_rew_mean | 7.6 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 32300 |\n", + "| time_elapsed | 1285 |\n", + "| total_timesteps | 161500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0985 |\n", + "| explained_variance | 0.984 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 32299 |\n", + "| policy_loss | 0.000681 |\n", + "| value_loss | 0.00966 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 561 |\n", + "| ep_rew_mean | 7.46 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 32400 |\n", + "| time_elapsed | 1289 |\n", + "| total_timesteps | 162000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.175 |\n", + "| explained_variance | -10.8 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 32399 |\n", + "| policy_loss | -0.00116 |\n", + "| value_loss | 0.0161 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 556 |\n", + "| ep_rew_mean | 7.34 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 32500 |\n", + "| time_elapsed | 1293 |\n", + "| total_timesteps | 162500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0178 |\n", + "| explained_variance | -57.2 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 32499 |\n", + "| policy_loss | 0.000257 |\n", + "| value_loss | 0.264 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 552 |\n", + "| ep_rew_mean | 7.28 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 32600 |\n", + "| time_elapsed | 1297 |\n", + "| total_timesteps | 163000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.259 |\n", + "| explained_variance | 0.982 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 32599 |\n", + "| policy_loss | 0.00372 |\n", + "| value_loss | 0.0734 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 552 |\n", + "| ep_rew_mean | 7.22 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 32700 |\n", + "| time_elapsed | 1301 |\n", + "| total_timesteps | 163500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0825 |\n", + "| explained_variance | -13.5 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 32699 |\n", + "| policy_loss | 0.00318 |\n", + "| value_loss | 0.0296 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.4 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 32800 |\n", + "| time_elapsed | 1305 |\n", + "| total_timesteps | 164000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.23 |\n", + "| explained_variance | 0.601 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 32799 |\n", + "| policy_loss | 0.0593 |\n", + "| value_loss | 0.0684 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.47 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 32900 |\n", + "| time_elapsed | 1309 |\n", + "| total_timesteps | 164500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00167 |\n", + "| explained_variance | -96 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 32899 |\n", + "| policy_loss | -2.43e-05 |\n", + "| value_loss | 0.0564 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 556 |\n", + "| ep_rew_mean | 7.4 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 33000 |\n", + "| time_elapsed | 1313 |\n", + "| total_timesteps | 165000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.128 |\n", + "| explained_variance | -713 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 32999 |\n", + "| policy_loss | -0.0126 |\n", + "| value_loss | 0.184 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.42 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 33100 |\n", + "| time_elapsed | 1317 |\n", + "| total_timesteps | 165500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.151 |\n", + "| explained_variance | 0.901 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 33099 |\n", + "| policy_loss | -0.00212 |\n", + "| value_loss | 0.0107 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 556 |\n", + "| ep_rew_mean | 7.4 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 33200 |\n", + "| time_elapsed | 1321 |\n", + "| total_timesteps | 166000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.3 |\n", + "| explained_variance | -79.1 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 33199 |\n", + "| policy_loss | 0.0122 |\n", + "| value_loss | 0.0273 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 557 |\n", + "| ep_rew_mean | 7.42 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 33300 |\n", + "| time_elapsed | 1325 |\n", + "| total_timesteps | 166500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.455 |\n", + "| explained_variance | 0.0173 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 33299 |\n", + "| policy_loss | 0.137 |\n", + "| value_loss | 0.192 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.46 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 33400 |\n", + "| time_elapsed | 1329 |\n", + "| total_timesteps | 167000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.103 |\n", + "| explained_variance | -3.89 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 33399 |\n", + "| policy_loss | 0.000237 |\n", + "| value_loss | 0.00261 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.42 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 33500 |\n", + "| time_elapsed | 1333 |\n", + "| total_timesteps | 167500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000205 |\n", + "| explained_variance | -15.1 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 33499 |\n", + "| policy_loss | -3.16e-06 |\n", + "| value_loss | 0.00853 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 557 |\n", + "| ep_rew_mean | 7.34 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 33600 |\n", + "| time_elapsed | 1337 |\n", + "| total_timesteps | 168000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.198 |\n", + "| explained_variance | 0.692 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 33599 |\n", + "| policy_loss | -0.0528 |\n", + "| value_loss | 0.0553 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 563 |\n", + "| ep_rew_mean | 7.43 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 33700 |\n", + "| time_elapsed | 1341 |\n", + "| total_timesteps | 168500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000205 |\n", + "| explained_variance | -8.26 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 33699 |\n", + "| policy_loss | -5.78e-07 |\n", + "| value_loss | 0.00243 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 569 |\n", + "| ep_rew_mean | 7.57 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 33800 |\n", + "| time_elapsed | 1345 |\n", + "| total_timesteps | 169000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0697 |\n", + "| explained_variance | -40.7 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 33799 |\n", + "| policy_loss | -0.000762 |\n", + "| value_loss | 0.00515 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 565 |\n", + "| ep_rew_mean | 7.47 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 33900 |\n", + "| time_elapsed | 1349 |\n", + "| total_timesteps | 169500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000955 |\n", + "| explained_variance | -2.85 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 33899 |\n", + "| policy_loss | -1.23e-05 |\n", + "| value_loss | 0.0166 |\n", + "-------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 554 |\n", + "| ep_rew_mean | 7.29 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 34000 |\n", + "| time_elapsed | 1353 |\n", + "| total_timesteps | 170000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.364 |\n", + "| explained_variance | -1.63e+14 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 33999 |\n", + "| policy_loss | -0.0692 |\n", + "| value_loss | 0.186 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 549 |\n", + "| ep_rew_mean | 7.23 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 34100 |\n", + "| time_elapsed | 1357 |\n", + "| total_timesteps | 170500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0679 |\n", + "| explained_variance | -11.9 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 34099 |\n", + "| policy_loss | 0.0252 |\n", + "| value_loss | 0.00831 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 544 |\n", + "| ep_rew_mean | 7.13 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 34200 |\n", + "| time_elapsed | 1361 |\n", + "| total_timesteps | 171000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.258 |\n", + "| explained_variance | -1.27e+03 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 34199 |\n", + "| policy_loss | -0.0106 |\n", + "| value_loss | 0.0292 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 547 |\n", + "| ep_rew_mean | 7.18 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 34300 |\n", + "| time_elapsed | 1365 |\n", + "| total_timesteps | 171500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.511 |\n", + "| explained_variance | -5.77e+14 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 34299 |\n", + "| policy_loss | -0.15 |\n", + "| value_loss | 0.0407 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 547 |\n", + "| ep_rew_mean | 7.2 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 34400 |\n", + "| time_elapsed | 1369 |\n", + "| total_timesteps | 172000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0125 |\n", + "| explained_variance | 0.987 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 34399 |\n", + "| policy_loss | 0.000198 |\n", + "| value_loss | 0.0049 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 548 |\n", + "| ep_rew_mean | 7.25 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 34500 |\n", + "| time_elapsed | 1373 |\n", + "| total_timesteps | 172500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.247 |\n", + "| explained_variance | 0.649 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 34499 |\n", + "| policy_loss | 0.0744 |\n", + "| value_loss | 0.0241 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 546 |\n", + "| ep_rew_mean | 7.19 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 34600 |\n", + "| time_elapsed | 1377 |\n", + "| total_timesteps | 173000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.124 |\n", + "| explained_variance | 0.991 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 34599 |\n", + "| policy_loss | 0.071 |\n", + "| value_loss | 0.00147 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 547 |\n", + "| ep_rew_mean | 7.25 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 34700 |\n", + "| time_elapsed | 1381 |\n", + "| total_timesteps | 173500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000434 |\n", + "| explained_variance | -4.24 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 34699 |\n", + "| policy_loss | -1.22e-05 |\n", + "| value_loss | 0.108 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 554 |\n", + "| ep_rew_mean | 7.39 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 34800 |\n", + "| time_elapsed | 1384 |\n", + "| total_timesteps | 174000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.201 |\n", + "| explained_variance | -2.42e+15 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 34799 |\n", + "| policy_loss | -0.0112 |\n", + "| value_loss | 0.0775 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.49 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 34900 |\n", + "| time_elapsed | 1388 |\n", + "| total_timesteps | 174500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00535 |\n", + "| explained_variance | -8.07 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 34899 |\n", + "| policy_loss | 4.56e-05 |\n", + "| value_loss | 0.0281 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 557 |\n", + "| ep_rew_mean | 7.45 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 35000 |\n", + "| time_elapsed | 1392 |\n", + "| total_timesteps | 175000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00318 |\n", + "| explained_variance | -34.4 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 34999 |\n", + "| policy_loss | -3.79e-05 |\n", + "| value_loss | 0.0607 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.48 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 35100 |\n", + "| time_elapsed | 1396 |\n", + "| total_timesteps | 175500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.465 |\n", + "| explained_variance | -276 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 35099 |\n", + "| policy_loss | -0.0381 |\n", + "| value_loss | 0.00932 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 554 |\n", + "| ep_rew_mean | 7.31 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 35200 |\n", + "| time_elapsed | 1400 |\n", + "| total_timesteps | 176000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000806 |\n", + "| explained_variance | -18.4 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 35199 |\n", + "| policy_loss | 9.12e-06 |\n", + "| value_loss | 0.0809 |\n", + "-------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 554 |\n", + "| ep_rew_mean | 7.29 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 35300 |\n", + "| time_elapsed | 1404 |\n", + "| total_timesteps | 176500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.13 |\n", + "| explained_variance | -162 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 35299 |\n", + "| policy_loss | -0.00291 |\n", + "| value_loss | 0.0232 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.39 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 35400 |\n", + "| time_elapsed | 1408 |\n", + "| total_timesteps | 177000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0865 |\n", + "| explained_variance | -60.4 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 35399 |\n", + "| policy_loss | 0.00818 |\n", + "| value_loss | 0.14 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 561 |\n", + "| ep_rew_mean | 7.48 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 35500 |\n", + "| time_elapsed | 1412 |\n", + "| total_timesteps | 177500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.335 |\n", + "| explained_variance | 0.962 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 35499 |\n", + "| policy_loss | 0.000292 |\n", + "| value_loss | 0.0109 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 565 |\n", + "| ep_rew_mean | 7.64 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 35600 |\n", + "| time_elapsed | 1416 |\n", + "| total_timesteps | 178000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.212 |\n", + "| explained_variance | -9.76e+13 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 35599 |\n", + "| policy_loss | -0.107 |\n", + "| value_loss | 0.576 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 561 |\n", + "| ep_rew_mean | 7.55 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 35700 |\n", + "| time_elapsed | 1420 |\n", + "| total_timesteps | 178500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.11 |\n", + "| explained_variance | 0.987 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 35699 |\n", + "| policy_loss | 0.00188 |\n", + "| value_loss | 0.00369 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 562 |\n", + "| ep_rew_mean | 7.54 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 35800 |\n", + "| time_elapsed | 1424 |\n", + "| total_timesteps | 179000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.172 |\n", + "| explained_variance | 0.802 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 35799 |\n", + "| policy_loss | -0.014 |\n", + "| value_loss | 0.161 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 559 |\n", + "| ep_rew_mean | 7.51 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 35900 |\n", + "| time_elapsed | 1428 |\n", + "| total_timesteps | 179500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0587 |\n", + "| explained_variance | -63.3 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 35899 |\n", + "| policy_loss | 0.00269 |\n", + "| value_loss | 0.0155 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.53 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 36000 |\n", + "| time_elapsed | 1432 |\n", + "| total_timesteps | 180000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.138 |\n", + "| explained_variance | 0.918 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 35999 |\n", + "| policy_loss | -0.0191 |\n", + "| value_loss | 0.0199 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 555 |\n", + "| ep_rew_mean | 7.47 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 36100 |\n", + "| time_elapsed | 1435 |\n", + "| total_timesteps | 180500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.395 |\n", + "| explained_variance | -163 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 36099 |\n", + "| policy_loss | -0.0255 |\n", + "| value_loss | 0.0285 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 550 |\n", + "| ep_rew_mean | 7.39 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 36200 |\n", + "| time_elapsed | 1439 |\n", + "| total_timesteps | 181000 |\n", + "| train/ | |\n", + "| entropy_loss | -6.76e-05 |\n", + "| explained_variance | -47.9 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 36199 |\n", + "| policy_loss | -2.29e-06 |\n", + "| value_loss | 0.0698 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 552 |\n", + "| ep_rew_mean | 7.48 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 36300 |\n", + "| time_elapsed | 1443 |\n", + "| total_timesteps | 181500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.171 |\n", + "| explained_variance | 0.978 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 36299 |\n", + "| policy_loss | 0.00187 |\n", + "| value_loss | 0.0051 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 560 |\n", + "| ep_rew_mean | 7.63 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 36400 |\n", + "| time_elapsed | 1447 |\n", + "| total_timesteps | 182000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0278 |\n", + "| explained_variance | -9.87 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 36399 |\n", + "| policy_loss | -0.000345 |\n", + "| value_loss | 0.0107 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 567 |\n", + "| ep_rew_mean | 7.71 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 36500 |\n", + "| time_elapsed | 1451 |\n", + "| total_timesteps | 182500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0817 |\n", + "| explained_variance | -326 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 36499 |\n", + "| policy_loss | -0.0004 |\n", + "| value_loss | 0.00975 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 569 |\n", + "| ep_rew_mean | 7.75 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 36600 |\n", + "| time_elapsed | 1455 |\n", + "| total_timesteps | 183000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.067 |\n", + "| explained_variance | -13 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 36599 |\n", + "| policy_loss | 0.0104 |\n", + "| value_loss | 0.589 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 572 |\n", + "| ep_rew_mean | 7.81 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 36700 |\n", + "| time_elapsed | 1458 |\n", + "| total_timesteps | 183500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0134 |\n", + "| explained_variance | -8.32 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 36699 |\n", + "| policy_loss | 0.000231 |\n", + "| value_loss | 0.0101 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 575 |\n", + "| ep_rew_mean | 7.85 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 36800 |\n", + "| time_elapsed | 1463 |\n", + "| total_timesteps | 184000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.131 |\n", + "| explained_variance | 0.976 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 36799 |\n", + "| policy_loss | 0.0635 |\n", + "| value_loss | 0.0164 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 574 |\n", + "| ep_rew_mean | 7.86 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 36900 |\n", + "| time_elapsed | 1466 |\n", + "| total_timesteps | 184500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0387 |\n", + "| explained_variance | 0.883 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 36899 |\n", + "| policy_loss | 0.0012 |\n", + "| value_loss | 0.0818 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 576 |\n", + "| ep_rew_mean | 7.82 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 37000 |\n", + "| time_elapsed | 1470 |\n", + "| total_timesteps | 185000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000433 |\n", + "| explained_variance | -7.48 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 36999 |\n", + "| policy_loss | -1.34e-06 |\n", + "| value_loss | 0.00814 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 7.94 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 37100 |\n", + "| time_elapsed | 1474 |\n", + "| total_timesteps | 185500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.201 |\n", + "| explained_variance | 0.889 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 37099 |\n", + "| policy_loss | 0.0357 |\n", + "| value_loss | 0.0453 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 588 |\n", + "| ep_rew_mean | 8.09 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 37200 |\n", + "| time_elapsed | 1478 |\n", + "| total_timesteps | 186000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0602 |\n", + "| explained_variance | -3.68 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 37199 |\n", + "| policy_loss | -0.000809 |\n", + "| value_loss | 0.0023 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 588 |\n", + "| ep_rew_mean | 8.11 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 37300 |\n", + "| time_elapsed | 1482 |\n", + "| total_timesteps | 186500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000626 |\n", + "| explained_variance | -20 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 37299 |\n", + "| policy_loss | 1.65e-06 |\n", + "| value_loss | 0.0234 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 581 |\n", + "| ep_rew_mean | 7.97 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 37400 |\n", + "| time_elapsed | 1486 |\n", + "| total_timesteps | 187000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0747 |\n", + "| explained_variance | 0.73 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 37399 |\n", + "| policy_loss | -0.00726 |\n", + "| value_loss | 0.0901 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 584 |\n", + "| ep_rew_mean | 8.04 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 37500 |\n", + "| time_elapsed | 1490 |\n", + "| total_timesteps | 187500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000625 |\n", + "| explained_variance | -3.37 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 37499 |\n", + "| policy_loss | 6.32e-06 |\n", + "| value_loss | 0.0121 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.04 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 37600 |\n", + "| time_elapsed | 1494 |\n", + "| total_timesteps | 188000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.134 |\n", + "| explained_variance | -308 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 37599 |\n", + "| policy_loss | -0.0254 |\n", + "| value_loss | 0.485 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.09 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 37700 |\n", + "| time_elapsed | 1498 |\n", + "| total_timesteps | 188500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.212 |\n", + "| explained_variance | 0.376 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 37699 |\n", + "| policy_loss | -0.0151 |\n", + "| value_loss | 0.0737 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 587 |\n", + "| ep_rew_mean | 8.24 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 37800 |\n", + "| time_elapsed | 1502 |\n", + "| total_timesteps | 189000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0329 |\n", + "| explained_variance | -52.1 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 37799 |\n", + "| policy_loss | -0.0016 |\n", + "| value_loss | 0.0363 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 588 |\n", + "| ep_rew_mean | 8.3 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 37900 |\n", + "| time_elapsed | 1506 |\n", + "| total_timesteps | 189500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.103 |\n", + "| explained_variance | -337 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 37899 |\n", + "| policy_loss | 0.00187 |\n", + "| value_loss | 0.0422 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 585 |\n", + "| ep_rew_mean | 8.25 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 38000 |\n", + "| time_elapsed | 1509 |\n", + "| total_timesteps | 190000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.338 |\n", + "| explained_variance | -399 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 37999 |\n", + "| policy_loss | -0.0701 |\n", + "| value_loss | 0.0106 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 584 |\n", + "| ep_rew_mean | 8.2 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 38100 |\n", + "| time_elapsed | 1513 |\n", + "| total_timesteps | 190500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.309 |\n", + "| explained_variance | 0.99 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 38099 |\n", + "| policy_loss | 0.0115 |\n", + "| value_loss | 0.00507 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 583 |\n", + "| ep_rew_mean | 8.07 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 38200 |\n", + "| time_elapsed | 1517 |\n", + "| total_timesteps | 191000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.34 |\n", + "| explained_variance | -9.68e+13 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 38199 |\n", + "| policy_loss | -0.249 |\n", + "| value_loss | 0.94 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 587 |\n", + "| ep_rew_mean | 8.15 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 38300 |\n", + "| time_elapsed | 1521 |\n", + "| total_timesteps | 191500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0453 |\n", + "| explained_variance | -197 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 38299 |\n", + "| policy_loss | 0.00305 |\n", + "| value_loss | 0.058 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 589 |\n", + "| ep_rew_mean | 8.23 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 38400 |\n", + "| time_elapsed | 1525 |\n", + "| total_timesteps | 192000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.121 |\n", + "| explained_variance | 0.605 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 38399 |\n", + "| policy_loss | -0.00266 |\n", + "| value_loss | 0.0125 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 594 |\n", + "| ep_rew_mean | 8.33 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 38500 |\n", + "| time_elapsed | 1529 |\n", + "| total_timesteps | 192500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00102 |\n", + "| explained_variance | -0.574 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 38499 |\n", + "| policy_loss | -7.44e-06 |\n", + "| value_loss | 0.00396 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 591 |\n", + "| ep_rew_mean | 8.27 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 38600 |\n", + "| time_elapsed | 1533 |\n", + "| total_timesteps | 193000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0107 |\n", + "| explained_variance | -16 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 38599 |\n", + "| policy_loss | 0.000195 |\n", + "| value_loss | 0.0355 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 591 |\n", + "| ep_rew_mean | 8.26 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 38700 |\n", + "| time_elapsed | 1537 |\n", + "| total_timesteps | 193500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.538 |\n", + "| explained_variance | nan |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 38699 |\n", + "| policy_loss | -0.0334 |\n", + "| value_loss | 0.0368 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 591 |\n", + "| ep_rew_mean | 8.25 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 38800 |\n", + "| time_elapsed | 1541 |\n", + "| total_timesteps | 194000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00669 |\n", + "| explained_variance | 0.691 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 38799 |\n", + "| policy_loss | -0.00029 |\n", + "| value_loss | 0.0927 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 589 |\n", + "| ep_rew_mean | 8.15 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 38900 |\n", + "| time_elapsed | 1545 |\n", + "| total_timesteps | 194500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.322 |\n", + "| explained_variance | -0.0103 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 38899 |\n", + "| policy_loss | -0.0748 |\n", + "| value_loss | 0.151 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 582 |\n", + "| ep_rew_mean | 8.03 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 39000 |\n", + "| time_elapsed | 1549 |\n", + "| total_timesteps | 195000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.236 |\n", + "| explained_variance | 0.86 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 38999 |\n", + "| policy_loss | 0.016 |\n", + "| value_loss | 0.0328 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 587 |\n", + "| ep_rew_mean | 8.11 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 39100 |\n", + "| time_elapsed | 1552 |\n", + "| total_timesteps | 195500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0606 |\n", + "| explained_variance | -27.1 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 39099 |\n", + "| policy_loss | 0.00101 |\n", + "| value_loss | 0.0698 |\n", + "------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 587 |\n", + "| ep_rew_mean | 8.08 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 39200 |\n", + "| time_elapsed | 1555 |\n", + "| total_timesteps | 196000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00191 |\n", + "| explained_variance | 0.976 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 39199 |\n", + "| policy_loss | -2.34e-05 |\n", + "| value_loss | 0.0156 |\n", + "-------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 585 |\n", + "| ep_rew_mean | 8 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 39300 |\n", + "| time_elapsed | 1559 |\n", + "| total_timesteps | 196500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.294 |\n", + "| explained_variance | -1.01e+04 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 39299 |\n", + "| policy_loss | -0.0495 |\n", + "| value_loss | 0.0699 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 579 |\n", + "| ep_rew_mean | 7.92 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 39400 |\n", + "| time_elapsed | 1563 |\n", + "| total_timesteps | 197000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.335 |\n", + "| explained_variance | -20.8 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 39399 |\n", + "| policy_loss | -0.025 |\n", + "| value_loss | 0.0299 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 578 |\n", + "| ep_rew_mean | 7.95 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 39500 |\n", + "| time_elapsed | 1567 |\n", + "| total_timesteps | 197500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.174 |\n", + "| explained_variance | -272 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 39499 |\n", + "| policy_loss | 0.000194 |\n", + "| value_loss | 0.0314 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 577 |\n", + "| ep_rew_mean | 7.95 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 39600 |\n", + "| time_elapsed | 1571 |\n", + "| total_timesteps | 198000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.184 |\n", + "| explained_variance | -8.78 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 39599 |\n", + "| policy_loss | 0.0193 |\n", + "| value_loss | 0.0758 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 574 |\n", + "| ep_rew_mean | 7.89 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 39700 |\n", + "| time_elapsed | 1575 |\n", + "| total_timesteps | 198500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0459 |\n", + "| explained_variance | -744 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 39699 |\n", + "| policy_loss | 0.000555 |\n", + "| value_loss | 0.00781 |\n", + "------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 575 |\n", + "| ep_rew_mean | 7.85 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 39800 |\n", + "| time_elapsed | 1579 |\n", + "| total_timesteps | 199000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.0128 |\n", + "| explained_variance | -5.29 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 39799 |\n", + "| policy_loss | 0.000485 |\n", + "| value_loss | 0.037 |\n", + "------------------------------------\n", + "-------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 576 |\n", + "| ep_rew_mean | 7.86 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 39900 |\n", + "| time_elapsed | 1583 |\n", + "| total_timesteps | 199500 |\n", + "| train/ | |\n", + "| entropy_loss | -0.000176 |\n", + "| explained_variance | -6.18 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 39899 |\n", + "| policy_loss | 4.95e-07 |\n", + "| value_loss | 0.00348 |\n", + "-------------------------------------\n", + "------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 578 |\n", + "| ep_rew_mean | 7.88 |\n", + "| time/ | |\n", + "| fps | 125 |\n", + "| iterations | 40000 |\n", + "| time_elapsed | 1587 |\n", + "| total_timesteps | 200000 |\n", + "| train/ | |\n", + "| entropy_loss | -0.00109 |\n", + "| explained_variance | 0.598 |\n", + "| learning_rate | 0.0007 |\n", + "| n_updates | 39999 |\n", + "| policy_loss | 8.01e-06 |\n", + "| value_loss | 0.00507 |\n", + "------------------------------------\n", + "******* Training PPO *******\n", + "Using cuda device\n", + "Wrapping the env in a VecTransposeImage.\n", + "Logging to Breakout-v0\\PPO_200000\\logs\\PPO_1\n", + "---------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.38 |\n", + "| time/ | |\n", + "| fps | 159 |\n", + "| iterations | 1 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 2048 |\n", + "---------------------------------\n", + "------------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.29 |\n", + "| time/ | |\n", + "| fps | 147 |\n", + "| iterations | 2 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 4096 |\n", + "| train/ | |\n", + "| approx_kl | 0.0074348208 |\n", + "| clip_fraction | 0.0237 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -1.38 |\n", + "| explained_variance | -0.0228 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.00649 |\n", + "| n_updates | 10 |\n", + "| policy_gradient_loss | -0.00242 |\n", + "| value_loss | 0.0788 |\n", + "------------------------------------------\n", + "-----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 3 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 6144 |\n", + "| train/ | |\n", + "| approx_kl | 0.011112304 |\n", + "| clip_fraction | 0.0882 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -1.38 |\n", + "| explained_variance | 0.451 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.00997 |\n", + "| n_updates | 20 |\n", + "| policy_gradient_loss | -0.0177 |\n", + "| value_loss | 0.0673 |\n", + "-----------------------------------------\n", + "-----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.72 |\n", + "| time/ | |\n", + "| fps | 136 |\n", + "| iterations | 4 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 8192 |\n", + "| train/ | |\n", + "| approx_kl | 0.013863411 |\n", + "| clip_fraction | 0.143 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -1.36 |\n", + "| explained_variance | 0.486 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.04 |\n", + "| n_updates | 30 |\n", + "| policy_gradient_loss | -0.0267 |\n", + "| value_loss | 0.0805 |\n", + "-----------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 315 |\n", + "| ep_rew_mean | 2.19 |\n", + "| time/ | |\n", + "| fps | 137 |\n", + "| iterations | 5 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 10240 |\n", + "| train/ | |\n", + "| approx_kl | 0.018323407 |\n", + "| clip_fraction | 0.192 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -1.34 |\n", + "| explained_variance | 0.5 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0381 |\n", + "| n_updates | 40 |\n", + "| policy_gradient_loss | -0.0451 |\n", + "| value_loss | 0.0852 |\n", + "-----------------------------------------\n", + "-----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 331 |\n", + "| ep_rew_mean | 2.66 |\n", + "| time/ | |\n", + "| fps | 138 |\n", + "| iterations | 6 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 12288 |\n", + "| train/ | |\n", + "| approx_kl | 0.022966402 |\n", + "| clip_fraction | 0.266 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -1.29 |\n", + "| explained_variance | 0.507 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0363 |\n", + "| n_updates | 50 |\n", + "| policy_gradient_loss | -0.0557 |\n", + "| value_loss | 0.113 |\n", + "-----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 348 |\n", + "| ep_rew_mean | 3.05 |\n", + "| time/ | |\n", + "| fps | 137 |\n", + "| iterations | 7 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 14336 |\n", + "| train/ | |\n", + "| approx_kl | 0.02551283 |\n", + "| clip_fraction | 0.258 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -1.25 |\n", + "| explained_variance | 0.563 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0766 |\n", + "| n_updates | 60 |\n", + "| policy_gradient_loss | -0.0611 |\n", + "| value_loss | 0.111 |\n", + "----------------------------------------\n", + "-----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 375 |\n", + "| ep_rew_mean | 3.57 |\n", + "| time/ | |\n", + "| fps | 138 |\n", + "| iterations | 8 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 16384 |\n", + "| train/ | |\n", + "| approx_kl | 0.031129573 |\n", + "| clip_fraction | 0.31 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -1.21 |\n", + "| explained_variance | 0.485 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0638 |\n", + "| n_updates | 70 |\n", + "| policy_gradient_loss | -0.0674 |\n", + "| value_loss | 0.123 |\n", + "-----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 398 |\n", + "| ep_rew_mean | 4.06 |\n", + "| time/ | |\n", + "| fps | 139 |\n", + "| iterations | 9 |\n", + "| time_elapsed | 132 |\n", + "| total_timesteps | 18432 |\n", + "| train/ | |\n", + "| approx_kl | 0.03541729 |\n", + "| clip_fraction | 0.321 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -1.17 |\n", + "| explained_variance | 0.562 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0846 |\n", + "| n_updates | 80 |\n", + "| policy_gradient_loss | -0.0699 |\n", + "| value_loss | 0.11 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 414 |\n", + "| ep_rew_mean | 4.34 |\n", + "| time/ | |\n", + "| fps | 140 |\n", + "| iterations | 10 |\n", + "| time_elapsed | 145 |\n", + "| total_timesteps | 20480 |\n", + "| train/ | |\n", + "| approx_kl | 0.03561859 |\n", + "| clip_fraction | 0.324 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -1.15 |\n", + "| explained_variance | 0.611 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0692 |\n", + "| n_updates | 90 |\n", + "| policy_gradient_loss | -0.0714 |\n", + "| value_loss | 0.104 |\n", + "----------------------------------------\n", + "-----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 439 |\n", + "| ep_rew_mean | 4.78 |\n", + "| time/ | |\n", + "| fps | 140 |\n", + "| iterations | 11 |\n", + "| time_elapsed | 160 |\n", + "| total_timesteps | 22528 |\n", + "| train/ | |\n", + "| approx_kl | 0.043584764 |\n", + "| clip_fraction | 0.36 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -1.11 |\n", + "| explained_variance | 0.596 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0895 |\n", + "| n_updates | 100 |\n", + "| policy_gradient_loss | -0.0743 |\n", + "| value_loss | 0.13 |\n", + "-----------------------------------------\n", + "-----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 460 |\n", + "| ep_rew_mean | 5.27 |\n", + "| time/ | |\n", + "| fps | 140 |\n", + "| iterations | 12 |\n", + "| time_elapsed | 174 |\n", + "| total_timesteps | 24576 |\n", + "| train/ | |\n", + "| approx_kl | 0.045096096 |\n", + "| clip_fraction | 0.34 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -1.08 |\n", + "| explained_variance | 0.733 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0898 |\n", + "| n_updates | 110 |\n", + "| policy_gradient_loss | -0.0708 |\n", + "| value_loss | 0.0774 |\n", + "-----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 482 |\n", + "| ep_rew_mean | 5.72 |\n", + "| time/ | |\n", + "| fps | 141 |\n", + "| iterations | 13 |\n", + "| time_elapsed | 188 |\n", + "| total_timesteps | 26624 |\n", + "| train/ | |\n", + "| approx_kl | 0.05456361 |\n", + "| clip_fraction | 0.363 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -1.03 |\n", + "| explained_variance | 0.797 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0711 |\n", + "| n_updates | 120 |\n", + "| policy_gradient_loss | -0.0736 |\n", + "| value_loss | 0.0668 |\n", + "----------------------------------------\n", + "-----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 495 |\n", + "| ep_rew_mean | 5.93 |\n", + "| time/ | |\n", + "| fps | 141 |\n", + "| iterations | 14 |\n", + "| time_elapsed | 202 |\n", + "| total_timesteps | 28672 |\n", + "| train/ | |\n", + "| approx_kl | 0.061365984 |\n", + "| clip_fraction | 0.396 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -1.02 |\n", + "| explained_variance | 0.799 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.106 |\n", + "| n_updates | 130 |\n", + "| policy_gradient_loss | -0.0773 |\n", + "| value_loss | 0.0596 |\n", + "-----------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 510 |\n", + "| ep_rew_mean | 6.28 |\n", + "| time/ | |\n", + "| fps | 141 |\n", + "| iterations | 15 |\n", + "| time_elapsed | 217 |\n", + "| total_timesteps | 30720 |\n", + "| train/ | |\n", + "| approx_kl | 0.055378716 |\n", + "| clip_fraction | 0.373 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.972 |\n", + "| explained_variance | 0.736 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.101 |\n", + "| n_updates | 140 |\n", + "| policy_gradient_loss | -0.075 |\n", + "| value_loss | 0.0755 |\n", + "-----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 510 |\n", + "| ep_rew_mean | 6.31 |\n", + "| time/ | |\n", + "| fps | 141 |\n", + "| iterations | 16 |\n", + "| time_elapsed | 231 |\n", + "| total_timesteps | 32768 |\n", + "| train/ | |\n", + "| approx_kl | 0.06191469 |\n", + "| clip_fraction | 0.408 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.939 |\n", + "| explained_variance | 0.706 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.098 |\n", + "| n_updates | 150 |\n", + "| policy_gradient_loss | -0.0793 |\n", + "| value_loss | 0.0712 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 516 |\n", + "| ep_rew_mean | 6.44 |\n", + "| time/ | |\n", + "| fps | 141 |\n", + "| iterations | 17 |\n", + "| time_elapsed | 245 |\n", + "| total_timesteps | 34816 |\n", + "| train/ | |\n", + "| approx_kl | 0.06931962 |\n", + "| clip_fraction | 0.39 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.914 |\n", + "| explained_variance | 0.726 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0921 |\n", + "| n_updates | 160 |\n", + "| policy_gradient_loss | -0.0768 |\n", + "| value_loss | 0.0755 |\n", + "----------------------------------------\n", + "-----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 510 |\n", + "| ep_rew_mean | 6.27 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 18 |\n", + "| time_elapsed | 259 |\n", + "| total_timesteps | 36864 |\n", + "| train/ | |\n", + "| approx_kl | 0.082729355 |\n", + "| clip_fraction | 0.412 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.87 |\n", + "| explained_variance | 0.791 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.101 |\n", + "| n_updates | 170 |\n", + "| policy_gradient_loss | -0.0772 |\n", + "| value_loss | 0.0601 |\n", + "-----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 515 |\n", + "| ep_rew_mean | 6.36 |\n", + "| time/ | |\n", + "| fps | 141 |\n", + "| iterations | 19 |\n", + "| time_elapsed | 274 |\n", + "| total_timesteps | 38912 |\n", + "| train/ | |\n", + "| approx_kl | 0.08745281 |\n", + "| clip_fraction | 0.415 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.839 |\n", + "| explained_variance | 0.772 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.107 |\n", + "| n_updates | 180 |\n", + "| policy_gradient_loss | -0.0749 |\n", + "| value_loss | 0.0604 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 507 |\n", + "| ep_rew_mean | 6.14 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 20 |\n", + "| time_elapsed | 288 |\n", + "| total_timesteps | 40960 |\n", + "| train/ | |\n", + "| approx_kl | 0.09114044 |\n", + "| clip_fraction | 0.42 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.86 |\n", + "| explained_variance | 0.796 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0934 |\n", + "| n_updates | 190 |\n", + "| policy_gradient_loss | -0.0762 |\n", + "| value_loss | 0.063 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 512 |\n", + "| ep_rew_mean | 6.2 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 21 |\n", + "| time_elapsed | 302 |\n", + "| total_timesteps | 43008 |\n", + "| train/ | |\n", + "| approx_kl | 0.10558937 |\n", + "| clip_fraction | 0.435 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.823 |\n", + "| explained_variance | 0.753 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0841 |\n", + "| n_updates | 200 |\n", + "| policy_gradient_loss | -0.0808 |\n", + "| value_loss | 0.0711 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 499 |\n", + "| ep_rew_mean | 5.95 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 22 |\n", + "| time_elapsed | 316 |\n", + "| total_timesteps | 45056 |\n", + "| train/ | |\n", + "| approx_kl | 0.08834617 |\n", + "| clip_fraction | 0.4 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.786 |\n", + "| explained_variance | 0.695 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.109 |\n", + "| n_updates | 210 |\n", + "| policy_gradient_loss | -0.0733 |\n", + "| value_loss | 0.0583 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 506 |\n", + "| ep_rew_mean | 6.12 |\n", + "| time/ | |\n", + "| fps | 141 |\n", + "| iterations | 23 |\n", + "| time_elapsed | 331 |\n", + "| total_timesteps | 47104 |\n", + "| train/ | |\n", + "| approx_kl | 0.10166623 |\n", + "| clip_fraction | 0.421 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.774 |\n", + "| explained_variance | 0.702 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.088 |\n", + "| n_updates | 220 |\n", + "| policy_gradient_loss | -0.0768 |\n", + "| value_loss | 0.0692 |\n", + "----------------------------------------\n", + "-----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 505 |\n", + "| ep_rew_mean | 6.23 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 24 |\n", + "| time_elapsed | 345 |\n", + "| total_timesteps | 49152 |\n", + "| train/ | |\n", + "| approx_kl | 0.109202646 |\n", + "| clip_fraction | 0.418 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.747 |\n", + "| explained_variance | 0.805 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.104 |\n", + "| n_updates | 230 |\n", + "| policy_gradient_loss | -0.0745 |\n", + "| value_loss | 0.0587 |\n", + "-----------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 521 |\n", + "| ep_rew_mean | 6.64 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 25 |\n", + "| time_elapsed | 359 |\n", + "| total_timesteps | 51200 |\n", + "| train/ | |\n", + "| approx_kl | 0.12011298 |\n", + "| clip_fraction | 0.418 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.699 |\n", + "| explained_variance | 0.747 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0769 |\n", + "| n_updates | 240 |\n", + "| policy_gradient_loss | -0.0764 |\n", + "| value_loss | 0.0689 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.89 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 26 |\n", + "| time_elapsed | 373 |\n", + "| total_timesteps | 53248 |\n", + "| train/ | |\n", + "| approx_kl | 0.13890032 |\n", + "| clip_fraction | 0.408 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.69 |\n", + "| explained_variance | 0.763 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.112 |\n", + "| n_updates | 250 |\n", + "| policy_gradient_loss | -0.0742 |\n", + "| value_loss | 0.0676 |\n", + "----------------------------------------\n", + "-----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 547 |\n", + "| ep_rew_mean | 7.22 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 27 |\n", + "| time_elapsed | 389 |\n", + "| total_timesteps | 55296 |\n", + "| train/ | |\n", + "| approx_kl | 0.120243564 |\n", + "| clip_fraction | 0.392 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.65 |\n", + "| explained_variance | 0.752 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0821 |\n", + "| n_updates | 260 |\n", + "| policy_gradient_loss | -0.0702 |\n", + "| value_loss | 0.0769 |\n", + "-----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 554 |\n", + "| ep_rew_mean | 7.39 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 28 |\n", + "| time_elapsed | 403 |\n", + "| total_timesteps | 57344 |\n", + "| train/ | |\n", + "| approx_kl | 0.12882699 |\n", + "| clip_fraction | 0.407 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.638 |\n", + "| explained_variance | 0.628 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.114 |\n", + "| n_updates | 270 |\n", + "| policy_gradient_loss | -0.0735 |\n", + "| value_loss | 0.0643 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 550 |\n", + "| ep_rew_mean | 7.27 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 29 |\n", + "| time_elapsed | 416 |\n", + "| total_timesteps | 59392 |\n", + "| train/ | |\n", + "| approx_kl | 0.13363059 |\n", + "| clip_fraction | 0.393 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.639 |\n", + "| explained_variance | 0.737 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0874 |\n", + "| n_updates | 280 |\n", + "| policy_gradient_loss | -0.0719 |\n", + "| value_loss | 0.0669 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 558 |\n", + "| ep_rew_mean | 7.37 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 30 |\n", + "| time_elapsed | 430 |\n", + "| total_timesteps | 61440 |\n", + "| train/ | |\n", + "| approx_kl | 0.17553839 |\n", + "| clip_fraction | 0.409 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.643 |\n", + "| explained_variance | 0.742 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.103 |\n", + "| n_updates | 290 |\n", + "| policy_gradient_loss | -0.0698 |\n", + "| value_loss | 0.0618 |\n", + "----------------------------------------\n", + "--------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 546 |\n", + "| ep_rew_mean | 7.08 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 31 |\n", + "| time_elapsed | 444 |\n", + "| total_timesteps | 63488 |\n", + "| train/ | |\n", + "| approx_kl | 0.141715 |\n", + "| clip_fraction | 0.413 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.653 |\n", + "| explained_variance | 0.786 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.102 |\n", + "| n_updates | 300 |\n", + "| policy_gradient_loss | -0.0738 |\n", + "| value_loss | 0.0524 |\n", + "--------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 544 |\n", + "| ep_rew_mean | 6.99 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 32 |\n", + "| time_elapsed | 458 |\n", + "| total_timesteps | 65536 |\n", + "| train/ | |\n", + "| approx_kl | 0.14705071 |\n", + "| clip_fraction | 0.408 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.631 |\n", + "| explained_variance | 0.806 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.101 |\n", + "| n_updates | 310 |\n", + "| policy_gradient_loss | -0.0747 |\n", + "| value_loss | 0.0522 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 550 |\n", + "| ep_rew_mean | 7.13 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 33 |\n", + "| time_elapsed | 472 |\n", + "| total_timesteps | 67584 |\n", + "| train/ | |\n", + "| approx_kl | 0.15750726 |\n", + "| clip_fraction | 0.403 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.613 |\n", + "| explained_variance | 0.754 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.119 |\n", + "| n_updates | 320 |\n", + "| policy_gradient_loss | -0.0719 |\n", + "| value_loss | 0.0574 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 550 |\n", + "| ep_rew_mean | 7.2 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 34 |\n", + "| time_elapsed | 487 |\n", + "| total_timesteps | 69632 |\n", + "| train/ | |\n", + "| approx_kl | 0.17063132 |\n", + "| clip_fraction | 0.395 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.59 |\n", + "| explained_variance | 0.721 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.106 |\n", + "| n_updates | 330 |\n", + "| policy_gradient_loss | -0.0699 |\n", + "| value_loss | 0.0599 |\n", + "----------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 541 |\n", + "| ep_rew_mean | 6.98 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 35 |\n", + "| time_elapsed | 500 |\n", + "| total_timesteps | 71680 |\n", + "| train/ | |\n", + "| approx_kl | 0.16702756 |\n", + "| clip_fraction | 0.4 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.57 |\n", + "| explained_variance | 0.783 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0967 |\n", + "| n_updates | 340 |\n", + "| policy_gradient_loss | -0.0669 |\n", + "| value_loss | 0.0595 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 534 |\n", + "| ep_rew_mean | 6.83 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 36 |\n", + "| time_elapsed | 514 |\n", + "| total_timesteps | 73728 |\n", + "| train/ | |\n", + "| approx_kl | 0.16488457 |\n", + "| clip_fraction | 0.399 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.581 |\n", + "| explained_variance | 0.755 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0844 |\n", + "| n_updates | 350 |\n", + "| policy_gradient_loss | -0.0676 |\n", + "| value_loss | 0.063 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 515 |\n", + "| ep_rew_mean | 6.51 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 37 |\n", + "| time_elapsed | 528 |\n", + "| total_timesteps | 75776 |\n", + "| train/ | |\n", + "| approx_kl | 0.17880183 |\n", + "| clip_fraction | 0.405 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.561 |\n", + "| explained_variance | 0.822 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.082 |\n", + "| n_updates | 360 |\n", + "| policy_gradient_loss | -0.0696 |\n", + "| value_loss | 0.0499 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 499 |\n", + "| ep_rew_mean | 6.2 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 38 |\n", + "| time_elapsed | 544 |\n", + "| total_timesteps | 77824 |\n", + "| train/ | |\n", + "| approx_kl | 0.18228962 |\n", + "| clip_fraction | 0.399 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.555 |\n", + "| explained_variance | 0.747 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0948 |\n", + "| n_updates | 370 |\n", + "| policy_gradient_loss | -0.0709 |\n", + "| value_loss | 0.0635 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 499 |\n", + "| ep_rew_mean | 6.15 |\n", + "| time/ | |\n", + "| fps | 142 |\n", + "| iterations | 39 |\n", + "| time_elapsed | 558 |\n", + "| total_timesteps | 79872 |\n", + "| train/ | |\n", + "| approx_kl | 0.17400414 |\n", + "| clip_fraction | 0.396 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.574 |\n", + "| explained_variance | 0.744 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0993 |\n", + "| n_updates | 380 |\n", + "| policy_gradient_loss | -0.0726 |\n", + "| value_loss | 0.0579 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 510 |\n", + "| ep_rew_mean | 6.39 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 40 |\n", + "| time_elapsed | 572 |\n", + "| total_timesteps | 81920 |\n", + "| train/ | |\n", + "| approx_kl | 0.19158044 |\n", + "| clip_fraction | 0.398 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.559 |\n", + "| explained_variance | 0.714 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.115 |\n", + "| n_updates | 390 |\n", + "| policy_gradient_loss | -0.072 |\n", + "| value_loss | 0.0591 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 510 |\n", + "| ep_rew_mean | 6.49 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 41 |\n", + "| time_elapsed | 586 |\n", + "| total_timesteps | 83968 |\n", + "| train/ | |\n", + "| approx_kl | 0.20450193 |\n", + "| clip_fraction | 0.42 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.585 |\n", + "| explained_variance | 0.809 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.095 |\n", + "| n_updates | 400 |\n", + "| policy_gradient_loss | -0.0753 |\n", + "| value_loss | 0.0553 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 511 |\n", + "| ep_rew_mean | 6.42 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 42 |\n", + "| time_elapsed | 600 |\n", + "| total_timesteps | 86016 |\n", + "| train/ | |\n", + "| approx_kl | 0.19733346 |\n", + "| clip_fraction | 0.41 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.569 |\n", + "| explained_variance | 0.792 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.094 |\n", + "| n_updates | 410 |\n", + "| policy_gradient_loss | -0.0735 |\n", + "| value_loss | 0.0608 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 516 |\n", + "| ep_rew_mean | 6.56 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 43 |\n", + "| time_elapsed | 614 |\n", + "| total_timesteps | 88064 |\n", + "| train/ | |\n", + "| approx_kl | 0.16123527 |\n", + "| clip_fraction | 0.376 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.531 |\n", + "| explained_variance | 0.743 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0691 |\n", + "| n_updates | 420 |\n", + "| policy_gradient_loss | -0.0647 |\n", + "| value_loss | 0.0657 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 514 |\n", + "| ep_rew_mean | 6.47 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 44 |\n", + "| time_elapsed | 627 |\n", + "| total_timesteps | 90112 |\n", + "| train/ | |\n", + "| approx_kl | 0.18678734 |\n", + "| clip_fraction | 0.386 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.518 |\n", + "| explained_variance | 0.757 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0956 |\n", + "| n_updates | 430 |\n", + "| policy_gradient_loss | -0.0679 |\n", + "| value_loss | 0.06 |\n", + "----------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 513 |\n", + "| ep_rew_mean | 6.43 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 45 |\n", + "| time_elapsed | 642 |\n", + "| total_timesteps | 92160 |\n", + "| train/ | |\n", + "| approx_kl | 0.15156776 |\n", + "| clip_fraction | 0.379 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.528 |\n", + "| explained_variance | 0.76 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0927 |\n", + "| n_updates | 440 |\n", + "| policy_gradient_loss | -0.0651 |\n", + "| value_loss | 0.0657 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 496 |\n", + "| ep_rew_mean | 6.09 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 46 |\n", + "| time_elapsed | 656 |\n", + "| total_timesteps | 94208 |\n", + "| train/ | |\n", + "| approx_kl | 0.20921491 |\n", + "| clip_fraction | 0.393 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.52 |\n", + "| explained_variance | 0.703 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0922 |\n", + "| n_updates | 450 |\n", + "| policy_gradient_loss | -0.0655 |\n", + "| value_loss | 0.0569 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 502 |\n", + "| ep_rew_mean | 6.27 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 47 |\n", + "| time_elapsed | 670 |\n", + "| total_timesteps | 96256 |\n", + "| train/ | |\n", + "| approx_kl | 0.21877939 |\n", + "| clip_fraction | 0.407 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.504 |\n", + "| explained_variance | 0.671 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0963 |\n", + "| n_updates | 460 |\n", + "| policy_gradient_loss | -0.0697 |\n", + "| value_loss | 0.0671 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 522 |\n", + "| ep_rew_mean | 6.67 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 48 |\n", + "| time_elapsed | 684 |\n", + "| total_timesteps | 98304 |\n", + "| train/ | |\n", + "| approx_kl | 0.22464156 |\n", + "| clip_fraction | 0.381 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.467 |\n", + "| explained_variance | 0.724 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.105 |\n", + "| n_updates | 470 |\n", + "| policy_gradient_loss | -0.0634 |\n", + "| value_loss | 0.0555 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 514 |\n", + "| ep_rew_mean | 6.48 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 49 |\n", + "| time_elapsed | 700 |\n", + "| total_timesteps | 100352 |\n", + "| train/ | |\n", + "| approx_kl | 0.24722983 |\n", + "| clip_fraction | 0.383 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.477 |\n", + "| explained_variance | 0.677 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0998 |\n", + "| n_updates | 480 |\n", + "| policy_gradient_loss | -0.0652 |\n", + "| value_loss | 0.0558 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 514 |\n", + "| ep_rew_mean | 6.5 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 50 |\n", + "| time_elapsed | 714 |\n", + "| total_timesteps | 102400 |\n", + "| train/ | |\n", + "| approx_kl | 0.23575845 |\n", + "| clip_fraction | 0.376 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.475 |\n", + "| explained_variance | 0.682 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0897 |\n", + "| n_updates | 490 |\n", + "| policy_gradient_loss | -0.0641 |\n", + "| value_loss | 0.0605 |\n", + "----------------------------------------\n", + "---------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.75 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 51 |\n", + "| time_elapsed | 728 |\n", + "| total_timesteps | 104448 |\n", + "| train/ | |\n", + "| approx_kl | 0.2517158 |\n", + "| clip_fraction | 0.4 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.495 |\n", + "| explained_variance | 0.787 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.11 |\n", + "| n_updates | 500 |\n", + "| policy_gradient_loss | -0.0721 |\n", + "| value_loss | 0.043 |\n", + "---------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 532 |\n", + "| ep_rew_mean | 6.78 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 52 |\n", + "| time_elapsed | 742 |\n", + "| total_timesteps | 106496 |\n", + "| train/ | |\n", + "| approx_kl | 0.22130829 |\n", + "| clip_fraction | 0.401 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.506 |\n", + "| explained_variance | 0.739 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0905 |\n", + "| n_updates | 510 |\n", + "| policy_gradient_loss | -0.0683 |\n", + "| value_loss | 0.0566 |\n", + "----------------------------------------\n", + "---------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.69 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 53 |\n", + "| time_elapsed | 756 |\n", + "| total_timesteps | 108544 |\n", + "| train/ | |\n", + "| approx_kl | 0.2464986 |\n", + "| clip_fraction | 0.405 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.5 |\n", + "| explained_variance | 0.799 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.107 |\n", + "| n_updates | 520 |\n", + "| policy_gradient_loss | -0.069 |\n", + "| value_loss | 0.0493 |\n", + "---------------------------------------\n", + "---------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 530 |\n", + "| ep_rew_mean | 6.81 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 54 |\n", + "| time_elapsed | 769 |\n", + "| total_timesteps | 110592 |\n", + "| train/ | |\n", + "| approx_kl | 0.2439814 |\n", + "| clip_fraction | 0.399 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.502 |\n", + "| explained_variance | 0.818 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0905 |\n", + "| n_updates | 530 |\n", + "| policy_gradient_loss | -0.0694 |\n", + "| value_loss | 0.051 |\n", + "---------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.85 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 55 |\n", + "| time_elapsed | 783 |\n", + "| total_timesteps | 112640 |\n", + "| train/ | |\n", + "| approx_kl | 0.19280937 |\n", + "| clip_fraction | 0.408 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.515 |\n", + "| explained_variance | 0.767 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.102 |\n", + "| n_updates | 540 |\n", + "| policy_gradient_loss | -0.0745 |\n", + "| value_loss | 0.0584 |\n", + "----------------------------------------\n", + "---------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 543 |\n", + "| ep_rew_mean | 7.1 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 56 |\n", + "| time_elapsed | 799 |\n", + "| total_timesteps | 114688 |\n", + "| train/ | |\n", + "| approx_kl | 0.2179278 |\n", + "| clip_fraction | 0.38 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.479 |\n", + "| explained_variance | 0.796 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.107 |\n", + "| n_updates | 550 |\n", + "| policy_gradient_loss | -0.0673 |\n", + "| value_loss | 0.0625 |\n", + "---------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 542 |\n", + "| ep_rew_mean | 7.19 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 57 |\n", + "| time_elapsed | 813 |\n", + "| total_timesteps | 116736 |\n", + "| train/ | |\n", + "| approx_kl | 0.25589988 |\n", + "| clip_fraction | 0.39 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.464 |\n", + "| explained_variance | 0.771 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0857 |\n", + "| n_updates | 560 |\n", + "| policy_gradient_loss | -0.0711 |\n", + "| value_loss | 0.0536 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 553 |\n", + "| ep_rew_mean | 7.4 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 58 |\n", + "| time_elapsed | 827 |\n", + "| total_timesteps | 118784 |\n", + "| train/ | |\n", + "| approx_kl | 0.27915424 |\n", + "| clip_fraction | 0.39 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.492 |\n", + "| explained_variance | 0.812 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0723 |\n", + "| n_updates | 570 |\n", + "| policy_gradient_loss | -0.0658 |\n", + "| value_loss | 0.051 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 552 |\n", + "| ep_rew_mean | 7.43 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 59 |\n", + "| time_elapsed | 841 |\n", + "| total_timesteps | 120832 |\n", + "| train/ | |\n", + "| approx_kl | 0.26594058 |\n", + "| clip_fraction | 0.408 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.477 |\n", + "| explained_variance | 0.752 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.093 |\n", + "| n_updates | 580 |\n", + "| policy_gradient_loss | -0.0717 |\n", + "| value_loss | 0.0526 |\n", + "----------------------------------------\n", + "---------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 548 |\n", + "| ep_rew_mean | 7.31 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 60 |\n", + "| time_elapsed | 855 |\n", + "| total_timesteps | 122880 |\n", + "| train/ | |\n", + "| approx_kl | 0.2564836 |\n", + "| clip_fraction | 0.392 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.466 |\n", + "| explained_variance | 0.828 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0953 |\n", + "| n_updates | 590 |\n", + "| policy_gradient_loss | -0.0682 |\n", + "| value_loss | 0.0451 |\n", + "---------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 548 |\n", + "| ep_rew_mean | 7.26 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 61 |\n", + "| time_elapsed | 869 |\n", + "| total_timesteps | 124928 |\n", + "| train/ | |\n", + "| approx_kl | 0.22554119 |\n", + "| clip_fraction | 0.387 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.474 |\n", + "| explained_variance | 0.813 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0953 |\n", + "| n_updates | 600 |\n", + "| policy_gradient_loss | -0.0676 |\n", + "| value_loss | 0.056 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 544 |\n", + "| ep_rew_mean | 7.22 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 62 |\n", + "| time_elapsed | 883 |\n", + "| total_timesteps | 126976 |\n", + "| train/ | |\n", + "| approx_kl | 0.24754368 |\n", + "| clip_fraction | 0.394 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.464 |\n", + "| explained_variance | 0.791 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.107 |\n", + "| n_updates | 610 |\n", + "| policy_gradient_loss | -0.0662 |\n", + "| value_loss | 0.0534 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 543 |\n", + "| ep_rew_mean | 7.25 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 63 |\n", + "| time_elapsed | 898 |\n", + "| total_timesteps | 129024 |\n", + "| train/ | |\n", + "| approx_kl | 0.24811602 |\n", + "| clip_fraction | 0.399 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.454 |\n", + "| explained_variance | 0.776 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.078 |\n", + "| n_updates | 620 |\n", + "| policy_gradient_loss | -0.0728 |\n", + "| value_loss | 0.0507 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 7.23 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 64 |\n", + "| time_elapsed | 912 |\n", + "| total_timesteps | 131072 |\n", + "| train/ | |\n", + "| approx_kl | 0.25386676 |\n", + "| clip_fraction | 0.386 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.46 |\n", + "| explained_variance | 0.784 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0814 |\n", + "| n_updates | 630 |\n", + "| policy_gradient_loss | -0.0694 |\n", + "| value_loss | 0.0515 |\n", + "----------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 7.18 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 65 |\n", + "| time_elapsed | 926 |\n", + "| total_timesteps | 133120 |\n", + "| train/ | |\n", + "| approx_kl | 0.22427694 |\n", + "| clip_fraction | 0.383 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.441 |\n", + "| explained_variance | 0.821 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.087 |\n", + "| n_updates | 640 |\n", + "| policy_gradient_loss | -0.069 |\n", + "| value_loss | 0.0523 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 542 |\n", + "| ep_rew_mean | 7.17 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 66 |\n", + "| time_elapsed | 939 |\n", + "| total_timesteps | 135168 |\n", + "| train/ | |\n", + "| approx_kl | 0.25027168 |\n", + "| clip_fraction | 0.38 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.438 |\n", + "| explained_variance | 0.801 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0686 |\n", + "| n_updates | 650 |\n", + "| policy_gradient_loss | -0.0677 |\n", + "| value_loss | 0.0514 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 528 |\n", + "| ep_rew_mean | 6.91 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 67 |\n", + "| time_elapsed | 955 |\n", + "| total_timesteps | 137216 |\n", + "| train/ | |\n", + "| approx_kl | 0.24148904 |\n", + "| clip_fraction | 0.382 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.454 |\n", + "| explained_variance | 0.75 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0929 |\n", + "| n_updates | 660 |\n", + "| policy_gradient_loss | -0.0671 |\n", + "| value_loss | 0.0523 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 7.13 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 68 |\n", + "| time_elapsed | 969 |\n", + "| total_timesteps | 139264 |\n", + "| train/ | |\n", + "| approx_kl | 0.28584003 |\n", + "| clip_fraction | 0.379 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.436 |\n", + "| explained_variance | 0.788 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.105 |\n", + "| n_updates | 670 |\n", + "| policy_gradient_loss | -0.068 |\n", + "| value_loss | 0.044 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 536 |\n", + "| ep_rew_mean | 6.9 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 69 |\n", + "| time_elapsed | 983 |\n", + "| total_timesteps | 141312 |\n", + "| train/ | |\n", + "| approx_kl | 0.27353552 |\n", + "| clip_fraction | 0.408 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.435 |\n", + "| explained_variance | 0.771 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0916 |\n", + "| n_updates | 680 |\n", + "| policy_gradient_loss | -0.0674 |\n", + "| value_loss | 0.0489 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.82 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 70 |\n", + "| time_elapsed | 997 |\n", + "| total_timesteps | 143360 |\n", + "| train/ | |\n", + "| approx_kl | 0.29146767 |\n", + "| clip_fraction | 0.384 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.419 |\n", + "| explained_variance | 0.789 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.115 |\n", + "| n_updates | 690 |\n", + "| policy_gradient_loss | -0.0657 |\n", + "| value_loss | 0.0485 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 7.03 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 71 |\n", + "| time_elapsed | 1011 |\n", + "| total_timesteps | 145408 |\n", + "| train/ | |\n", + "| approx_kl | 0.29717997 |\n", + "| clip_fraction | 0.374 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.424 |\n", + "| explained_variance | 0.739 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.108 |\n", + "| n_updates | 700 |\n", + "| policy_gradient_loss | -0.0669 |\n", + "| value_loss | 0.0574 |\n", + "----------------------------------------\n", + "---------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 548 |\n", + "| ep_rew_mean | 7.41 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 72 |\n", + "| time_elapsed | 1025 |\n", + "| total_timesteps | 147456 |\n", + "| train/ | |\n", + "| approx_kl | 0.2900552 |\n", + "| clip_fraction | 0.378 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.407 |\n", + "| explained_variance | 0.799 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0967 |\n", + "| n_updates | 710 |\n", + "| policy_gradient_loss | -0.0636 |\n", + "| value_loss | 0.0551 |\n", + "---------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 554 |\n", + "| ep_rew_mean | 7.54 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 73 |\n", + "| time_elapsed | 1039 |\n", + "| total_timesteps | 149504 |\n", + "| train/ | |\n", + "| approx_kl | 0.35325933 |\n", + "| clip_fraction | 0.387 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.402 |\n", + "| explained_variance | 0.73 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0861 |\n", + "| n_updates | 720 |\n", + "| policy_gradient_loss | -0.0681 |\n", + "| value_loss | 0.0652 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 557 |\n", + "| ep_rew_mean | 7.5 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 74 |\n", + "| time_elapsed | 1053 |\n", + "| total_timesteps | 151552 |\n", + "| train/ | |\n", + "| approx_kl | 0.25882453 |\n", + "| clip_fraction | 0.366 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.406 |\n", + "| explained_variance | 0.676 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0678 |\n", + "| n_updates | 730 |\n", + "| policy_gradient_loss | -0.0648 |\n", + "| value_loss | 0.059 |\n", + "----------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "---------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 556 |\n", + "| ep_rew_mean | 7.49 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 75 |\n", + "| time_elapsed | 1069 |\n", + "| total_timesteps | 153600 |\n", + "| train/ | |\n", + "| approx_kl | 0.2784238 |\n", + "| clip_fraction | 0.384 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.419 |\n", + "| explained_variance | 0.679 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0837 |\n", + "| n_updates | 740 |\n", + "| policy_gradient_loss | -0.0669 |\n", + "| value_loss | 0.0708 |\n", + "---------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 565 |\n", + "| ep_rew_mean | 7.7 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 76 |\n", + "| time_elapsed | 1082 |\n", + "| total_timesteps | 155648 |\n", + "| train/ | |\n", + "| approx_kl | 0.30195433 |\n", + "| clip_fraction | 0.393 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.422 |\n", + "| explained_variance | 0.699 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0993 |\n", + "| n_updates | 750 |\n", + "| policy_gradient_loss | -0.0677 |\n", + "| value_loss | 0.0596 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 563 |\n", + "| ep_rew_mean | 7.57 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 77 |\n", + "| time_elapsed | 1096 |\n", + "| total_timesteps | 157696 |\n", + "| train/ | |\n", + "| approx_kl | 0.26116168 |\n", + "| clip_fraction | 0.394 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.457 |\n", + "| explained_variance | 0.793 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.105 |\n", + "| n_updates | 760 |\n", + "| policy_gradient_loss | -0.0689 |\n", + "| value_loss | 0.0513 |\n", + "----------------------------------------\n", + "---------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 554 |\n", + "| ep_rew_mean | 7.27 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 78 |\n", + "| time_elapsed | 1110 |\n", + "| total_timesteps | 159744 |\n", + "| train/ | |\n", + "| approx_kl | 0.2658801 |\n", + "| clip_fraction | 0.414 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.457 |\n", + "| explained_variance | 0.733 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0972 |\n", + "| n_updates | 770 |\n", + "| policy_gradient_loss | -0.0686 |\n", + "| value_loss | 0.0582 |\n", + "---------------------------------------\n", + "---------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 543 |\n", + "| ep_rew_mean | 7.05 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 79 |\n", + "| time_elapsed | 1125 |\n", + "| total_timesteps | 161792 |\n", + "| train/ | |\n", + "| approx_kl | 0.2831304 |\n", + "| clip_fraction | 0.41 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.469 |\n", + "| explained_variance | 0.717 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.11 |\n", + "| n_updates | 780 |\n", + "| policy_gradient_loss | -0.0706 |\n", + "| value_loss | 0.0573 |\n", + "---------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 538 |\n", + "| ep_rew_mean | 7.04 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 80 |\n", + "| time_elapsed | 1139 |\n", + "| total_timesteps | 163840 |\n", + "| train/ | |\n", + "| approx_kl | 0.29544058 |\n", + "| clip_fraction | 0.391 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.453 |\n", + "| explained_variance | 0.709 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.105 |\n", + "| n_updates | 790 |\n", + "| policy_gradient_loss | -0.0724 |\n", + "| value_loss | 0.0605 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 529 |\n", + "| ep_rew_mean | 6.86 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 81 |\n", + "| time_elapsed | 1153 |\n", + "| total_timesteps | 165888 |\n", + "| train/ | |\n", + "| approx_kl | 0.29373556 |\n", + "| clip_fraction | 0.39 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.434 |\n", + "| explained_variance | 0.779 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.111 |\n", + "| n_updates | 800 |\n", + "| policy_gradient_loss | -0.0712 |\n", + "| value_loss | 0.0534 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 527 |\n", + "| ep_rew_mean | 6.84 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 82 |\n", + "| time_elapsed | 1167 |\n", + "| total_timesteps | 167936 |\n", + "| train/ | |\n", + "| approx_kl | 0.31549555 |\n", + "| clip_fraction | 0.4 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.42 |\n", + "| explained_variance | 0.76 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0939 |\n", + "| n_updates | 810 |\n", + "| policy_gradient_loss | -0.072 |\n", + "| value_loss | 0.0459 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 523 |\n", + "| ep_rew_mean | 6.86 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 83 |\n", + "| time_elapsed | 1182 |\n", + "| total_timesteps | 169984 |\n", + "| train/ | |\n", + "| approx_kl | 0.36642045 |\n", + "| clip_fraction | 0.393 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.407 |\n", + "| explained_variance | 0.69 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0773 |\n", + "| n_updates | 820 |\n", + "| policy_gradient_loss | -0.0682 |\n", + "| value_loss | 0.0497 |\n", + "----------------------------------------\n", + "---------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 7.03 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 84 |\n", + "| time_elapsed | 1196 |\n", + "| total_timesteps | 172032 |\n", + "| train/ | |\n", + "| approx_kl | 0.3540674 |\n", + "| clip_fraction | 0.376 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.392 |\n", + "| explained_variance | 0.717 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0922 |\n", + "| n_updates | 830 |\n", + "| policy_gradient_loss | -0.0691 |\n", + "| value_loss | 0.05 |\n", + "---------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.95 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 85 |\n", + "| time_elapsed | 1209 |\n", + "| total_timesteps | 174080 |\n", + "| train/ | |\n", + "| approx_kl | 0.34060726 |\n", + "| clip_fraction | 0.384 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.416 |\n", + "| explained_variance | 0.704 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0891 |\n", + "| n_updates | 840 |\n", + "| policy_gradient_loss | -0.0677 |\n", + "| value_loss | 0.0643 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 529 |\n", + "| ep_rew_mean | 6.85 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 86 |\n", + "| time_elapsed | 1223 |\n", + "| total_timesteps | 176128 |\n", + "| train/ | |\n", + "| approx_kl | 0.30397373 |\n", + "| clip_fraction | 0.398 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.41 |\n", + "| explained_variance | 0.748 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.106 |\n", + "| n_updates | 850 |\n", + "| policy_gradient_loss | -0.0677 |\n", + "| value_loss | 0.0617 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 7.11 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 87 |\n", + "| time_elapsed | 1238 |\n", + "| total_timesteps | 178176 |\n", + "| train/ | |\n", + "| approx_kl | 0.40354127 |\n", + "| clip_fraction | 0.391 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.402 |\n", + "| explained_variance | 0.718 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.1 |\n", + "| n_updates | 860 |\n", + "| policy_gradient_loss | -0.0668 |\n", + "| value_loss | 0.0621 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 550 |\n", + "| ep_rew_mean | 7.36 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 88 |\n", + "| time_elapsed | 1252 |\n", + "| total_timesteps | 180224 |\n", + "| train/ | |\n", + "| approx_kl | 0.34445953 |\n", + "| clip_fraction | 0.385 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.39 |\n", + "| explained_variance | 0.7 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.101 |\n", + "| n_updates | 870 |\n", + "| policy_gradient_loss | -0.0676 |\n", + "| value_loss | 0.0593 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 537 |\n", + "| ep_rew_mean | 6.99 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 89 |\n", + "| time_elapsed | 1266 |\n", + "| total_timesteps | 182272 |\n", + "| train/ | |\n", + "| approx_kl | 0.42724013 |\n", + "| clip_fraction | 0.39 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.371 |\n", + "| explained_variance | 0.69 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.105 |\n", + "| n_updates | 880 |\n", + "| policy_gradient_loss | -0.0706 |\n", + "| value_loss | 0.0613 |\n", + "----------------------------------------\n", + "---------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 533 |\n", + "| ep_rew_mean | 6.97 |\n", + "| time/ | |\n", + "| fps | 144 |\n", + "| iterations | 90 |\n", + "| time_elapsed | 1279 |\n", + "| total_timesteps | 184320 |\n", + "| train/ | |\n", + "| approx_kl | 0.3335083 |\n", + "| clip_fraction | 0.388 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.391 |\n", + "| explained_variance | 0.72 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0847 |\n", + "| n_updates | 890 |\n", + "| policy_gradient_loss | -0.069 |\n", + "| value_loss | 0.0563 |\n", + "---------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 531 |\n", + "| ep_rew_mean | 6.98 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 91 |\n", + "| time_elapsed | 1296 |\n", + "| total_timesteps | 186368 |\n", + "| train/ | |\n", + "| approx_kl | 0.33520117 |\n", + "| clip_fraction | 0.382 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.382 |\n", + "| explained_variance | 0.678 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0903 |\n", + "| n_updates | 900 |\n", + "| policy_gradient_loss | -0.0658 |\n", + "| value_loss | 0.0645 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 525 |\n", + "| ep_rew_mean | 6.79 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 92 |\n", + "| time_elapsed | 1310 |\n", + "| total_timesteps | 188416 |\n", + "| train/ | |\n", + "| approx_kl | 0.29656547 |\n", + "| clip_fraction | 0.398 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.401 |\n", + "| explained_variance | 0.727 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0964 |\n", + "| n_updates | 910 |\n", + "| policy_gradient_loss | -0.0667 |\n", + "| value_loss | 0.0518 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 516 |\n", + "| ep_rew_mean | 6.6 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 93 |\n", + "| time_elapsed | 1323 |\n", + "| total_timesteps | 190464 |\n", + "| train/ | |\n", + "| approx_kl | 0.33420765 |\n", + "| clip_fraction | 0.39 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.389 |\n", + "| explained_variance | 0.648 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0673 |\n", + "| n_updates | 920 |\n", + "| policy_gradient_loss | -0.068 |\n", + "| value_loss | 0.0575 |\n", + "----------------------------------------\n", + "---------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 525 |\n", + "| ep_rew_mean | 6.81 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 94 |\n", + "| time_elapsed | 1337 |\n", + "| total_timesteps | 192512 |\n", + "| train/ | |\n", + "| approx_kl | 0.3820832 |\n", + "| clip_fraction | 0.396 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.406 |\n", + "| explained_variance | 0.624 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0869 |\n", + "| n_updates | 930 |\n", + "| policy_gradient_loss | -0.0671 |\n", + "| value_loss | 0.0583 |\n", + "---------------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 541 |\n", + "| ep_rew_mean | 7.14 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 95 |\n", + "| time_elapsed | 1351 |\n", + "| total_timesteps | 194560 |\n", + "| train/ | |\n", + "| approx_kl | 0.38957772 |\n", + "| clip_fraction | 0.395 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.424 |\n", + "| explained_variance | 0.564 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0748 |\n", + "| n_updates | 940 |\n", + "| policy_gradient_loss | -0.0693 |\n", + "| value_loss | 0.054 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 551 |\n", + "| ep_rew_mean | 7.28 |\n", + "| time/ | |\n", + "| fps | 144 |\n", + "| iterations | 96 |\n", + "| time_elapsed | 1365 |\n", + "| total_timesteps | 196608 |\n", + "| train/ | |\n", + "| approx_kl | 0.32080528 |\n", + "| clip_fraction | 0.407 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.427 |\n", + "| explained_variance | 0.655 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0888 |\n", + "| n_updates | 950 |\n", + "| policy_gradient_loss | -0.0691 |\n", + "| value_loss | 0.0537 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 555 |\n", + "| ep_rew_mean | 7.35 |\n", + "| time/ | |\n", + "| fps | 144 |\n", + "| iterations | 97 |\n", + "| time_elapsed | 1379 |\n", + "| total_timesteps | 198656 |\n", + "| train/ | |\n", + "| approx_kl | 0.32273126 |\n", + "| clip_fraction | 0.402 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.415 |\n", + "| explained_variance | 0.661 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0978 |\n", + "| n_updates | 960 |\n", + "| policy_gradient_loss | -0.0697 |\n", + "| value_loss | 0.0717 |\n", + "----------------------------------------\n", + "----------------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 552 |\n", + "| ep_rew_mean | 7.29 |\n", + "| time/ | |\n", + "| fps | 143 |\n", + "| iterations | 98 |\n", + "| time_elapsed | 1394 |\n", + "| total_timesteps | 200704 |\n", + "| train/ | |\n", + "| approx_kl | 0.36426872 |\n", + "| clip_fraction | 0.414 |\n", + "| clip_range | 0.2 |\n", + "| entropy_loss | -0.409 |\n", + "| explained_variance | 0.668 |\n", + "| learning_rate | 0.0003 |\n", + "| loss | -0.0927 |\n", + "| n_updates | 970 |\n", + "| policy_gradient_loss | -0.0718 |\n", + "| value_loss | 0.0621 |\n", + "----------------------------------------\n" + ] + } + ], + "source": [ + "train_experiment(algo_list, env_name, 200000, models_records)" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "0580187d", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "dict_keys(['DQN', 'A2C', 'PPO'])" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "models_records.keys()" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.0" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/1b_Breakout-v0-Evaluate.ipynb b/1b_Breakout-v0-Evaluate.ipynb new file mode 100644 index 0000000..0343de4 --- /dev/null +++ b/1b_Breakout-v0-Evaluate.ipynb @@ -0,0 +1,261 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "7d1fa20c", + "metadata": {}, + "outputs": [], + "source": [ + "import os, sys\n", + "import gc\n", + "import matplotlib.pyplot as plt\n", + "import numpy as np" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "65a74373", + "metadata": {}, + "outputs": [], + "source": [ + "sys.path.append('../')\n", + "import torch" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "c8c767df", + "metadata": {}, + "outputs": [], + "source": [ + "from get_algos import get_all_algos , run_experiment ,call_paths, plot_mean" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "c9fc3531", + "metadata": {}, + "outputs": [], + "source": [ + "import gym\n", + "from gym.wrappers import Monitor\n", + "from stable_baselines3 import PPO, A2C, DDPG, DQN, SAC, TD3\n", + "from stable_baselines3.common.vec_env import VecFrameStack\n", + "from stable_baselines3.common.evaluation import evaluate_policy\n", + "from stable_baselines3.common.env_util import make_atari_env" + ] + }, + { + "cell_type": "markdown", + "id": "e1d33e3c", + "metadata": {}, + "source": [ + "### 1. Explore breakout environment\n", + "" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "1aad3196", + "metadata": {}, + "outputs": [], + "source": [ + "env_name='Breakout-v0'\n", + "env=make_atari_env(env_name)\n", + "env=VecFrameStack(env,n_stack=6)" + ] + }, + { + "cell_type": "markdown", + "id": "54c5cdd5", + "metadata": {}, + "source": [ + "### 2. Evaluation\n", + "
    \n", + "
  1. Create the environment
  2. \n", + "
  3. For each algorithm:
  4. \n", + "
    1. Load the model
    2. \n", + "
    3. Evaluate the model for 5 sample iterations
    4. \n", + "
    5. Output the score for each algo and each iteration
    6. \n", + "
    7. Assess stability of the model based on the variance / standard deviation
    8. \n", + "
    \n", + "
  5. Plot the corresponding scores
  6. \n", + "
" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "65fae03b", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['PPO', 'A2C', 'DQN']\n" + ] + } + ], + "source": [ + "algo_list=get_all_algos(gym.make(env_name))\n", + "print(algo_list)" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "52178f03", + "metadata": {}, + "outputs": [], + "source": [ + "def evaluate_experiment(algo_list, env_name,n_steps=200000,n_episodes=100):\n", + " rewards_mean={}\n", + " rewards_std={}\n", + " for algo_name in reversed(algo_list):\n", + " env=make_atari_env(env_name)\n", + " env=VecFrameStack(env, n_stack=6)\n", + " print('******* Evaluating', algo_name,' *******')\n", + " device='cpu' if algo_name=='DQN' else 'cuda'\n", + " log_path, render_path, model_path=call_paths(algo_name,env_name,n_steps)\n", + " model_name=env_name+\"_\"+algo_name+\"_model\"\n", + " model=eval(algo_name).load(os.path.join(model_path,model_name),env,device=device)\n", + " mean_rew, mean_std=evaluate_policy(model,env, n_eval_episodes=n_episodes)\n", + " rewards_mean[algo_name]=mean_rew\n", + " rewards_std[algo_name]=mean_std\n", + " print('Mean rewards for ',n_episodes, ' episodes of ',algo_name,' is ',mean_rew,'\\n')\n", + " del model\n", + " env.close()\n", + " return rewards_mean,rewards_std" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "66a2bd41", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "******* Evaluating DQN *******\n", + "Wrapping the env in a VecTransposeImage.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "E:\\Anaconda\\envs\\ai_gym\\lib\\site-packages\\stable_baselines3\\common\\buffers.py:229: UserWarning: This system does not have apparently enough memory to store the complete replay buffer 84.69GB > 11.52GB\n", + " \"This system does not have apparently enough memory to store the complete \"\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Mean rewards for 100 episodes of DQN is 9.13 \n", + "\n", + "******* Evaluating A2C *******\n", + "Wrapping the env in a VecTransposeImage.\n", + "Mean rewards for 100 episodes of A2C is 8.62 \n", + "\n", + "******* Evaluating PPO *******\n", + "Wrapping the env in a VecTransposeImage.\n", + "Mean rewards for 100 episodes of PPO is 7.93 \n", + "\n" + ] + } + ], + "source": [ + "rewards=evaluate_experiment(algo_list, env_name)" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "0a4d7aa0", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plot_mean(rewards[0],'mean rewards')" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "46b5aa97", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plot_mean(rewards[1],'std deviation')" + ] + }, + { + "cell_type": "markdown", + "id": "719d552f", + "metadata": {}, + "source": [ + "Hence, we see that while DQN has the highest average reward, it also has the second highest standard deviation:\n", + "
  1. 6% higher reward than A2C but 0.96 the std deviation
  2. \n", + "
  3. 15% higher reward than PPO but 122% the std deviation
  4. \n", + "
  5. Similarly, A2C has 9% higher reward than PPO but 1.3X its std deviation
  6. " + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.0" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/1c_Breakout-v0-Test.ipynb b/1c_Breakout-v0-Test.ipynb new file mode 100644 index 0000000..75a02a8 --- /dev/null +++ b/1c_Breakout-v0-Test.ipynb @@ -0,0 +1,235 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "7d1fa20c", + "metadata": {}, + "outputs": [], + "source": [ + "import os, sys\n", + "import gc\n", + "import matplotlib.pyplot as plt\n", + "import numpy as np" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "32bb66c4", + "metadata": {}, + "outputs": [], + "source": [ + "sys.path.append('../')\n", + "import torch" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "c8c767df", + "metadata": {}, + "outputs": [], + "source": [ + "from get_algos import get_all_algos , run_experiment ,call_paths, plot_mean" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "c9fc3531", + "metadata": {}, + "outputs": [], + "source": [ + "import gym\n", + "# from gym.wrappers import Monitor\n", + "from stable_baselines3 import PPO, A2C, DDPG, DQN, SAC, TD3\n", + "from stable_baselines3.common.vec_env import VecFrameStack,VecVideoRecorder\n", + "from stable_baselines3.common.evaluation import evaluate_policy\n", + "from stable_baselines3.common.env_util import make_atari_env\n", + "from stable_baselines3.common.monitor import Monitor" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "b1e1b76a", + "metadata": {}, + "outputs": [], + "source": [ + "env_name='Breakout-v0'" + ] + }, + { + "cell_type": "markdown", + "id": "54c5cdd5", + "metadata": {}, + "source": [ + "### 2. Testing\n", + "
      \n", + "
    1. Create the environment
    2. \n", + "
    3. For each algorithm:
    4. \n", + "
      1. Load the model
      2. \n", + "
      3. Evaluate the model for 5 sample iterations
      4. \n", + "
      5. Output the score for each algo and each iteration
      6. \n", + "
      7. Save renders of the output
      8. \n", + "
      \n", + "
    " + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "65fae03b", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['PPO', 'A2C', 'DQN']\n" + ] + } + ], + "source": [ + "algo_list=get_all_algos(gym.make(env_name))\n", + "print(algo_list)" + ] + }, + { + "cell_type": "markdown", + "id": "7e8fab60", + "metadata": {}, + "source": [ + "### 3. Testing" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "972110da", + "metadata": {}, + "outputs": [], + "source": [ + "def testing_model(algo_list, env_name,n_steps,vid_length):\n", + " total_rewards={}\n", + " for algo_name in reversed(algo_list):\n", + " algo_rewards=[]\n", + " device='cpu' if algo_name=='DQN' else 'cuda'\n", + " log_path, render_path, model_path=call_paths(algo_name,env_name,n_steps)\n", + " env=VecVideoRecorder(VecFrameStack(make_atari_env(env_name,monitor_dir=render_path),n_stack=6),render_path,record_video_trigger=lambda step: step == 0,video_length=vid_length)\n", + " model_name=env_name+\"_\"+algo_name+\"_model\"\n", + " model=eval(algo_name).load(os.path.join(model_path, model_name),env,device=device)\n", + " for i in range(5):\n", + " state=env.reset()\n", + " epi_rewards=0\n", + " while True:\n", + " action,_=model.predict(state)\n", + " state,reward,done,_=env.step(action)\n", + " epi_rewards+=reward[0]\n", + " env.render()\n", + " if done:\n", + " algo_rewards.append(epi_rewards)\n", + " break\n", + " total_rewards[algo_name]=algo_rewards\n", + " del model\n", + " env.close()\n", + " return total_rewards" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "2f2d2d60", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Wrapping the env in a VecTransposeImage.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "E:\\Anaconda\\envs\\ai_gym\\lib\\site-packages\\stable_baselines3\\common\\buffers.py:229: UserWarning: This system does not have apparently enough memory to store the complete replay buffer 84.69GB > 11.00GB\n", + " \"This system does not have apparently enough memory to store the complete \"\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Wrapping the env in a VecTransposeImage.\n", + "Wrapping the env in a VecTransposeImage.\n" + ] + } + ], + "source": [ + "test=total_rewards=testing_model(algo_list, env_name,n_steps=200000,vid_length=1000)" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "63f6b45f", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'DQN': [0.0, 0.0, 0.0, 5.0, 0.0],\n", + " 'A2C': [4.0, 0.0, 0.0, 0.0, 0.0],\n", + " 'PPO': [3.0, 0.0, 0.0, 3.0, 0.0]}" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "test" + ] + }, + { + "cell_type": "markdown", + "id": "870561de", + "metadata": {}, + "source": [ + "We see that PPO seems to consistently provide rewards with the highest average reward. Hence, we will use PPO as the algorithm for subsequent training of 5,000,000 steps" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "13d01daf", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.0" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/2a_Breakout-v0_recurrent_train.ipynb b/2a_Breakout-v0_recurrent_train.ipynb new file mode 100644 index 0000000..1564f5c --- /dev/null +++ b/2a_Breakout-v0_recurrent_train.ipynb @@ -0,0 +1,65703 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "7d1fa20c", + "metadata": {}, + "outputs": [], + "source": [ + "import os, sys\n", + "import gc\n", + "import matplotlib.pyplot as plt\n", + "import numpy as np" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "14af36c4", + "metadata": {}, + "outputs": [], + "source": [ + "sys.path.append('../')\n", + "import torch" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "c8c767df", + "metadata": {}, + "outputs": [], + "source": [ + "from get_algos import get_all_algos , run_experiment ,create_paths, get_action_type_name" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "c9fc3531", + "metadata": {}, + "outputs": [], + "source": [ + "import gym\n", + "from sb3_contrib import QRDQN ,RecurrentPPO,TRPO \n", + "from stable_baselines3.common.vec_env import VecFrameStack\n", + "from stable_baselines3.common.env_util import make_atari_env" + ] + }, + { + "cell_type": "markdown", + "id": "e1d33e3c", + "metadata": {}, + "source": [ + "### 1. Explore breakout environment\n", + "
      \n", + "
    • Explore the environment
    • \n", + "
    " + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "1aad3196", + "metadata": {}, + "outputs": [], + "source": [ + "env_name='Breakout-v0'\n", + "env=gym.make(env_name)" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "id": "df2cd276", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Action space: Discrete(4)\n", + "Observation space shape: Box([[[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " ...\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]], [[[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " ...\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]], (210, 160, 3), uint8)\n", + "Action space shape: ()\n", + "Observation space shape: (210, 160, 3)\n" + ] + } + ], + "source": [ + "print('Action space: ',env.action_space)\n", + "print('Observation space shape: ',env.observation_space)\n", + "print('Action space shape: ',env.action_space.shape)\n", + "print('Observation space shape: ',env.observation_space.shape)" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "id": "a837072d", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "E:\\Anaconda\\envs\\ai_gym\\lib\\site-packages\\gym\\envs\\atari\\environment.py:269: UserWarning: \u001b[33mWARN: We strongly suggest supplying `render_mode` when constructing your environment, e.g., gym.make(ID, render_mode='human'). Using `render_mode` provides access to proper scaling, audio support, and proper framerates.\u001b[0m\n", + " \"We strongly suggest supplying `render_mode` when \"\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Episode: 5 Reward: 4.0\n", + "Episode: 10 Reward: 1.0\n", + "Episode: 15 Reward: 1.0\n", + "Episode: 20 Reward: 1.0\n", + "Episode: 25 Reward: 5.0\n", + "Episode: 30 Reward: 1.0\n", + "Episode: 35 Reward: 0.0\n", + "Episode: 40 Reward: 1.0\n", + "Episode: 45 Reward: 0.0\n", + "Episode: 50 Reward: 1.0\n", + "Average rewards for random action Breakout-v0 is: 1.36\n" + ] + } + ], + "source": [ + "#Taking a look at how breakout looks and simulate random actions\n", + "env.reset()\n", + "rewards_all=[]\n", + "for epi in range(50):\n", + " state=env.reset()\n", + " rewards=0\n", + " while True:\n", + " action=env.action_space.sample()\n", + " state,reward,done,_=env.step(action)\n", + " env.render()\n", + " rewards+=reward\n", + " if done:\n", + " rewards_all.append(rewards)\n", + " if (epi+1)%5==0:\n", + " print('Episode: ',epi+1,' Reward: ',rewards)\n", + " break \n", + "env.close()\n", + "print('Average rewards for random action Breakout-v0 is: ',sum(rewards_all)/len(rewards_all))" + ] + }, + { + "cell_type": "markdown", + "id": "54c5cdd5", + "metadata": {}, + "source": [ + "### 2. Training\n", + "
      \n", + "
    1. Make the atari env using make_atari_env
    2. \n", + "
    3. Parallelize the learning using VecFrameStack
    4. \n", + "
    5. Create train function for all appropriate algos
    6. \n", + "
    7. Train
    8. \n", + "
    9. Store model
    10. \n", + "
    " + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "1b3fb6a8", + "metadata": {}, + "outputs": [], + "source": [ + "env_recurrent_type={'Discrete':['MaskablePPO', 'QRDQN', 'RecurrentPPO', 'TRPO'],'Box':['ARS', 'RecurrentPPO', 'TQC', 'TRPO'], \n", + " 'MultiDiscrete':['MaskablePPO', 'RecurrentPPO', 'TRPO'],'MultiBinary':['MaskablePPO', 'RecurrentPPO', 'TRPO']}\n", + "def get_algo_recurrent(env):\n", + " act_space=str(type(env.action_space)).split('.')[3].split(\"'\")[0]\n", + " return env_recurrent_type[act_space]\n", + " " + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "1f221195", + "metadata": {}, + "outputs": [], + "source": [ + "algo_list=get_algo_recurrent(gym.make(env_name))\n", + "print(algo_list)\n", + "if 'MaskablePPO' in algo_list:\n", + " algo_list.remove('MaskablePPO')" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "00e701da", + "metadata": {}, + "outputs": [], + "source": [ + "def train_breakout(algo_name, env_name,n_steps,device='cuda'):\n", + " if algo_name =='QRDQN' or 'TRPO':\n", + " device='cpu'\n", + " else:\n", + " device='cuda' #GPU was unable to load the entire experience relay so moved to virtual memory on disk\n", + " policy='CnnLstmPolicy' if algo_name=='RecurrentPPO' else 'CnnPolicy' \n", + " log_path, render_path, model_path=create_paths(algo_name,env_name,n_steps)\n", + " env=make_atari_env(env_name,n_envs=6,seed=0)\n", + " env=VecFrameStack(env, n_stack=6)\n", + " model=eval(algo_name)(policy,env, tensorboard_log=log_path,verbose=1,device=device)\n", + " model.learn(n_steps,)\n", + " model.save(os.path.join(model_path,env_name+\"_\"+algo_name+\"_\"+\"model\"))\n", + " del model\n", + " env.close()\n", + " gc.collect()\n", + " torch.cuda.empty_cache()\n", + "\n", + " return log_path, render_path, model_path" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "ebcf18c9", + "metadata": {}, + "outputs": [], + "source": [ + "models_records={}\n", + "n_steps=200000\n", + "env_name='Breakout-v0'" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "52178f03", + "metadata": {}, + "outputs": [], + "source": [ + "def train_experiment(algo_list, env_name,n_steps, models_records):\n", + " for algo in reversed(algo_list):\n", + " model_record={}\n", + " train_breakout(algo, env_name,n_steps)" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "0a4d7aa0", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Using cpu device\n", + "Wrapping the env in a VecTransposeImage.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "E:\\Anaconda\\envs\\ai_gym\\lib\\site-packages\\stable_baselines3\\common\\buffers.py:229: UserWarning: This system does not have apparently enough memory to store the complete replay buffer 84.69GB > 12.96GB\n", + " \"This system does not have apparently enough memory to store the complete \"\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Logging to Breakout-v0\\QRDQN_200000\\logs\\QRDQN_1\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| exploration_rate | 0.958 |\n", + "| time/ | |\n", + "| episodes | 4 |\n", + "| fps | 151 |\n", + "| time_elapsed | 0 |\n", + "| total_timesteps | 42 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| exploration_rate | 0.923 |\n", + "| time/ | |\n", + "| episodes | 8 |\n", + "| fps | 212 |\n", + "| time_elapsed | 0 |\n", + "| total_timesteps | 78 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| exploration_rate | 0.881 |\n", + "| time/ | |\n", + "| episodes | 12 |\n", + "| fps | 257 |\n", + "| time_elapsed | 0 |\n", + "| total_timesteps | 120 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| exploration_rate | 0.851 |\n", + "| time/ | |\n", + "| episodes | 16 |\n", + "| fps | 280 |\n", + "| time_elapsed | 0 |\n", + "| total_timesteps | 150 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 212 |\n", + "| ep_rew_mean | 0 |\n", + "| exploration_rate | 0.792 |\n", + "| time/ | |\n", + "| episodes | 20 |\n", + "| fps | 308 |\n", + "| time_elapsed | 0 |\n", + "| total_timesteps | 210 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 212 |\n", + "| ep_rew_mean | 0 |\n", + "| exploration_rate | 0.756 |\n", + "| time/ | |\n", + "| episodes | 24 |\n", + "| fps | 308 |\n", + "| time_elapsed | 0 |\n", + "| total_timesteps | 246 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 246 |\n", + "| ep_rew_mean | 0.75 |\n", + "| exploration_rate | 0.721 |\n", + "| time/ | |\n", + "| episodes | 28 |\n", + "| fps | 308 |\n", + "| time_elapsed | 0 |\n", + "| total_timesteps | 282 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 246 |\n", + "| ep_rew_mean | 0.75 |\n", + "| exploration_rate | 0.65 |\n", + "| time/ | |\n", + "| episodes | 32 |\n", + "| fps | 327 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 354 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 238 |\n", + "| ep_rew_mean | 0.6 |\n", + "| exploration_rate | 0.584 |\n", + "| time/ | |\n", + "| episodes | 36 |\n", + "| fps | 344 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 420 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.549 |\n", + "| time/ | |\n", + "| episodes | 40 |\n", + "| fps | 338 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 456 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.501 |\n", + "| time/ | |\n", + "| episodes | 44 |\n", + "| fps | 342 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 504 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.459 |\n", + "| time/ | |\n", + "| episodes | 48 |\n", + "| fps | 346 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 546 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.43 |\n", + "| time/ | |\n", + "| episodes | 52 |\n", + "| fps | 345 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 576 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.4 |\n", + "| time/ | |\n", + "| episodes | 56 |\n", + "| fps | 346 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 606 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.37 |\n", + "| time/ | |\n", + "| episodes | 60 |\n", + "| fps | 346 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 636 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.335 |\n", + "| time/ | |\n", + "| episodes | 64 |\n", + "| fps | 347 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 672 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.323 |\n", + "| time/ | |\n", + "| episodes | 68 |\n", + "| fps | 344 |\n", + "| time_elapsed | 1 |\n", + "| total_timesteps | 684 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.281 |\n", + "| time/ | |\n", + "| episodes | 72 |\n", + "| fps | 345 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 726 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.257 |\n", + "| time/ | |\n", + "| episodes | 76 |\n", + "| fps | 342 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 750 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.13 |\n", + "| exploration_rate | 0.216 |\n", + "| time/ | |\n", + "| episodes | 80 |\n", + "| fps | 342 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 792 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.13 |\n", + "| exploration_rate | 0.18 |\n", + "| time/ | |\n", + "| episodes | 84 |\n", + "| fps | 344 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 828 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.13 |\n", + "| exploration_rate | 0.139 |\n", + "| time/ | |\n", + "| episodes | 88 |\n", + "| fps | 347 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 870 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.13 |\n", + "| exploration_rate | 0.0734 |\n", + "| time/ | |\n", + "| episodes | 92 |\n", + "| fps | 353 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 936 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.06 |\n", + "| exploration_rate | 0.0377 |\n", + "| time/ | |\n", + "| episodes | 96 |\n", + "| fps | 353 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 972 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 100 |\n", + "| fps | 353 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 1008 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 104 |\n", + "| fps | 353 |\n", + "| time_elapsed | 2 |\n", + "| total_timesteps | 1044 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 108 |\n", + "| fps | 351 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1080 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 112 |\n", + "| fps | 354 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1116 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 116 |\n", + "| fps | 355 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1152 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 120 |\n", + "| fps | 355 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1194 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 124 |\n", + "| fps | 355 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1224 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 128 |\n", + "| fps | 352 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 132 |\n", + "| fps | 351 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1272 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 136 |\n", + "| fps | 353 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1320 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 140 |\n", + "| fps | 354 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1368 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 144 |\n", + "| fps | 353 |\n", + "| time_elapsed | 3 |\n", + "| total_timesteps | 1404 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 148 |\n", + "| fps | 352 |\n", + "| time_elapsed | 4 |\n", + "| total_timesteps | 1434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 152 |\n", + "| fps | 354 |\n", + "| time_elapsed | 4 |\n", + "| total_timesteps | 1494 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 156 |\n", + "| fps | 355 |\n", + "| time_elapsed | 4 |\n", + "| total_timesteps | 1554 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 160 |\n", + "| fps | 355 |\n", + "| time_elapsed | 4 |\n", + "| total_timesteps | 1596 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 164 |\n", + "| fps | 355 |\n", + "| time_elapsed | 4 |\n", + "| total_timesteps | 1632 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 168 |\n", + "| fps | 355 |\n", + "| time_elapsed | 4 |\n", + "| total_timesteps | 1674 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 172 |\n", + "| fps | 354 |\n", + "| time_elapsed | 4 |\n", + "| total_timesteps | 1716 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 176 |\n", + "| fps | 356 |\n", + "| time_elapsed | 4 |\n", + "| total_timesteps | 1770 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 180 |\n", + "| fps | 356 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 1824 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 184 |\n", + "| fps | 356 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 1860 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 188 |\n", + "| fps | 355 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 1896 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 192 |\n", + "| fps | 356 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 1932 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 196 |\n", + "| fps | 356 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 1974 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 200 |\n", + "| fps | 355 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 2010 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 204 |\n", + "| fps | 355 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 2022 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 208 |\n", + "| fps | 356 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 2070 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 212 |\n", + "| fps | 356 |\n", + "| time_elapsed | 5 |\n", + "| total_timesteps | 2124 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 216 |\n", + "| fps | 356 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2178 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 220 |\n", + "| fps | 356 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2220 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 224 |\n", + "| fps | 357 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2250 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 228 |\n", + "| fps | 359 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2316 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 232 |\n", + "| fps | 358 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2346 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 236 |\n", + "| fps | 358 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2388 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 240 |\n", + "| fps | 359 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2430 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 244 |\n", + "| fps | 359 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2472 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 248 |\n", + "| fps | 361 |\n", + "| time_elapsed | 6 |\n", + "| total_timesteps | 2526 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 252 |\n", + "| fps | 361 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2574 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 256 |\n", + "| fps | 362 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2610 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 260 |\n", + "| fps | 361 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2652 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 264 |\n", + "| fps | 361 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2706 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.27 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 268 |\n", + "| fps | 361 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2742 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 272 |\n", + "| fps | 362 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2802 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.25 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 276 |\n", + "| fps | 363 |\n", + "| time_elapsed | 7 |\n", + "| total_timesteps | 2874 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.28 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 280 |\n", + "| fps | 364 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 2934 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 284 |\n", + "| fps | 363 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 2988 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 288 |\n", + "| fps | 363 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 3030 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 292 |\n", + "| fps | 363 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 3060 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 296 |\n", + "| fps | 363 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 3096 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 300 |\n", + "| fps | 363 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 3114 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 304 |\n", + "| fps | 362 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 3144 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 308 |\n", + "| fps | 361 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 3174 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 312 |\n", + "| fps | 362 |\n", + "| time_elapsed | 8 |\n", + "| total_timesteps | 3228 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 316 |\n", + "| fps | 361 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3264 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 320 |\n", + "| fps | 362 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3312 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 324 |\n", + "| fps | 362 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3354 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 328 |\n", + "| fps | 363 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3408 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 332 |\n", + "| fps | 362 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3432 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 336 |\n", + "| fps | 363 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3474 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 340 |\n", + "| fps | 364 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3540 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 344 |\n", + "| fps | 364 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3576 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 348 |\n", + "| fps | 363 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3588 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 352 |\n", + "| fps | 364 |\n", + "| time_elapsed | 9 |\n", + "| total_timesteps | 3624 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 356 |\n", + "| fps | 364 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3702 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 360 |\n", + "| fps | 364 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3720 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 364 |\n", + "| fps | 364 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3756 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 368 |\n", + "| fps | 364 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3798 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 372 |\n", + "| fps | 363 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3828 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 376 |\n", + "| fps | 363 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3858 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 380 |\n", + "| fps | 364 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3918 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 384 |\n", + "| fps | 365 |\n", + "| time_elapsed | 10 |\n", + "| total_timesteps | 3978 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 388 |\n", + "| fps | 363 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 4014 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 392 |\n", + "| fps | 364 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 4050 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 396 |\n", + "| fps | 365 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 4122 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 400 |\n", + "| fps | 366 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 4200 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 404 |\n", + "| fps | 366 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 4236 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 408 |\n", + "| fps | 367 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 4314 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 412 |\n", + "| fps | 367 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 4356 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 416 |\n", + "| fps | 368 |\n", + "| time_elapsed | 11 |\n", + "| total_timesteps | 4416 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 420 |\n", + "| fps | 369 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4512 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 424 |\n", + "| fps | 369 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4554 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 428 |\n", + "| fps | 370 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4632 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 432 |\n", + "| fps | 370 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4668 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 436 |\n", + "| fps | 369 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4704 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 440 |\n", + "| fps | 369 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4740 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 444 |\n", + "| fps | 370 |\n", + "| time_elapsed | 12 |\n", + "| total_timesteps | 4800 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 448 |\n", + "| fps | 370 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 4842 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 452 |\n", + "| fps | 370 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 4884 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 456 |\n", + "| fps | 370 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 4914 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 460 |\n", + "| fps | 370 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 4944 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 464 |\n", + "| fps | 369 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 4986 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 468 |\n", + "| fps | 369 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 5028 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 472 |\n", + "| fps | 369 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 5070 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 476 |\n", + "| fps | 369 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 5088 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 480 |\n", + "| fps | 369 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 5106 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 484 |\n", + "| fps | 369 |\n", + "| time_elapsed | 13 |\n", + "| total_timesteps | 5136 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 488 |\n", + "| fps | 369 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 5172 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 492 |\n", + "| fps | 368 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 5214 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 496 |\n", + "| fps | 368 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 5250 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 500 |\n", + "| fps | 370 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 5340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 504 |\n", + "| fps | 369 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 5376 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 508 |\n", + "| fps | 369 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 5400 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 512 |\n", + "| fps | 370 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 5478 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 516 |\n", + "| fps | 371 |\n", + "| time_elapsed | 14 |\n", + "| total_timesteps | 5544 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 520 |\n", + "| fps | 371 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5586 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 524 |\n", + "| fps | 371 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5640 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 528 |\n", + "| fps | 371 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5682 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 532 |\n", + "| fps | 371 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5706 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 536 |\n", + "| fps | 372 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 540 |\n", + "| fps | 371 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5784 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 544 |\n", + "| fps | 371 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5862 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 548 |\n", + "| fps | 372 |\n", + "| time_elapsed | 15 |\n", + "| total_timesteps | 5898 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 552 |\n", + "| fps | 372 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 5988 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 556 |\n", + "| fps | 373 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 6048 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 560 |\n", + "| fps | 373 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 6072 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 564 |\n", + "| fps | 372 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 6096 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 568 |\n", + "| fps | 372 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 6180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 572 |\n", + "| fps | 372 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 6228 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 576 |\n", + "| fps | 373 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 6270 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 580 |\n", + "| fps | 373 |\n", + "| time_elapsed | 16 |\n", + "| total_timesteps | 6306 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 584 |\n", + "| fps | 373 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 6360 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 588 |\n", + "| fps | 373 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 6402 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 592 |\n", + "| fps | 373 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 6444 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 596 |\n", + "| fps | 373 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 6480 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 600 |\n", + "| fps | 373 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 6522 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 604 |\n", + "| fps | 372 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 6528 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 608 |\n", + "| fps | 372 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 6564 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 612 |\n", + "| fps | 373 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 6594 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 616 |\n", + "| fps | 373 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 6630 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 620 |\n", + "| fps | 372 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 6666 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 624 |\n", + "| fps | 372 |\n", + "| time_elapsed | 17 |\n", + "| total_timesteps | 6702 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 628 |\n", + "| fps | 372 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 6744 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 632 |\n", + "| fps | 372 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 6798 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 636 |\n", + "| fps | 372 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 6840 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 640 |\n", + "| fps | 372 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 6864 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 644 |\n", + "| fps | 372 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 6924 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 648 |\n", + "| fps | 373 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 6984 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 652 |\n", + "| fps | 373 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 7020 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 656 |\n", + "| fps | 373 |\n", + "| time_elapsed | 18 |\n", + "| total_timesteps | 7050 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 660 |\n", + "| fps | 373 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 7122 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 664 |\n", + "| fps | 373 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 7164 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 668 |\n", + "| fps | 373 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 7194 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 672 |\n", + "| fps | 373 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 7248 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 676 |\n", + "| fps | 373 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 7326 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 680 |\n", + "| fps | 374 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 7362 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 684 |\n", + "| fps | 374 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 7398 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 688 |\n", + "| fps | 374 |\n", + "| time_elapsed | 19 |\n", + "| total_timesteps | 7446 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 692 |\n", + "| fps | 373 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 7482 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 696 |\n", + "| fps | 373 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 7512 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 700 |\n", + "| fps | 373 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 7548 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 704 |\n", + "| fps | 373 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 7596 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 708 |\n", + "| fps | 373 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 7638 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 712 |\n", + "| fps | 373 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 7704 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 716 |\n", + "| fps | 373 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 7752 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 720 |\n", + "| fps | 373 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 7800 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 724 |\n", + "| fps | 373 |\n", + "| time_elapsed | 20 |\n", + "| total_timesteps | 7836 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 728 |\n", + "| fps | 373 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 7878 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 732 |\n", + "| fps | 372 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 7914 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 736 |\n", + "| fps | 373 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 8028 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 740 |\n", + "| fps | 373 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 8052 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 744 |\n", + "| fps | 373 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 8082 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 748 |\n", + "| fps | 373 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 8106 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 752 |\n", + "| fps | 373 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 8142 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 756 |\n", + "| fps | 373 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 8172 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 760 |\n", + "| fps | 373 |\n", + "| time_elapsed | 21 |\n", + "| total_timesteps | 8202 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 764 |\n", + "| fps | 372 |\n", + "| time_elapsed | 22 |\n", + "| total_timesteps | 8226 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 768 |\n", + "| fps | 372 |\n", + "| time_elapsed | 22 |\n", + "| total_timesteps | 8262 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 772 |\n", + "| fps | 372 |\n", + "| time_elapsed | 22 |\n", + "| total_timesteps | 8310 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 776 |\n", + "| fps | 373 |\n", + "| time_elapsed | 22 |\n", + "| total_timesteps | 8382 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 780 |\n", + "| fps | 373 |\n", + "| time_elapsed | 22 |\n", + "| total_timesteps | 8424 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 784 |\n", + "| fps | 373 |\n", + "| time_elapsed | 22 |\n", + "| total_timesteps | 8478 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 788 |\n", + "| fps | 373 |\n", + "| time_elapsed | 22 |\n", + "| total_timesteps | 8520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 792 |\n", + "| fps | 373 |\n", + "| time_elapsed | 22 |\n", + "| total_timesteps | 8556 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 796 |\n", + "| fps | 373 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 8586 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 800 |\n", + "| fps | 372 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 8598 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 804 |\n", + "| fps | 373 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 8664 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 808 |\n", + "| fps | 373 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 8724 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 812 |\n", + "| fps | 373 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 8772 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 816 |\n", + "| fps | 373 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 8796 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 820 |\n", + "| fps | 373 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 8850 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 824 |\n", + "| fps | 373 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 8904 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 828 |\n", + "| fps | 373 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 8922 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 832 |\n", + "| fps | 373 |\n", + "| time_elapsed | 23 |\n", + "| total_timesteps | 8964 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 836 |\n", + "| fps | 373 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 9024 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 840 |\n", + "| fps | 374 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 9102 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 844 |\n", + "| fps | 374 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 9138 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 848 |\n", + "| fps | 374 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 9180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 852 |\n", + "| fps | 374 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 9216 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 856 |\n", + "| fps | 373 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 9246 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 860 |\n", + "| fps | 373 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 9282 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 864 |\n", + "| fps | 373 |\n", + "| time_elapsed | 24 |\n", + "| total_timesteps | 9318 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 868 |\n", + "| fps | 373 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 9354 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 872 |\n", + "| fps | 373 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 9396 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 876 |\n", + "| fps | 373 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 9426 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 880 |\n", + "| fps | 372 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 9456 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 884 |\n", + "| fps | 372 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 9486 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 888 |\n", + "| fps | 372 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 9540 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 892 |\n", + "| fps | 372 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 9582 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 896 |\n", + "| fps | 372 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 9618 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 900 |\n", + "| fps | 372 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 9666 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 904 |\n", + "| fps | 372 |\n", + "| time_elapsed | 25 |\n", + "| total_timesteps | 9696 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 908 |\n", + "| fps | 372 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 9732 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 912 |\n", + "| fps | 372 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 9780 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 916 |\n", + "| fps | 373 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 9840 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 920 |\n", + "| fps | 373 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 9876 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 924 |\n", + "| fps | 373 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 9912 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 928 |\n", + "| fps | 373 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 9984 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 932 |\n", + "| fps | 373 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 10008 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 936 |\n", + "| fps | 374 |\n", + "| time_elapsed | 26 |\n", + "| total_timesteps | 10098 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 940 |\n", + "| fps | 374 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 10158 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 944 |\n", + "| fps | 374 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 10218 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 948 |\n", + "| fps | 374 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 10272 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 952 |\n", + "| fps | 374 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 10326 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 956 |\n", + "| fps | 375 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 10404 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 960 |\n", + "| fps | 375 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 10446 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 964 |\n", + "| fps | 375 |\n", + "| time_elapsed | 27 |\n", + "| total_timesteps | 10488 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 968 |\n", + "| fps | 375 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 10518 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 972 |\n", + "| fps | 374 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 10560 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 976 |\n", + "| fps | 374 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 10602 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 980 |\n", + "| fps | 374 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 10638 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 984 |\n", + "| fps | 374 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 10674 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 988 |\n", + "| fps | 374 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 10710 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 992 |\n", + "| fps | 374 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 10722 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 996 |\n", + "| fps | 374 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 10752 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1000 |\n", + "| fps | 374 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 10788 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1004 |\n", + "| fps | 373 |\n", + "| time_elapsed | 28 |\n", + "| total_timesteps | 10812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1008 |\n", + "| fps | 374 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 10848 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1012 |\n", + "| fps | 373 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 10884 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1016 |\n", + "| fps | 374 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 10920 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1020 |\n", + "| fps | 373 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 10950 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1024 |\n", + "| fps | 374 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 11010 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1028 |\n", + "| fps | 374 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 11082 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1032 |\n", + "| fps | 374 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 11118 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1036 |\n", + "| fps | 374 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 11160 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1040 |\n", + "| fps | 373 |\n", + "| time_elapsed | 29 |\n", + "| total_timesteps | 11184 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1044 |\n", + "| fps | 374 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 11244 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1048 |\n", + "| fps | 374 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 11298 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1052 |\n", + "| fps | 374 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 11364 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1056 |\n", + "| fps | 374 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 11400 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1060 |\n", + "| fps | 374 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 11454 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1064 |\n", + "| fps | 374 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 11496 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1068 |\n", + "| fps | 374 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 11550 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1072 |\n", + "| fps | 374 |\n", + "| time_elapsed | 30 |\n", + "| total_timesteps | 11586 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1076 |\n", + "| fps | 374 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 11652 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1080 |\n", + "| fps | 374 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 11694 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1084 |\n", + "| fps | 374 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 11730 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1088 |\n", + "| fps | 374 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 11784 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1092 |\n", + "| fps | 374 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 11856 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1096 |\n", + "| fps | 374 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 11904 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1100 |\n", + "| fps | 374 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 11946 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1104 |\n", + "| fps | 375 |\n", + "| time_elapsed | 31 |\n", + "| total_timesteps | 11994 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1108 |\n", + "| fps | 375 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 12036 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1112 |\n", + "| fps | 375 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 12078 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1116 |\n", + "| fps | 375 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 12114 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1120 |\n", + "| fps | 374 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 12156 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1124 |\n", + "| fps | 374 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 12198 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1128 |\n", + "| fps | 375 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 12222 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1132 |\n", + "| fps | 374 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 12240 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1136 |\n", + "| fps | 375 |\n", + "| time_elapsed | 32 |\n", + "| total_timesteps | 12360 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1140 |\n", + "| fps | 375 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 12402 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1144 |\n", + "| fps | 375 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 12444 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1148 |\n", + "| fps | 375 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 12480 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1152 |\n", + "| fps | 375 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 12522 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1156 |\n", + "| fps | 375 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 12546 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1160 |\n", + "| fps | 375 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 12660 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1164 |\n", + "| fps | 375 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 12696 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1168 |\n", + "| fps | 376 |\n", + "| time_elapsed | 33 |\n", + "| total_timesteps | 12744 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1172 |\n", + "| fps | 376 |\n", + "| time_elapsed | 34 |\n", + "| total_timesteps | 12840 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1176 |\n", + "| fps | 376 |\n", + "| time_elapsed | 34 |\n", + "| total_timesteps | 12870 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1180 |\n", + "| fps | 376 |\n", + "| time_elapsed | 34 |\n", + "| total_timesteps | 12930 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1184 |\n", + "| fps | 376 |\n", + "| time_elapsed | 34 |\n", + "| total_timesteps | 12996 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1188 |\n", + "| fps | 377 |\n", + "| time_elapsed | 34 |\n", + "| total_timesteps | 13068 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1192 |\n", + "| fps | 377 |\n", + "| time_elapsed | 34 |\n", + "| total_timesteps | 13182 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1196 |\n", + "| fps | 377 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 13224 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1200 |\n", + "| fps | 377 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 13260 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1204 |\n", + "| fps | 377 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 13302 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1208 |\n", + "| fps | 377 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 13338 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1212 |\n", + "| fps | 377 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 13350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1216 |\n", + "| fps | 377 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 13392 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1220 |\n", + "| fps | 377 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 13458 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1224 |\n", + "| fps | 377 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 13494 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1228 |\n", + "| fps | 377 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 13530 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1232 |\n", + "| fps | 377 |\n", + "| time_elapsed | 35 |\n", + "| total_timesteps | 13566 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1236 |\n", + "| fps | 377 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 13602 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1240 |\n", + "| fps | 377 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 13650 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1244 |\n", + "| fps | 377 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 13686 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1248 |\n", + "| fps | 377 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 13716 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1252 |\n", + "| fps | 377 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 13758 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1256 |\n", + "| fps | 377 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 13794 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1260 |\n", + "| fps | 376 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 13836 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1264 |\n", + "| fps | 376 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 13860 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1268 |\n", + "| fps | 376 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 13884 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1272 |\n", + "| fps | 376 |\n", + "| time_elapsed | 36 |\n", + "| total_timesteps | 13914 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1276 |\n", + "| fps | 376 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 13992 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1280 |\n", + "| fps | 376 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 14028 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1284 |\n", + "| fps | 376 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 14070 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1288 |\n", + "| fps | 376 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 14124 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1292 |\n", + "| fps | 376 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 14166 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1296 |\n", + "| fps | 376 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 14202 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1300 |\n", + "| fps | 376 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 14214 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1304 |\n", + "| fps | 376 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 14250 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1308 |\n", + "| fps | 376 |\n", + "| time_elapsed | 37 |\n", + "| total_timesteps | 14292 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1312 |\n", + "| fps | 376 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 14376 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1316 |\n", + "| fps | 376 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 14424 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1320 |\n", + "| fps | 376 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 14484 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1324 |\n", + "| fps | 376 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 14520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1328 |\n", + "| fps | 376 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 14562 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1332 |\n", + "| fps | 376 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 14598 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1336 |\n", + "| fps | 376 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 14640 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1340 |\n", + "| fps | 376 |\n", + "| time_elapsed | 38 |\n", + "| total_timesteps | 14664 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1344 |\n", + "| fps | 376 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 14682 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1348 |\n", + "| fps | 376 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 14712 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1352 |\n", + "| fps | 376 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 14748 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1356 |\n", + "| fps | 376 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 14814 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1360 |\n", + "| fps | 376 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 14862 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1364 |\n", + "| fps | 376 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 14916 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1368 |\n", + "| fps | 376 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 14952 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1372 |\n", + "| fps | 376 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 14994 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1376 |\n", + "| fps | 376 |\n", + "| time_elapsed | 39 |\n", + "| total_timesteps | 15018 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1380 |\n", + "| fps | 376 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 15090 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1384 |\n", + "| fps | 376 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 15186 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1388 |\n", + "| fps | 376 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 15216 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1392 |\n", + "| fps | 377 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 15294 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1396 |\n", + "| fps | 376 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 15330 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1400 |\n", + "| fps | 376 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 15354 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1404 |\n", + "| fps | 376 |\n", + "| time_elapsed | 40 |\n", + "| total_timesteps | 15402 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1408 |\n", + "| fps | 376 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 15450 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1412 |\n", + "| fps | 376 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 15492 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1416 |\n", + "| fps | 376 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 15516 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1420 |\n", + "| fps | 376 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 15546 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1424 |\n", + "| fps | 376 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 15582 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1428 |\n", + "| fps | 376 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 15618 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1432 |\n", + "| fps | 376 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 15648 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1436 |\n", + "| fps | 376 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 15678 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1440 |\n", + "| fps | 376 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 15720 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1444 |\n", + "| fps | 376 |\n", + "| time_elapsed | 41 |\n", + "| total_timesteps | 15762 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1448 |\n", + "| fps | 376 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 15804 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1452 |\n", + "| fps | 376 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 15846 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1456 |\n", + "| fps | 376 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 15864 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1460 |\n", + "| fps | 376 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 15936 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1464 |\n", + "| fps | 376 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 16020 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1468 |\n", + "| fps | 376 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 16044 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1472 |\n", + "| fps | 376 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 16116 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1476 |\n", + "| fps | 376 |\n", + "| time_elapsed | 42 |\n", + "| total_timesteps | 16152 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1480 |\n", + "| fps | 376 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 16200 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1484 |\n", + "| fps | 376 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 16242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1488 |\n", + "| fps | 376 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 16308 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1492 |\n", + "| fps | 376 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 16362 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1496 |\n", + "| fps | 376 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 16410 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1500 |\n", + "| fps | 376 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 16458 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1504 |\n", + "| fps | 376 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 16500 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1508 |\n", + "| fps | 376 |\n", + "| time_elapsed | 43 |\n", + "| total_timesteps | 16524 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1512 |\n", + "| fps | 376 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 16554 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1516 |\n", + "| fps | 376 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 16614 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1520 |\n", + "| fps | 375 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 16656 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1524 |\n", + "| fps | 375 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 16692 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1528 |\n", + "| fps | 375 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 16728 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1532 |\n", + "| fps | 375 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 16764 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1536 |\n", + "| fps | 375 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 16800 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1540 |\n", + "| fps | 376 |\n", + "| time_elapsed | 44 |\n", + "| total_timesteps | 16860 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1544 |\n", + "| fps | 376 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 16932 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1548 |\n", + "| fps | 376 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 16962 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1552 |\n", + "| fps | 376 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 17004 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1556 |\n", + "| fps | 375 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 17034 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1560 |\n", + "| fps | 376 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 17076 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1564 |\n", + "| fps | 376 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 17160 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1568 |\n", + "| fps | 376 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 17202 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1572 |\n", + "| fps | 376 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 17232 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1576 |\n", + "| fps | 376 |\n", + "| time_elapsed | 45 |\n", + "| total_timesteps | 17256 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1580 |\n", + "| fps | 376 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 17322 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1584 |\n", + "| fps | 376 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 17352 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1588 |\n", + "| fps | 376 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 17388 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1592 |\n", + "| fps | 376 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 17424 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1596 |\n", + "| fps | 376 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 17490 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1600 |\n", + "| fps | 376 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 17526 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1604 |\n", + "| fps | 376 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 17550 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1608 |\n", + "| fps | 376 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 17580 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1612 |\n", + "| fps | 376 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 17622 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1616 |\n", + "| fps | 376 |\n", + "| time_elapsed | 46 |\n", + "| total_timesteps | 17670 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1620 |\n", + "| fps | 376 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 17712 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1624 |\n", + "| fps | 376 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 17742 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1628 |\n", + "| fps | 376 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 17772 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1632 |\n", + "| fps | 376 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 17820 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1636 |\n", + "| fps | 376 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 17862 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1640 |\n", + "| fps | 376 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 17898 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1644 |\n", + "| fps | 375 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 17928 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1648 |\n", + "| fps | 375 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 17958 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1652 |\n", + "| fps | 375 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 18000 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1656 |\n", + "| fps | 375 |\n", + "| time_elapsed | 47 |\n", + "| total_timesteps | 18036 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1660 |\n", + "| fps | 375 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 18042 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1664 |\n", + "| fps | 375 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 18078 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1668 |\n", + "| fps | 375 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 18120 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1672 |\n", + "| fps | 375 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 18150 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1676 |\n", + "| fps | 375 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 18186 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1680 |\n", + "| fps | 375 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 18246 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1684 |\n", + "| fps | 375 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 18276 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1688 |\n", + "| fps | 375 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 18318 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1692 |\n", + "| fps | 375 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 18348 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1696 |\n", + "| fps | 375 |\n", + "| time_elapsed | 48 |\n", + "| total_timesteps | 18390 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1700 |\n", + "| fps | 375 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 18444 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1704 |\n", + "| fps | 375 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 18486 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1708 |\n", + "| fps | 375 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 18522 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1712 |\n", + "| fps | 375 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 18546 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1716 |\n", + "| fps | 375 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 18570 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1720 |\n", + "| fps | 375 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 18606 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1724 |\n", + "| fps | 375 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 18636 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1728 |\n", + "| fps | 375 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 18678 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1732 |\n", + "| fps | 375 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 18708 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1736 |\n", + "| fps | 375 |\n", + "| time_elapsed | 49 |\n", + "| total_timesteps | 18732 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1740 |\n", + "| fps | 375 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 18768 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1744 |\n", + "| fps | 375 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 18810 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1748 |\n", + "| fps | 375 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 18852 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1752 |\n", + "| fps | 375 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 18924 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1756 |\n", + "| fps | 375 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 18966 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1760 |\n", + "| fps | 375 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 19008 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1764 |\n", + "| fps | 375 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 19044 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1768 |\n", + "| fps | 375 |\n", + "| time_elapsed | 50 |\n", + "| total_timesteps | 19122 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1772 |\n", + "| fps | 375 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 19164 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1776 |\n", + "| fps | 375 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 19200 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1780 |\n", + "| fps | 375 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 19236 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1784 |\n", + "| fps | 375 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 19278 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1788 |\n", + "| fps | 375 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 19308 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1792 |\n", + "| fps | 375 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 19326 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1796 |\n", + "| fps | 375 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 19368 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1800 |\n", + "| fps | 375 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 19404 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1804 |\n", + "| fps | 375 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 19446 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1808 |\n", + "| fps | 375 |\n", + "| time_elapsed | 51 |\n", + "| total_timesteps | 19488 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1812 |\n", + "| fps | 375 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 19530 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1816 |\n", + "| fps | 375 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 19572 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1820 |\n", + "| fps | 375 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 19608 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1824 |\n", + "| fps | 375 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 19632 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1828 |\n", + "| fps | 375 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 19698 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1832 |\n", + "| fps | 375 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 19746 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1836 |\n", + "| fps | 375 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 19782 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1840 |\n", + "| fps | 375 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 19824 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1844 |\n", + "| fps | 375 |\n", + "| time_elapsed | 52 |\n", + "| total_timesteps | 19866 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1848 |\n", + "| fps | 375 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 19902 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1852 |\n", + "| fps | 375 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 19944 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1856 |\n", + "| fps | 375 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 19992 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1860 |\n", + "| fps | 375 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 20028 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1864 |\n", + "| fps | 375 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 20064 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1868 |\n", + "| fps | 375 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 20100 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1872 |\n", + "| fps | 375 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 20142 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1876 |\n", + "| fps | 375 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 20184 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1880 |\n", + "| fps | 375 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 20226 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1884 |\n", + "| fps | 375 |\n", + "| time_elapsed | 53 |\n", + "| total_timesteps | 20268 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1888 |\n", + "| fps | 375 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 20298 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1892 |\n", + "| fps | 375 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 20340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1896 |\n", + "| fps | 375 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 20382 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1900 |\n", + "| fps | 375 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 20412 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1904 |\n", + "| fps | 375 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 20454 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1908 |\n", + "| fps | 375 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 20520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1912 |\n", + "| fps | 375 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 20544 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1916 |\n", + "| fps | 375 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 20580 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.36 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1920 |\n", + "| fps | 375 |\n", + "| time_elapsed | 54 |\n", + "| total_timesteps | 20652 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1924 |\n", + "| fps | 375 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 20712 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1928 |\n", + "| fps | 375 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 20808 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1932 |\n", + "| fps | 375 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 20838 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1936 |\n", + "| fps | 375 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 20880 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1940 |\n", + "| fps | 375 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 20922 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1944 |\n", + "| fps | 375 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 20952 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1948 |\n", + "| fps | 375 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 20976 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1952 |\n", + "| fps | 375 |\n", + "| time_elapsed | 55 |\n", + "| total_timesteps | 21006 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1956 |\n", + "| fps | 375 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 21042 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1960 |\n", + "| fps | 375 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 21114 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1964 |\n", + "| fps | 375 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 21186 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1968 |\n", + "| fps | 375 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 21252 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1972 |\n", + "| fps | 375 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 21288 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1976 |\n", + "| fps | 375 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 21324 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1980 |\n", + "| fps | 375 |\n", + "| time_elapsed | 56 |\n", + "| total_timesteps | 21378 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1984 |\n", + "| fps | 375 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 21420 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1988 |\n", + "| fps | 375 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 21456 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1992 |\n", + "| fps | 376 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 21570 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 1996 |\n", + "| fps | 376 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 21606 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2000 |\n", + "| fps | 376 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 21648 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2004 |\n", + "| fps | 376 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 21672 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2008 |\n", + "| fps | 376 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 21702 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2012 |\n", + "| fps | 376 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 21738 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2016 |\n", + "| fps | 376 |\n", + "| time_elapsed | 57 |\n", + "| total_timesteps | 21816 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2020 |\n", + "| fps | 376 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 21858 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2024 |\n", + "| fps | 376 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 21882 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2028 |\n", + "| fps | 376 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 21900 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2032 |\n", + "| fps | 376 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 21966 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2036 |\n", + "| fps | 376 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 22014 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2040 |\n", + "| fps | 376 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 22044 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2044 |\n", + "| fps | 376 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 22080 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2048 |\n", + "| fps | 376 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 22116 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2052 |\n", + "| fps | 375 |\n", + "| time_elapsed | 58 |\n", + "| total_timesteps | 22152 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2056 |\n", + "| fps | 376 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 22188 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2060 |\n", + "| fps | 376 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 22230 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2064 |\n", + "| fps | 376 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 22266 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2068 |\n", + "| fps | 376 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 22302 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2072 |\n", + "| fps | 376 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 22338 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2076 |\n", + "| fps | 376 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 22368 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2080 |\n", + "| fps | 375 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 22410 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2084 |\n", + "| fps | 375 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 22446 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2088 |\n", + "| fps | 375 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 22476 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2092 |\n", + "| fps | 376 |\n", + "| time_elapsed | 59 |\n", + "| total_timesteps | 22512 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2096 |\n", + "| fps | 375 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 22554 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2100 |\n", + "| fps | 375 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 22590 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2104 |\n", + "| fps | 375 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 22626 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2108 |\n", + "| fps | 375 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 22668 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2112 |\n", + "| fps | 375 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 22704 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2116 |\n", + "| fps | 375 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 22746 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2120 |\n", + "| fps | 375 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 22806 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2124 |\n", + "| fps | 375 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 22860 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2128 |\n", + "| fps | 375 |\n", + "| time_elapsed | 60 |\n", + "| total_timesteps | 22908 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2132 |\n", + "| fps | 375 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 22944 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2136 |\n", + "| fps | 375 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 22980 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2140 |\n", + "| fps | 375 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 23016 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2144 |\n", + "| fps | 376 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 23070 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2148 |\n", + "| fps | 376 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 23148 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2152 |\n", + "| fps | 376 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 23184 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2156 |\n", + "| fps | 376 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 23220 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2160 |\n", + "| fps | 376 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 23250 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2164 |\n", + "| fps | 375 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 23262 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2168 |\n", + "| fps | 375 |\n", + "| time_elapsed | 61 |\n", + "| total_timesteps | 23298 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2172 |\n", + "| fps | 375 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 23352 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2176 |\n", + "| fps | 375 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 23382 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2180 |\n", + "| fps | 375 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 23424 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2184 |\n", + "| fps | 375 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 23478 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2188 |\n", + "| fps | 375 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 23496 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2192 |\n", + "| fps | 375 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 23532 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2196 |\n", + "| fps | 375 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 23574 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2200 |\n", + "| fps | 375 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 23616 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2204 |\n", + "| fps | 375 |\n", + "| time_elapsed | 62 |\n", + "| total_timesteps | 23646 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2208 |\n", + "| fps | 375 |\n", + "| time_elapsed | 63 |\n", + "| total_timesteps | 23700 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2212 |\n", + "| fps | 375 |\n", + "| time_elapsed | 63 |\n", + "| total_timesteps | 23748 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2216 |\n", + "| fps | 375 |\n", + "| time_elapsed | 63 |\n", + "| total_timesteps | 23772 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2220 |\n", + "| fps | 375 |\n", + "| time_elapsed | 63 |\n", + "| total_timesteps | 23802 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2224 |\n", + "| fps | 375 |\n", + "| time_elapsed | 63 |\n", + "| total_timesteps | 23868 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2228 |\n", + "| fps | 376 |\n", + "| time_elapsed | 63 |\n", + "| total_timesteps | 23910 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2232 |\n", + "| fps | 375 |\n", + "| time_elapsed | 63 |\n", + "| total_timesteps | 23940 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2236 |\n", + "| fps | 376 |\n", + "| time_elapsed | 63 |\n", + "| total_timesteps | 24060 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2240 |\n", + "| fps | 376 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 24108 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2244 |\n", + "| fps | 376 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 24138 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2248 |\n", + "| fps | 376 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 24174 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2252 |\n", + "| fps | 376 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 24234 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2256 |\n", + "| fps | 376 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 24288 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2260 |\n", + "| fps | 376 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 24318 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2264 |\n", + "| fps | 376 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 24354 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2268 |\n", + "| fps | 376 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 24384 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2272 |\n", + "| fps | 376 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 24402 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2276 |\n", + "| fps | 376 |\n", + "| time_elapsed | 64 |\n", + "| total_timesteps | 24432 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2280 |\n", + "| fps | 376 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 24474 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2284 |\n", + "| fps | 376 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 24522 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2288 |\n", + "| fps | 376 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 24594 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2292 |\n", + "| fps | 376 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 24636 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2296 |\n", + "| fps | 376 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 24672 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2300 |\n", + "| fps | 376 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 24708 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2304 |\n", + "| fps | 376 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 24726 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2308 |\n", + "| fps | 376 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 24756 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2312 |\n", + "| fps | 376 |\n", + "| time_elapsed | 65 |\n", + "| total_timesteps | 24792 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2316 |\n", + "| fps | 376 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 24852 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2320 |\n", + "| fps | 376 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 24876 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2324 |\n", + "| fps | 376 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 24900 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2328 |\n", + "| fps | 376 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 24942 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2332 |\n", + "| fps | 376 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 24984 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2336 |\n", + "| fps | 376 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 25008 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2340 |\n", + "| fps | 376 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 25026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2344 |\n", + "| fps | 376 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 25062 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2348 |\n", + "| fps | 376 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 25098 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2352 |\n", + "| fps | 376 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 25170 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2356 |\n", + "| fps | 376 |\n", + "| time_elapsed | 66 |\n", + "| total_timesteps | 25206 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2360 |\n", + "| fps | 376 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 25254 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2364 |\n", + "| fps | 376 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 25296 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2368 |\n", + "| fps | 376 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 25350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2372 |\n", + "| fps | 376 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 25380 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2376 |\n", + "| fps | 376 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 25416 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2380 |\n", + "| fps | 376 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 25494 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2384 |\n", + "| fps | 376 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 25518 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2388 |\n", + "| fps | 376 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 25560 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2392 |\n", + "| fps | 376 |\n", + "| time_elapsed | 67 |\n", + "| total_timesteps | 25596 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2396 |\n", + "| fps | 376 |\n", + "| time_elapsed | 68 |\n", + "| total_timesteps | 25656 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2400 |\n", + "| fps | 376 |\n", + "| time_elapsed | 68 |\n", + "| total_timesteps | 25770 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2404 |\n", + "| fps | 376 |\n", + "| time_elapsed | 68 |\n", + "| total_timesteps | 25818 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2408 |\n", + "| fps | 376 |\n", + "| time_elapsed | 68 |\n", + "| total_timesteps | 25860 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2412 |\n", + "| fps | 376 |\n", + "| time_elapsed | 68 |\n", + "| total_timesteps | 25902 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2416 |\n", + "| fps | 376 |\n", + "| time_elapsed | 68 |\n", + "| total_timesteps | 25950 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2420 |\n", + "| fps | 376 |\n", + "| time_elapsed | 68 |\n", + "| total_timesteps | 25986 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2424 |\n", + "| fps | 376 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 26010 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2428 |\n", + "| fps | 376 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 26076 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2432 |\n", + "| fps | 376 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 26154 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2436 |\n", + "| fps | 376 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 26184 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2440 |\n", + "| fps | 376 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 26220 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2444 |\n", + "| fps | 376 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 26256 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2448 |\n", + "| fps | 376 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 26280 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2452 |\n", + "| fps | 376 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 26322 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2456 |\n", + "| fps | 376 |\n", + "| time_elapsed | 69 |\n", + "| total_timesteps | 26358 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2460 |\n", + "| fps | 377 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 26400 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2464 |\n", + "| fps | 377 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 26484 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2468 |\n", + "| fps | 377 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 26496 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2472 |\n", + "| fps | 376 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 26520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2476 |\n", + "| fps | 376 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 26556 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2480 |\n", + "| fps | 376 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 26586 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2484 |\n", + "| fps | 376 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 26616 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2488 |\n", + "| fps | 377 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 26676 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2492 |\n", + "| fps | 377 |\n", + "| time_elapsed | 70 |\n", + "| total_timesteps | 26742 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2496 |\n", + "| fps | 377 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 26802 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2500 |\n", + "| fps | 377 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 26838 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2504 |\n", + "| fps | 377 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 26886 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2508 |\n", + "| fps | 377 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 26952 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2512 |\n", + "| fps | 377 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 26988 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2516 |\n", + "| fps | 377 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 27048 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2520 |\n", + "| fps | 377 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 27084 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2524 |\n", + "| fps | 377 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 27108 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2528 |\n", + "| fps | 377 |\n", + "| time_elapsed | 71 |\n", + "| total_timesteps | 27132 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2532 |\n", + "| fps | 377 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 27192 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2536 |\n", + "| fps | 377 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 27234 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2540 |\n", + "| fps | 377 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 27276 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2544 |\n", + "| fps | 377 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 27324 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2548 |\n", + "| fps | 377 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 27378 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2552 |\n", + "| fps | 377 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 27414 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2556 |\n", + "| fps | 377 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 27456 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2560 |\n", + "| fps | 377 |\n", + "| time_elapsed | 72 |\n", + "| total_timesteps | 27498 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2564 |\n", + "| fps | 377 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 27540 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2568 |\n", + "| fps | 377 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 27606 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2572 |\n", + "| fps | 377 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 27666 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2576 |\n", + "| fps | 377 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 27696 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2580 |\n", + "| fps | 377 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 27720 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2584 |\n", + "| fps | 377 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 27750 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2588 |\n", + "| fps | 377 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 27786 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2592 |\n", + "| fps | 377 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 27810 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2596 |\n", + "| fps | 377 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 27870 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2600 |\n", + "| fps | 377 |\n", + "| time_elapsed | 73 |\n", + "| total_timesteps | 27912 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2604 |\n", + "| fps | 377 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 27948 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2608 |\n", + "| fps | 377 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 27978 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2612 |\n", + "| fps | 377 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 28014 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2616 |\n", + "| fps | 377 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 28038 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2620 |\n", + "| fps | 377 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 28068 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2624 |\n", + "| fps | 377 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 28110 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2628 |\n", + "| fps | 377 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 28176 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2632 |\n", + "| fps | 377 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 28242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2636 |\n", + "| fps | 377 |\n", + "| time_elapsed | 74 |\n", + "| total_timesteps | 28284 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2640 |\n", + "| fps | 377 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 28314 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2644 |\n", + "| fps | 377 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 28344 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2648 |\n", + "| fps | 377 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 28380 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2652 |\n", + "| fps | 377 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 28416 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2656 |\n", + "| fps | 377 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 28494 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2660 |\n", + "| fps | 377 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 28548 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2664 |\n", + "| fps | 377 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 28584 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2668 |\n", + "| fps | 377 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 28626 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2672 |\n", + "| fps | 377 |\n", + "| time_elapsed | 75 |\n", + "| total_timesteps | 28644 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2676 |\n", + "| fps | 377 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 28692 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2680 |\n", + "| fps | 377 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 28800 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2684 |\n", + "| fps | 377 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 28830 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2688 |\n", + "| fps | 377 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 28866 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2692 |\n", + "| fps | 377 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 28938 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2696 |\n", + "| fps | 377 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 28962 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2700 |\n", + "| fps | 377 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 29028 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2704 |\n", + "| fps | 377 |\n", + "| time_elapsed | 76 |\n", + "| total_timesteps | 29070 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2708 |\n", + "| fps | 377 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 29112 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2712 |\n", + "| fps | 377 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 29190 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2716 |\n", + "| fps | 377 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 29214 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2720 |\n", + "| fps | 377 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 29256 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2724 |\n", + "| fps | 377 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 29304 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2728 |\n", + "| fps | 377 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 29382 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2732 |\n", + "| fps | 378 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 29424 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2736 |\n", + "| fps | 377 |\n", + "| time_elapsed | 77 |\n", + "| total_timesteps | 29466 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2740 |\n", + "| fps | 378 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 29502 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2744 |\n", + "| fps | 378 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 29562 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2748 |\n", + "| fps | 378 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 29616 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2752 |\n", + "| fps | 378 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 29652 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2756 |\n", + "| fps | 378 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 29712 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2760 |\n", + "| fps | 378 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 29760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2764 |\n", + "| fps | 378 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 29832 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2768 |\n", + "| fps | 378 |\n", + "| time_elapsed | 78 |\n", + "| total_timesteps | 29886 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2772 |\n", + "| fps | 378 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 29910 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2776 |\n", + "| fps | 378 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 29934 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2780 |\n", + "| fps | 378 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 29964 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2784 |\n", + "| fps | 378 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 29994 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2788 |\n", + "| fps | 377 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 30036 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2792 |\n", + "| fps | 377 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 30048 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2796 |\n", + "| fps | 378 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 30102 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2800 |\n", + "| fps | 378 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 30162 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2804 |\n", + "| fps | 378 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 30198 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2808 |\n", + "| fps | 377 |\n", + "| time_elapsed | 79 |\n", + "| total_timesteps | 30234 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2812 |\n", + "| fps | 378 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 30270 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2816 |\n", + "| fps | 378 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 30294 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2820 |\n", + "| fps | 377 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 30318 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2824 |\n", + "| fps | 377 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 30348 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2828 |\n", + "| fps | 377 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 30384 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2832 |\n", + "| fps | 377 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 30420 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2836 |\n", + "| fps | 377 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 30474 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2840 |\n", + "| fps | 377 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 30528 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2844 |\n", + "| fps | 378 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 30558 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2848 |\n", + "| fps | 377 |\n", + "| time_elapsed | 80 |\n", + "| total_timesteps | 30594 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2852 |\n", + "| fps | 377 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 30624 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2856 |\n", + "| fps | 377 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 30660 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2860 |\n", + "| fps | 377 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 30708 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2864 |\n", + "| fps | 378 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 30786 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2868 |\n", + "| fps | 378 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 30816 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2872 |\n", + "| fps | 377 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 30852 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2876 |\n", + "| fps | 378 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 30894 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2880 |\n", + "| fps | 377 |\n", + "| time_elapsed | 81 |\n", + "| total_timesteps | 30948 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2884 |\n", + "| fps | 377 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 30996 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2888 |\n", + "| fps | 378 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 31038 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2892 |\n", + "| fps | 378 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 31080 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2896 |\n", + "| fps | 377 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 31110 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2900 |\n", + "| fps | 377 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 31128 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2904 |\n", + "| fps | 377 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 31158 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2908 |\n", + "| fps | 377 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 31188 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2912 |\n", + "| fps | 377 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 31224 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2916 |\n", + "| fps | 377 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 31290 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2920 |\n", + "| fps | 378 |\n", + "| time_elapsed | 82 |\n", + "| total_timesteps | 31338 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2924 |\n", + "| fps | 378 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 31386 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2928 |\n", + "| fps | 378 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 31422 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2932 |\n", + "| fps | 378 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 31452 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2936 |\n", + "| fps | 377 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 31476 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2940 |\n", + "| fps | 377 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 31506 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2944 |\n", + "| fps | 378 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 31578 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2948 |\n", + "| fps | 378 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 31638 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2952 |\n", + "| fps | 378 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 31692 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2956 |\n", + "| fps | 378 |\n", + "| time_elapsed | 83 |\n", + "| total_timesteps | 31740 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2960 |\n", + "| fps | 378 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 31776 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2964 |\n", + "| fps | 378 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 31836 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2968 |\n", + "| fps | 378 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 31878 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2972 |\n", + "| fps | 378 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 31914 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2976 |\n", + "| fps | 378 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 31950 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2980 |\n", + "| fps | 378 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 31962 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2984 |\n", + "| fps | 378 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 32016 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2988 |\n", + "| fps | 378 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 32070 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2992 |\n", + "| fps | 378 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 32100 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 2996 |\n", + "| fps | 378 |\n", + "| time_elapsed | 84 |\n", + "| total_timesteps | 32130 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3000 |\n", + "| fps | 378 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 32154 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3004 |\n", + "| fps | 378 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 32190 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3008 |\n", + "| fps | 377 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 32208 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3012 |\n", + "| fps | 377 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 32232 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3016 |\n", + "| fps | 377 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 32262 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3020 |\n", + "| fps | 377 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 32298 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3024 |\n", + "| fps | 377 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 32328 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3028 |\n", + "| fps | 377 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 32340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3032 |\n", + "| fps | 377 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 32370 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3036 |\n", + "| fps | 377 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 32424 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3040 |\n", + "| fps | 377 |\n", + "| time_elapsed | 85 |\n", + "| total_timesteps | 32472 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3044 |\n", + "| fps | 377 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 32520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3048 |\n", + "| fps | 377 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 32586 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3052 |\n", + "| fps | 378 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 32646 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3056 |\n", + "| fps | 378 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 32694 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3060 |\n", + "| fps | 377 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 32730 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3064 |\n", + "| fps | 377 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 32760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3068 |\n", + "| fps | 377 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 32778 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3072 |\n", + "| fps | 377 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 32814 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3076 |\n", + "| fps | 377 |\n", + "| time_elapsed | 86 |\n", + "| total_timesteps | 32856 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3080 |\n", + "| fps | 377 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 32898 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3084 |\n", + "| fps | 377 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 32928 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3088 |\n", + "| fps | 377 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 32982 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3092 |\n", + "| fps | 377 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 33036 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3096 |\n", + "| fps | 378 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 33072 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3100 |\n", + "| fps | 377 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 33102 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3104 |\n", + "| fps | 377 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 33126 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3108 |\n", + "| fps | 377 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 33180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3112 |\n", + "| fps | 377 |\n", + "| time_elapsed | 87 |\n", + "| total_timesteps | 33240 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3116 |\n", + "| fps | 377 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 33270 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3120 |\n", + "| fps | 377 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 33306 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3124 |\n", + "| fps | 377 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 33348 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3128 |\n", + "| fps | 377 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 33390 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3132 |\n", + "| fps | 377 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 33420 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3136 |\n", + "| fps | 377 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 33456 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3140 |\n", + "| fps | 377 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 33480 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3144 |\n", + "| fps | 377 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 33510 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3148 |\n", + "| fps | 377 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 33576 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3152 |\n", + "| fps | 377 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 33606 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3156 |\n", + "| fps | 377 |\n", + "| time_elapsed | 88 |\n", + "| total_timesteps | 33624 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3160 |\n", + "| fps | 377 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 33660 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3164 |\n", + "| fps | 377 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 33690 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3168 |\n", + "| fps | 377 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 33792 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3172 |\n", + "| fps | 378 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 33912 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3176 |\n", + "| fps | 378 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 33942 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3180 |\n", + "| fps | 378 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 33972 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3184 |\n", + "| fps | 377 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 33990 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3188 |\n", + "| fps | 377 |\n", + "| time_elapsed | 89 |\n", + "| total_timesteps | 34014 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3192 |\n", + "| fps | 377 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 34056 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3196 |\n", + "| fps | 377 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 34098 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3200 |\n", + "| fps | 377 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 34146 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3204 |\n", + "| fps | 378 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 34206 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3208 |\n", + "| fps | 377 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 34242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3212 |\n", + "| fps | 378 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 34308 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3216 |\n", + "| fps | 377 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 34350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3220 |\n", + "| fps | 377 |\n", + "| time_elapsed | 90 |\n", + "| total_timesteps | 34380 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3224 |\n", + "| fps | 378 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 34512 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3228 |\n", + "| fps | 378 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 34548 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3232 |\n", + "| fps | 378 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 34584 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3236 |\n", + "| fps | 378 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 34626 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3240 |\n", + "| fps | 378 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 34680 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3244 |\n", + "| fps | 378 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 34698 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3248 |\n", + "| fps | 378 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 34728 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3252 |\n", + "| fps | 378 |\n", + "| time_elapsed | 91 |\n", + "| total_timesteps | 34764 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3256 |\n", + "| fps | 378 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 34806 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3260 |\n", + "| fps | 378 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 34842 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3264 |\n", + "| fps | 378 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 34884 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3268 |\n", + "| fps | 378 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 34926 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3272 |\n", + "| fps | 378 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 34956 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3276 |\n", + "| fps | 378 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 35016 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3280 |\n", + "| fps | 378 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 35088 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3284 |\n", + "| fps | 378 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 35130 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3288 |\n", + "| fps | 378 |\n", + "| time_elapsed | 92 |\n", + "| total_timesteps | 35148 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3292 |\n", + "| fps | 378 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 35178 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3296 |\n", + "| fps | 378 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 35214 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3300 |\n", + "| fps | 378 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 35280 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3304 |\n", + "| fps | 378 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 35340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3308 |\n", + "| fps | 378 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 35400 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3312 |\n", + "| fps | 378 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 35430 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3316 |\n", + "| fps | 378 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 35478 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3320 |\n", + "| fps | 378 |\n", + "| time_elapsed | 93 |\n", + "| total_timesteps | 35508 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3324 |\n", + "| fps | 378 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 35568 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3328 |\n", + "| fps | 378 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 35592 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3332 |\n", + "| fps | 378 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 35628 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3336 |\n", + "| fps | 378 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 35664 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3340 |\n", + "| fps | 378 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 35694 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3344 |\n", + "| fps | 378 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 35712 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3348 |\n", + "| fps | 378 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 35748 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3352 |\n", + "| fps | 378 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 35790 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3356 |\n", + "| fps | 378 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 35832 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3360 |\n", + "| fps | 378 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 35868 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3364 |\n", + "| fps | 378 |\n", + "| time_elapsed | 94 |\n", + "| total_timesteps | 35922 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3368 |\n", + "| fps | 378 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 35976 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3372 |\n", + "| fps | 378 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 36012 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3376 |\n", + "| fps | 378 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 36054 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3380 |\n", + "| fps | 378 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 36084 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3384 |\n", + "| fps | 378 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 36120 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3388 |\n", + "| fps | 378 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 36156 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3392 |\n", + "| fps | 378 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 36198 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3396 |\n", + "| fps | 378 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 36234 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3400 |\n", + "| fps | 378 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 36270 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3404 |\n", + "| fps | 378 |\n", + "| time_elapsed | 95 |\n", + "| total_timesteps | 36288 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3408 |\n", + "| fps | 378 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 36318 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3412 |\n", + "| fps | 377 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 36336 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3416 |\n", + "| fps | 377 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 36378 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3420 |\n", + "| fps | 377 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 36420 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3424 |\n", + "| fps | 377 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 36450 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3428 |\n", + "| fps | 378 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 36504 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3432 |\n", + "| fps | 378 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 36588 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3436 |\n", + "| fps | 378 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 36654 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3440 |\n", + "| fps | 378 |\n", + "| time_elapsed | 96 |\n", + "| total_timesteps | 36678 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3444 |\n", + "| fps | 378 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 36726 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3448 |\n", + "| fps | 378 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 36768 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3452 |\n", + "| fps | 378 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 36810 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3456 |\n", + "| fps | 378 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 36882 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3460 |\n", + "| fps | 378 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 36918 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3464 |\n", + "| fps | 378 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 36960 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3468 |\n", + "| fps | 378 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 37008 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3472 |\n", + "| fps | 378 |\n", + "| time_elapsed | 97 |\n", + "| total_timesteps | 37062 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3476 |\n", + "| fps | 378 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 37104 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3480 |\n", + "| fps | 378 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 37146 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3484 |\n", + "| fps | 378 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 37188 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3488 |\n", + "| fps | 378 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 37224 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3492 |\n", + "| fps | 378 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 37254 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3496 |\n", + "| fps | 378 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 37314 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3500 |\n", + "| fps | 378 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 37356 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3504 |\n", + "| fps | 378 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 37398 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3508 |\n", + "| fps | 378 |\n", + "| time_elapsed | 98 |\n", + "| total_timesteps | 37452 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3512 |\n", + "| fps | 378 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 37482 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3516 |\n", + "| fps | 378 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 37524 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3520 |\n", + "| fps | 378 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 37566 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3524 |\n", + "| fps | 378 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 37608 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3528 |\n", + "| fps | 378 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 37644 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3532 |\n", + "| fps | 378 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 37680 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3536 |\n", + "| fps | 378 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 37710 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3540 |\n", + "| fps | 378 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 37746 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3544 |\n", + "| fps | 378 |\n", + "| time_elapsed | 99 |\n", + "| total_timesteps | 37788 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3548 |\n", + "| fps | 378 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 37860 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3552 |\n", + "| fps | 378 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 37902 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3556 |\n", + "| fps | 378 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 37962 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3560 |\n", + "| fps | 378 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 38004 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3564 |\n", + "| fps | 378 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 38058 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3568 |\n", + "| fps | 378 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 38118 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3572 |\n", + "| fps | 378 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 38148 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3576 |\n", + "| fps | 378 |\n", + "| time_elapsed | 100 |\n", + "| total_timesteps | 38196 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3580 |\n", + "| fps | 378 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 38226 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3584 |\n", + "| fps | 378 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 38268 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3588 |\n", + "| fps | 378 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 38310 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3592 |\n", + "| fps | 378 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 38352 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3596 |\n", + "| fps | 378 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 38406 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3600 |\n", + "| fps | 378 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 38442 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3604 |\n", + "| fps | 378 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 38490 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3608 |\n", + "| fps | 378 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 38550 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3612 |\n", + "| fps | 378 |\n", + "| time_elapsed | 101 |\n", + "| total_timesteps | 38592 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3616 |\n", + "| fps | 378 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 38634 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3620 |\n", + "| fps | 378 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 38676 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3624 |\n", + "| fps | 378 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 38718 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3628 |\n", + "| fps | 378 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 38760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3632 |\n", + "| fps | 378 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 38832 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3636 |\n", + "| fps | 378 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 38862 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3640 |\n", + "| fps | 378 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 38946 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3644 |\n", + "| fps | 378 |\n", + "| time_elapsed | 102 |\n", + "| total_timesteps | 38994 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3648 |\n", + "| fps | 378 |\n", + "| time_elapsed | 103 |\n", + "| total_timesteps | 39042 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3652 |\n", + "| fps | 378 |\n", + "| time_elapsed | 103 |\n", + "| total_timesteps | 39072 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3656 |\n", + "| fps | 378 |\n", + "| time_elapsed | 103 |\n", + "| total_timesteps | 39096 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3660 |\n", + "| fps | 378 |\n", + "| time_elapsed | 103 |\n", + "| total_timesteps | 39186 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3664 |\n", + "| fps | 378 |\n", + "| time_elapsed | 103 |\n", + "| total_timesteps | 39246 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3668 |\n", + "| fps | 378 |\n", + "| time_elapsed | 103 |\n", + "| total_timesteps | 39282 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3672 |\n", + "| fps | 378 |\n", + "| time_elapsed | 103 |\n", + "| total_timesteps | 39324 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3676 |\n", + "| fps | 379 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 39456 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3680 |\n", + "| fps | 379 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 39504 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3684 |\n", + "| fps | 379 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 39546 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3688 |\n", + "| fps | 379 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 39576 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3692 |\n", + "| fps | 379 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 39618 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3696 |\n", + "| fps | 379 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 39660 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3700 |\n", + "| fps | 379 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 39714 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3704 |\n", + "| fps | 379 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 39738 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3708 |\n", + "| fps | 379 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 39768 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3712 |\n", + "| fps | 379 |\n", + "| time_elapsed | 104 |\n", + "| total_timesteps | 39804 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3716 |\n", + "| fps | 379 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 39840 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3720 |\n", + "| fps | 379 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 39888 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3724 |\n", + "| fps | 379 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 39930 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3728 |\n", + "| fps | 379 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 39972 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3732 |\n", + "| fps | 379 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 40008 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3736 |\n", + "| fps | 379 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 40074 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3740 |\n", + "| fps | 379 |\n", + "| time_elapsed | 105 |\n", + "| total_timesteps | 40122 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3744 |\n", + "| fps | 379 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 40278 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3748 |\n", + "| fps | 379 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 40320 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3752 |\n", + "| fps | 379 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 40356 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3756 |\n", + "| fps | 379 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 40392 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3760 |\n", + "| fps | 379 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 40428 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3764 |\n", + "| fps | 379 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 40470 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3768 |\n", + "| fps | 379 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 40494 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3772 |\n", + "| fps | 379 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 40512 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3776 |\n", + "| fps | 379 |\n", + "| time_elapsed | 106 |\n", + "| total_timesteps | 40572 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3780 |\n", + "| fps | 379 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 40620 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3784 |\n", + "| fps | 379 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 40656 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3788 |\n", + "| fps | 379 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 40698 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3792 |\n", + "| fps | 379 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 40734 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3796 |\n", + "| fps | 379 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 40776 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3800 |\n", + "| fps | 379 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 40842 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3804 |\n", + "| fps | 379 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 40884 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3808 |\n", + "| fps | 379 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 40956 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3812 |\n", + "| fps | 379 |\n", + "| time_elapsed | 107 |\n", + "| total_timesteps | 40980 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3816 |\n", + "| fps | 379 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 41010 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3820 |\n", + "| fps | 379 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 41046 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3824 |\n", + "| fps | 379 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 41070 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3828 |\n", + "| fps | 379 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 41184 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3832 |\n", + "| fps | 379 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 41226 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3836 |\n", + "| fps | 379 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 41244 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3840 |\n", + "| fps | 379 |\n", + "| time_elapsed | 108 |\n", + "| total_timesteps | 41304 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3844 |\n", + "| fps | 379 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 41400 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3848 |\n", + "| fps | 379 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 41460 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3852 |\n", + "| fps | 379 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 41496 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3856 |\n", + "| fps | 379 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 41562 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3860 |\n", + "| fps | 379 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 41592 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3864 |\n", + "| fps | 379 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 41634 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3868 |\n", + "| fps | 380 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 41706 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3872 |\n", + "| fps | 380 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 41754 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3876 |\n", + "| fps | 380 |\n", + "| time_elapsed | 109 |\n", + "| total_timesteps | 41796 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3880 |\n", + "| fps | 379 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 41814 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3884 |\n", + "| fps | 379 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 41850 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3888 |\n", + "| fps | 379 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 41892 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3892 |\n", + "| fps | 379 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 41946 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3896 |\n", + "| fps | 380 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 41976 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3900 |\n", + "| fps | 379 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 42012 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3904 |\n", + "| fps | 379 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 42066 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3908 |\n", + "| fps | 380 |\n", + "| time_elapsed | 110 |\n", + "| total_timesteps | 42144 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3912 |\n", + "| fps | 380 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 42198 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3916 |\n", + "| fps | 380 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 42228 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3920 |\n", + "| fps | 380 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 42270 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3924 |\n", + "| fps | 380 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 42300 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3928 |\n", + "| fps | 380 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 42348 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3932 |\n", + "| fps | 380 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 42390 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3936 |\n", + "| fps | 380 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 42432 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3940 |\n", + "| fps | 380 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 42474 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3944 |\n", + "| fps | 380 |\n", + "| time_elapsed | 111 |\n", + "| total_timesteps | 42516 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3948 |\n", + "| fps | 380 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 42594 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3952 |\n", + "| fps | 380 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 42636 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3956 |\n", + "| fps | 380 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 42666 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3960 |\n", + "| fps | 380 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 42708 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3964 |\n", + "| fps | 380 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 42774 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3968 |\n", + "| fps | 380 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 42822 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3972 |\n", + "| fps | 380 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 42852 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3976 |\n", + "| fps | 380 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 42894 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3980 |\n", + "| fps | 380 |\n", + "| time_elapsed | 112 |\n", + "| total_timesteps | 42942 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3984 |\n", + "| fps | 380 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 42996 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3988 |\n", + "| fps | 380 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 43014 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3992 |\n", + "| fps | 380 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 43050 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 3996 |\n", + "| fps | 380 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 43110 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4000 |\n", + "| fps | 380 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 43152 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4004 |\n", + "| fps | 380 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 43206 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4008 |\n", + "| fps | 380 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 43236 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4012 |\n", + "| fps | 380 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 43272 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4016 |\n", + "| fps | 380 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 43296 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4020 |\n", + "| fps | 380 |\n", + "| time_elapsed | 113 |\n", + "| total_timesteps | 43338 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4024 |\n", + "| fps | 380 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 43446 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4028 |\n", + "| fps | 380 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 43470 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4032 |\n", + "| fps | 380 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 43512 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4036 |\n", + "| fps | 380 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 43584 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4040 |\n", + "| fps | 380 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 43626 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4044 |\n", + "| fps | 380 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 43668 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4048 |\n", + "| fps | 380 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 43698 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4052 |\n", + "| fps | 380 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 43716 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4056 |\n", + "| fps | 380 |\n", + "| time_elapsed | 114 |\n", + "| total_timesteps | 43752 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4060 |\n", + "| fps | 380 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 43806 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4064 |\n", + "| fps | 380 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 43872 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4068 |\n", + "| fps | 380 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 43938 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4072 |\n", + "| fps | 380 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 43998 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4076 |\n", + "| fps | 380 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 44028 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4080 |\n", + "| fps | 380 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 44064 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4084 |\n", + "| fps | 380 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 44088 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4088 |\n", + "| fps | 380 |\n", + "| time_elapsed | 115 |\n", + "| total_timesteps | 44118 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4092 |\n", + "| fps | 380 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 44148 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4096 |\n", + "| fps | 380 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 44190 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4100 |\n", + "| fps | 380 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 44232 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4104 |\n", + "| fps | 380 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 44286 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4108 |\n", + "| fps | 380 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 44322 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4112 |\n", + "| fps | 380 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 44358 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4116 |\n", + "| fps | 380 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 44382 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4120 |\n", + "| fps | 380 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 44406 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4124 |\n", + "| fps | 380 |\n", + "| time_elapsed | 116 |\n", + "| total_timesteps | 44442 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4128 |\n", + "| fps | 380 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 44484 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4132 |\n", + "| fps | 380 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 44550 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4136 |\n", + "| fps | 380 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 44574 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4140 |\n", + "| fps | 380 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 44598 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4144 |\n", + "| fps | 380 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 44640 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4148 |\n", + "| fps | 380 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 44688 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4152 |\n", + "| fps | 380 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 44724 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4156 |\n", + "| fps | 379 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 44754 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4160 |\n", + "| fps | 379 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 44772 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4164 |\n", + "| fps | 379 |\n", + "| time_elapsed | 117 |\n", + "| total_timesteps | 44832 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4168 |\n", + "| fps | 379 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 44898 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4172 |\n", + "| fps | 380 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 44946 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4176 |\n", + "| fps | 380 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 45006 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4180 |\n", + "| fps | 380 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 45018 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4184 |\n", + "| fps | 380 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 45060 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4188 |\n", + "| fps | 379 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 45102 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4192 |\n", + "| fps | 380 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 45144 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4196 |\n", + "| fps | 379 |\n", + "| time_elapsed | 118 |\n", + "| total_timesteps | 45186 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4200 |\n", + "| fps | 379 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 45222 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4204 |\n", + "| fps | 379 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 45264 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4208 |\n", + "| fps | 380 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 45324 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4212 |\n", + "| fps | 380 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 45360 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4216 |\n", + "| fps | 380 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 45396 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4220 |\n", + "| fps | 380 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 45450 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4224 |\n", + "| fps | 380 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 45498 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4228 |\n", + "| fps | 380 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 45540 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4232 |\n", + "| fps | 380 |\n", + "| time_elapsed | 119 |\n", + "| total_timesteps | 45606 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4236 |\n", + "| fps | 380 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 45648 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4240 |\n", + "| fps | 380 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 45678 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4244 |\n", + "| fps | 380 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 45714 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4248 |\n", + "| fps | 380 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 45750 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4252 |\n", + "| fps | 380 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 45780 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4256 |\n", + "| fps | 380 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 45810 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4260 |\n", + "| fps | 380 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 45828 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4264 |\n", + "| fps | 380 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 45888 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4268 |\n", + "| fps | 380 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 45924 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4272 |\n", + "| fps | 380 |\n", + "| time_elapsed | 120 |\n", + "| total_timesteps | 45966 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4276 |\n", + "| fps | 380 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 45996 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4280 |\n", + "| fps | 379 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 46026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4284 |\n", + "| fps | 379 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 46050 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4288 |\n", + "| fps | 379 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 46068 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4292 |\n", + "| fps | 379 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 46110 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4296 |\n", + "| fps | 379 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 46146 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4300 |\n", + "| fps | 379 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 46218 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4304 |\n", + "| fps | 379 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 46266 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4308 |\n", + "| fps | 379 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 46308 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4312 |\n", + "| fps | 380 |\n", + "| time_elapsed | 121 |\n", + "| total_timesteps | 46362 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4316 |\n", + "| fps | 380 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 46416 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4320 |\n", + "| fps | 380 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 46482 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4324 |\n", + "| fps | 380 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 46536 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4328 |\n", + "| fps | 380 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 46590 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4332 |\n", + "| fps | 380 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 46638 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4336 |\n", + "| fps | 380 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 46686 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4340 |\n", + "| fps | 380 |\n", + "| time_elapsed | 122 |\n", + "| total_timesteps | 46722 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4344 |\n", + "| fps | 380 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 46764 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4348 |\n", + "| fps | 380 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 46794 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4352 |\n", + "| fps | 380 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 46848 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4356 |\n", + "| fps | 380 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 46866 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4360 |\n", + "| fps | 380 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 46926 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4364 |\n", + "| fps | 380 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 46968 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4368 |\n", + "| fps | 380 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 47004 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4372 |\n", + "| fps | 380 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 47076 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4376 |\n", + "| fps | 380 |\n", + "| time_elapsed | 123 |\n", + "| total_timesteps | 47124 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4380 |\n", + "| fps | 380 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 47160 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4384 |\n", + "| fps | 380 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 47196 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4388 |\n", + "| fps | 380 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 47256 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4392 |\n", + "| fps | 380 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 47292 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4396 |\n", + "| fps | 380 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 47310 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4400 |\n", + "| fps | 380 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 47352 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4404 |\n", + "| fps | 380 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 47382 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4408 |\n", + "| fps | 380 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 47424 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4412 |\n", + "| fps | 380 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 47460 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4416 |\n", + "| fps | 380 |\n", + "| time_elapsed | 124 |\n", + "| total_timesteps | 47502 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4420 |\n", + "| fps | 380 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 47538 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4424 |\n", + "| fps | 380 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 47592 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4428 |\n", + "| fps | 380 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 47628 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4432 |\n", + "| fps | 380 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 47682 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4436 |\n", + "| fps | 380 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 47754 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4440 |\n", + "| fps | 380 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 47778 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4444 |\n", + "| fps | 380 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 47808 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4448 |\n", + "| fps | 380 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 47850 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4452 |\n", + "| fps | 380 |\n", + "| time_elapsed | 125 |\n", + "| total_timesteps | 47886 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4456 |\n", + "| fps | 380 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 47910 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4460 |\n", + "| fps | 380 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 47934 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4464 |\n", + "| fps | 380 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 47964 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4468 |\n", + "| fps | 380 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 47994 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4472 |\n", + "| fps | 379 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 48012 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4476 |\n", + "| fps | 379 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 48054 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4480 |\n", + "| fps | 379 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 48096 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4484 |\n", + "| fps | 379 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 48120 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4488 |\n", + "| fps | 379 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 48144 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4492 |\n", + "| fps | 379 |\n", + "| time_elapsed | 126 |\n", + "| total_timesteps | 48180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4496 |\n", + "| fps | 379 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 48246 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4500 |\n", + "| fps | 379 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 48288 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4504 |\n", + "| fps | 379 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 48318 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4508 |\n", + "| fps | 379 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 48354 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4512 |\n", + "| fps | 379 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 48384 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4516 |\n", + "| fps | 379 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 48426 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4520 |\n", + "| fps | 379 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 48462 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4524 |\n", + "| fps | 379 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 48480 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4528 |\n", + "| fps | 379 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 48516 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4532 |\n", + "| fps | 379 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 48546 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4536 |\n", + "| fps | 379 |\n", + "| time_elapsed | 127 |\n", + "| total_timesteps | 48582 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4540 |\n", + "| fps | 379 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 48612 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4544 |\n", + "| fps | 379 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 48702 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4548 |\n", + "| fps | 379 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 48738 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4552 |\n", + "| fps | 379 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 48786 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4556 |\n", + "| fps | 379 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 48828 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4560 |\n", + "| fps | 379 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 48858 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4564 |\n", + "| fps | 379 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 48888 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.38 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4568 |\n", + "| fps | 379 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 48900 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4572 |\n", + "| fps | 379 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 48930 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4576 |\n", + "| fps | 379 |\n", + "| time_elapsed | 128 |\n", + "| total_timesteps | 48966 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.34 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4580 |\n", + "| fps | 379 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 49044 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.35 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4584 |\n", + "| fps | 379 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 49092 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.32 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4588 |\n", + "| fps | 379 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 49134 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4592 |\n", + "| fps | 379 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 49194 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4596 |\n", + "| fps | 379 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 49230 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4600 |\n", + "| fps | 379 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 49272 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4604 |\n", + "| fps | 379 |\n", + "| time_elapsed | 129 |\n", + "| total_timesteps | 49350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.31 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4608 |\n", + "| fps | 379 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 49404 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.33 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4612 |\n", + "| fps | 379 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 49440 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.37 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4616 |\n", + "| fps | 379 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 49488 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4620 |\n", + "| fps | 379 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 49524 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4624 |\n", + "| fps | 379 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 49572 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.39 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4628 |\n", + "| fps | 379 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 49608 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4632 |\n", + "| fps | 379 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 49620 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4636 |\n", + "| fps | 379 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 49662 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.4 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4640 |\n", + "| fps | 379 |\n", + "| time_elapsed | 130 |\n", + "| total_timesteps | 49734 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4644 |\n", + "| fps | 379 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 49770 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4648 |\n", + "| fps | 379 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 49794 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4652 |\n", + "| fps | 379 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 49824 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4656 |\n", + "| fps | 379 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 49860 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4660 |\n", + "| fps | 379 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 49908 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.42 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4664 |\n", + "| fps | 379 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 49974 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4668 |\n", + "| fps | 379 |\n", + "| time_elapsed | 131 |\n", + "| total_timesteps | 50016 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.41 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4672 |\n", + "| fps | 378 |\n", + "| time_elapsed | 132 |\n", + "| total_timesteps | 50052 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0643 |\n", + "| n_updates | 2 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4676 |\n", + "| fps | 377 |\n", + "| time_elapsed | 132 |\n", + "| total_timesteps | 50118 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0635 |\n", + "| n_updates | 5 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4680 |\n", + "| fps | 377 |\n", + "| time_elapsed | 132 |\n", + "| total_timesteps | 50148 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.63 |\n", + "| n_updates | 6 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4684 |\n", + "| fps | 376 |\n", + "| time_elapsed | 133 |\n", + "| total_timesteps | 50220 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0623 |\n", + "| n_updates | 9 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4688 |\n", + "| fps | 375 |\n", + "| time_elapsed | 133 |\n", + "| total_timesteps | 50268 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.06 |\n", + "| n_updates | 11 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4692 |\n", + "| fps | 375 |\n", + "| time_elapsed | 134 |\n", + "| total_timesteps | 50322 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 13 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4696 |\n", + "| fps | 374 |\n", + "| time_elapsed | 134 |\n", + "| total_timesteps | 50364 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 15 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4700 |\n", + "| fps | 373 |\n", + "| time_elapsed | 134 |\n", + "| total_timesteps | 50406 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 17 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4704 |\n", + "| fps | 373 |\n", + "| time_elapsed | 135 |\n", + "| total_timesteps | 50472 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0548 |\n", + "| n_updates | 19 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4708 |\n", + "| fps | 372 |\n", + "| time_elapsed | 135 |\n", + "| total_timesteps | 50508 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0546 |\n", + "| n_updates | 21 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4712 |\n", + "| fps | 372 |\n", + "| time_elapsed | 135 |\n", + "| total_timesteps | 50550 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.17 |\n", + "| n_updates | 23 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4716 |\n", + "| fps | 371 |\n", + "| time_elapsed | 136 |\n", + "| total_timesteps | 50574 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0535 |\n", + "| n_updates | 24 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4720 |\n", + "| fps | 371 |\n", + "| time_elapsed | 136 |\n", + "| total_timesteps | 50640 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 26 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4724 |\n", + "| fps | 369 |\n", + "| time_elapsed | 137 |\n", + "| total_timesteps | 50700 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.61 |\n", + "| n_updates | 29 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4728 |\n", + "| fps | 369 |\n", + "| time_elapsed | 137 |\n", + "| total_timesteps | 50742 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.6 |\n", + "| n_updates | 31 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4732 |\n", + "| fps | 369 |\n", + "| time_elapsed | 137 |\n", + "| total_timesteps | 50772 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0517 |\n", + "| n_updates | 32 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4736 |\n", + "| fps | 368 |\n", + "| time_elapsed | 137 |\n", + "| total_timesteps | 50808 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0517 |\n", + "| n_updates | 33 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4740 |\n", + "| fps | 367 |\n", + "| time_elapsed | 138 |\n", + "| total_timesteps | 50886 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.6 |\n", + "| n_updates | 37 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4744 |\n", + "| fps | 366 |\n", + "| time_elapsed | 138 |\n", + "| total_timesteps | 50952 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.59 |\n", + "| n_updates | 39 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4748 |\n", + "| fps | 366 |\n", + "| time_elapsed | 139 |\n", + "| total_timesteps | 50988 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.6 |\n", + "| n_updates | 41 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4752 |\n", + "| fps | 365 |\n", + "| time_elapsed | 139 |\n", + "| total_timesteps | 51006 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.6 |\n", + "| n_updates | 42 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4756 |\n", + "| fps | 365 |\n", + "| time_elapsed | 139 |\n", + "| total_timesteps | 51036 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.67 |\n", + "| n_updates | 43 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4760 |\n", + "| fps | 365 |\n", + "| time_elapsed | 139 |\n", + "| total_timesteps | 51066 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0502 |\n", + "| n_updates | 44 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4764 |\n", + "| fps | 363 |\n", + "| time_elapsed | 140 |\n", + "| total_timesteps | 51162 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.6 |\n", + "| n_updates | 48 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4768 |\n", + "| fps | 363 |\n", + "| time_elapsed | 140 |\n", + "| total_timesteps | 51192 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0514 |\n", + "| n_updates | 49 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4772 |\n", + "| fps | 362 |\n", + "| time_elapsed | 141 |\n", + "| total_timesteps | 51228 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0519 |\n", + "| n_updates | 51 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4776 |\n", + "| fps | 362 |\n", + "| time_elapsed | 141 |\n", + "| total_timesteps | 51258 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0477 |\n", + "| n_updates | 52 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4780 |\n", + "| fps | 362 |\n", + "| time_elapsed | 141 |\n", + "| total_timesteps | 51288 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0511 |\n", + "| n_updates | 53 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4784 |\n", + "| fps | 361 |\n", + "| time_elapsed | 141 |\n", + "| total_timesteps | 51318 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.57 |\n", + "| n_updates | 55 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4788 |\n", + "| fps | 361 |\n", + "| time_elapsed | 142 |\n", + "| total_timesteps | 51360 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0482 |\n", + "| n_updates | 56 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4792 |\n", + "| fps | 359 |\n", + "| time_elapsed | 143 |\n", + "| total_timesteps | 51492 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0514 |\n", + "| n_updates | 62 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4796 |\n", + "| fps | 359 |\n", + "| time_elapsed | 143 |\n", + "| total_timesteps | 51522 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.05 |\n", + "| n_updates | 63 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4800 |\n", + "| fps | 358 |\n", + "| time_elapsed | 143 |\n", + "| total_timesteps | 51558 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0523 |\n", + "| n_updates | 65 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4804 |\n", + "| fps | 357 |\n", + "| time_elapsed | 144 |\n", + "| total_timesteps | 51624 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 67 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4808 |\n", + "| fps | 357 |\n", + "| time_elapsed | 144 |\n", + "| total_timesteps | 51660 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.052 |\n", + "| n_updates | 69 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4812 |\n", + "| fps | 356 |\n", + "| time_elapsed | 144 |\n", + "| total_timesteps | 51702 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0537 |\n", + "| n_updates | 71 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4816 |\n", + "| fps | 356 |\n", + "| time_elapsed | 145 |\n", + "| total_timesteps | 51768 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0545 |\n", + "| n_updates | 73 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4820 |\n", + "| fps | 355 |\n", + "| time_elapsed | 145 |\n", + "| total_timesteps | 51852 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.94 |\n", + "| n_updates | 77 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4824 |\n", + "| fps | 354 |\n", + "| time_elapsed | 146 |\n", + "| total_timesteps | 51882 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0572 |\n", + "| n_updates | 78 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4828 |\n", + "| fps | 354 |\n", + "| time_elapsed | 146 |\n", + "| total_timesteps | 51924 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 80 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4832 |\n", + "| fps | 353 |\n", + "| time_elapsed | 146 |\n", + "| total_timesteps | 51948 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 81 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4836 |\n", + "| fps | 352 |\n", + "| time_elapsed | 147 |\n", + "| total_timesteps | 52050 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.5 |\n", + "| n_updates | 85 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4840 |\n", + "| fps | 351 |\n", + "| time_elapsed | 148 |\n", + "| total_timesteps | 52122 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0724 |\n", + "| n_updates | 88 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4844 |\n", + "| fps | 351 |\n", + "| time_elapsed | 148 |\n", + "| total_timesteps | 52140 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.9 |\n", + "| n_updates | 89 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4848 |\n", + "| fps | 351 |\n", + "| time_elapsed | 148 |\n", + "| total_timesteps | 52170 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0924 |\n", + "| n_updates | 90 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4852 |\n", + "| fps | 350 |\n", + "| time_elapsed | 148 |\n", + "| total_timesteps | 52200 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.51 |\n", + "| n_updates | 91 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4856 |\n", + "| fps | 350 |\n", + "| time_elapsed | 149 |\n", + "| total_timesteps | 52236 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0831 |\n", + "| n_updates | 93 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4860 |\n", + "| fps | 349 |\n", + "| time_elapsed | 149 |\n", + "| total_timesteps | 52260 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.49 |\n", + "| n_updates | 94 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4864 |\n", + "| fps | 349 |\n", + "| time_elapsed | 149 |\n", + "| total_timesteps | 52302 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.49 |\n", + "| n_updates | 96 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4868 |\n", + "| fps | 348 |\n", + "| time_elapsed | 150 |\n", + "| total_timesteps | 52368 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.44 |\n", + "| n_updates | 98 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4872 |\n", + "| fps | 347 |\n", + "| time_elapsed | 150 |\n", + "| total_timesteps | 52434 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.49 |\n", + "| n_updates | 101 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4876 |\n", + "| fps | 347 |\n", + "| time_elapsed | 151 |\n", + "| total_timesteps | 52470 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.21 |\n", + "| n_updates | 103 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4880 |\n", + "| fps | 347 |\n", + "| time_elapsed | 151 |\n", + "| total_timesteps | 52494 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.45 |\n", + "| n_updates | 104 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4884 |\n", + "| fps | 346 |\n", + "| time_elapsed | 151 |\n", + "| total_timesteps | 52524 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.44 |\n", + "| n_updates | 105 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4888 |\n", + "| fps | 346 |\n", + "| time_elapsed | 151 |\n", + "| total_timesteps | 52554 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.83 |\n", + "| n_updates | 106 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4892 |\n", + "| fps | 346 |\n", + "| time_elapsed | 151 |\n", + "| total_timesteps | 52584 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.44 |\n", + "| n_updates | 107 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4896 |\n", + "| fps | 345 |\n", + "| time_elapsed | 152 |\n", + "| total_timesteps | 52638 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.49 |\n", + "| n_updates | 110 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4900 |\n", + "| fps | 344 |\n", + "| time_elapsed | 153 |\n", + "| total_timesteps | 52746 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.219 |\n", + "| n_updates | 114 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4904 |\n", + "| fps | 344 |\n", + "| time_elapsed | 153 |\n", + "| total_timesteps | 52776 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.49 |\n", + "| n_updates | 115 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4908 |\n", + "| fps | 343 |\n", + "| time_elapsed | 153 |\n", + "| total_timesteps | 52788 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.193 |\n", + "| n_updates | 116 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4912 |\n", + "| fps | 343 |\n", + "| time_elapsed | 153 |\n", + "| total_timesteps | 52812 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.216 |\n", + "| n_updates | 117 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4916 |\n", + "| fps | 343 |\n", + "| time_elapsed | 153 |\n", + "| total_timesteps | 52848 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.221 |\n", + "| n_updates | 118 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4920 |\n", + "| fps | 342 |\n", + "| time_elapsed | 154 |\n", + "| total_timesteps | 52932 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.154 |\n", + "| n_updates | 122 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4924 |\n", + "| fps | 341 |\n", + "| time_elapsed | 154 |\n", + "| total_timesteps | 52980 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.86 |\n", + "| n_updates | 124 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4928 |\n", + "| fps | 341 |\n", + "| time_elapsed | 155 |\n", + "| total_timesteps | 53022 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.4 |\n", + "| n_updates | 126 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4932 |\n", + "| fps | 340 |\n", + "| time_elapsed | 155 |\n", + "| total_timesteps | 53100 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.12 |\n", + "| n_updates | 129 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4936 |\n", + "| fps | 340 |\n", + "| time_elapsed | 156 |\n", + "| total_timesteps | 53142 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.36 |\n", + "| n_updates | 131 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4940 |\n", + "| fps | 339 |\n", + "| time_elapsed | 156 |\n", + "| total_timesteps | 53184 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.47 |\n", + "| n_updates | 132 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4944 |\n", + "| fps | 339 |\n", + "| time_elapsed | 156 |\n", + "| total_timesteps | 53214 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0945 |\n", + "| n_updates | 134 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4948 |\n", + "| fps | 338 |\n", + "| time_elapsed | 157 |\n", + "| total_timesteps | 53286 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0956 |\n", + "| n_updates | 137 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4952 |\n", + "| fps | 338 |\n", + "| time_elapsed | 157 |\n", + "| total_timesteps | 53352 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 139 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4956 |\n", + "| fps | 337 |\n", + "| time_elapsed | 158 |\n", + "| total_timesteps | 53394 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.116 |\n", + "| n_updates | 141 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4960 |\n", + "| fps | 337 |\n", + "| time_elapsed | 158 |\n", + "| total_timesteps | 53424 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.12 |\n", + "| n_updates | 142 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4964 |\n", + "| fps | 336 |\n", + "| time_elapsed | 158 |\n", + "| total_timesteps | 53472 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.12 |\n", + "| n_updates | 144 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4968 |\n", + "| fps | 336 |\n", + "| time_elapsed | 159 |\n", + "| total_timesteps | 53502 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 146 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4972 |\n", + "| fps | 336 |\n", + "| time_elapsed | 159 |\n", + "| total_timesteps | 53544 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 147 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4976 |\n", + "| fps | 335 |\n", + "| time_elapsed | 159 |\n", + "| total_timesteps | 53604 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.3 |\n", + "| n_updates | 150 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4980 |\n", + "| fps | 334 |\n", + "| time_elapsed | 160 |\n", + "| total_timesteps | 53670 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.143 |\n", + "| n_updates | 153 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4984 |\n", + "| fps | 334 |\n", + "| time_elapsed | 160 |\n", + "| total_timesteps | 53712 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.0861 |\n", + "| n_updates | 154 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4988 |\n", + "| fps | 334 |\n", + "| time_elapsed | 160 |\n", + "| total_timesteps | 53742 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.109 |\n", + "| n_updates | 156 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4992 |\n", + "| fps | 333 |\n", + "| time_elapsed | 161 |\n", + "| total_timesteps | 53766 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.31 |\n", + "| n_updates | 157 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 4996 |\n", + "| fps | 333 |\n", + "| time_elapsed | 161 |\n", + "| total_timesteps | 53814 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.14 |\n", + "| n_updates | 159 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5000 |\n", + "| fps | 332 |\n", + "| time_elapsed | 162 |\n", + "| total_timesteps | 53904 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.136 |\n", + "| n_updates | 162 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5004 |\n", + "| fps | 332 |\n", + "| time_elapsed | 162 |\n", + "| total_timesteps | 53952 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.62 |\n", + "| n_updates | 164 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5008 |\n", + "| fps | 331 |\n", + "| time_elapsed | 162 |\n", + "| total_timesteps | 53982 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.109 |\n", + "| n_updates | 166 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5012 |\n", + "| fps | 331 |\n", + "| time_elapsed | 163 |\n", + "| total_timesteps | 54012 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 167 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5016 |\n", + "| fps | 331 |\n", + "| time_elapsed | 163 |\n", + "| total_timesteps | 54042 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.117 |\n", + "| n_updates | 168 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5020 |\n", + "| fps | 330 |\n", + "| time_elapsed | 163 |\n", + "| total_timesteps | 54078 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.126 |\n", + "| n_updates | 170 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5024 |\n", + "| fps | 330 |\n", + "| time_elapsed | 163 |\n", + "| total_timesteps | 54120 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 171 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5028 |\n", + "| fps | 329 |\n", + "| time_elapsed | 164 |\n", + "| total_timesteps | 54186 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.123 |\n", + "| n_updates | 174 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5032 |\n", + "| fps | 329 |\n", + "| time_elapsed | 164 |\n", + "| total_timesteps | 54258 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.37 |\n", + "| n_updates | 177 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5036 |\n", + "| fps | 328 |\n", + "| time_elapsed | 165 |\n", + "| total_timesteps | 54318 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.142 |\n", + "| n_updates | 180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5040 |\n", + "| fps | 328 |\n", + "| time_elapsed | 165 |\n", + "| total_timesteps | 54360 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.123 |\n", + "| n_updates | 181 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5044 |\n", + "| fps | 327 |\n", + "| time_elapsed | 165 |\n", + "| total_timesteps | 54390 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.37 |\n", + "| n_updates | 183 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5048 |\n", + "| fps | 327 |\n", + "| time_elapsed | 166 |\n", + "| total_timesteps | 54438 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 185 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5052 |\n", + "| fps | 326 |\n", + "| time_elapsed | 166 |\n", + "| total_timesteps | 54510 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.185 |\n", + "| n_updates | 188 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5056 |\n", + "| fps | 326 |\n", + "| time_elapsed | 167 |\n", + "| total_timesteps | 54564 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 190 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5060 |\n", + "| fps | 326 |\n", + "| time_elapsed | 167 |\n", + "| total_timesteps | 54594 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.36 |\n", + "| n_updates | 191 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5064 |\n", + "| fps | 325 |\n", + "| time_elapsed | 167 |\n", + "| total_timesteps | 54624 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.45 |\n", + "| n_updates | 192 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5068 |\n", + "| fps | 325 |\n", + "| time_elapsed | 168 |\n", + "| total_timesteps | 54654 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.203 |\n", + "| n_updates | 194 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5072 |\n", + "| fps | 325 |\n", + "| time_elapsed | 168 |\n", + "| total_timesteps | 54678 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.189 |\n", + "| n_updates | 195 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5076 |\n", + "| fps | 324 |\n", + "| time_elapsed | 168 |\n", + "| total_timesteps | 54702 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.33 |\n", + "| n_updates | 196 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5080 |\n", + "| fps | 324 |\n", + "| time_elapsed | 168 |\n", + "| total_timesteps | 54774 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 199 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5084 |\n", + "| fps | 323 |\n", + "| time_elapsed | 169 |\n", + "| total_timesteps | 54852 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.59 |\n", + "| n_updates | 202 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5088 |\n", + "| fps | 323 |\n", + "| time_elapsed | 169 |\n", + "| total_timesteps | 54894 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.23 |\n", + "| n_updates | 204 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5092 |\n", + "| fps | 323 |\n", + "| time_elapsed | 169 |\n", + "| total_timesteps | 54924 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.2 |\n", + "| n_updates | 205 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5096 |\n", + "| fps | 322 |\n", + "| time_elapsed | 170 |\n", + "| total_timesteps | 54948 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.31 |\n", + "| n_updates | 206 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5100 |\n", + "| fps | 322 |\n", + "| time_elapsed | 170 |\n", + "| total_timesteps | 54984 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 207 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5104 |\n", + "| fps | 322 |\n", + "| time_elapsed | 170 |\n", + "| total_timesteps | 55014 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.332 |\n", + "| n_updates | 209 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5108 |\n", + "| fps | 322 |\n", + "| time_elapsed | 170 |\n", + "| total_timesteps | 55026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5112 |\n", + "| fps | 321 |\n", + "| time_elapsed | 171 |\n", + "| total_timesteps | 55086 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.23 |\n", + "| n_updates | 212 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5116 |\n", + "| fps | 320 |\n", + "| time_elapsed | 171 |\n", + "| total_timesteps | 55164 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.21 |\n", + "| n_updates | 215 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5120 |\n", + "| fps | 320 |\n", + "| time_elapsed | 172 |\n", + "| total_timesteps | 55224 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.39 |\n", + "| n_updates | 217 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5124 |\n", + "| fps | 320 |\n", + "| time_elapsed | 172 |\n", + "| total_timesteps | 55236 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.307 |\n", + "| n_updates | 218 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5128 |\n", + "| fps | 319 |\n", + "| time_elapsed | 172 |\n", + "| total_timesteps | 55290 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.39 |\n", + "| n_updates | 220 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5132 |\n", + "| fps | 319 |\n", + "| time_elapsed | 173 |\n", + "| total_timesteps | 55326 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.313 |\n", + "| n_updates | 222 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5136 |\n", + "| fps | 319 |\n", + "| time_elapsed | 173 |\n", + "| total_timesteps | 55362 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.34 |\n", + "| n_updates | 223 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5140 |\n", + "| fps | 318 |\n", + "| time_elapsed | 173 |\n", + "| total_timesteps | 55422 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.246 |\n", + "| n_updates | 226 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5144 |\n", + "| fps | 318 |\n", + "| time_elapsed | 174 |\n", + "| total_timesteps | 55470 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.181 |\n", + "| n_updates | 228 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5148 |\n", + "| fps | 317 |\n", + "| time_elapsed | 174 |\n", + "| total_timesteps | 55512 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.3 |\n", + "| n_updates | 229 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5152 |\n", + "| fps | 317 |\n", + "| time_elapsed | 174 |\n", + "| total_timesteps | 55548 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.32 |\n", + "| n_updates | 231 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5156 |\n", + "| fps | 317 |\n", + "| time_elapsed | 175 |\n", + "| total_timesteps | 55596 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.31 |\n", + "| n_updates | 233 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5160 |\n", + "| fps | 316 |\n", + "| time_elapsed | 175 |\n", + "| total_timesteps | 55626 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.144 |\n", + "| n_updates | 234 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5164 |\n", + "| fps | 316 |\n", + "| time_elapsed | 175 |\n", + "| total_timesteps | 55674 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.33 |\n", + "| n_updates | 236 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5168 |\n", + "| fps | 315 |\n", + "| time_elapsed | 176 |\n", + "| total_timesteps | 55758 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 240 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5172 |\n", + "| fps | 315 |\n", + "| time_elapsed | 176 |\n", + "| total_timesteps | 55806 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.52 |\n", + "| n_updates | 242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5176 |\n", + "| fps | 315 |\n", + "| time_elapsed | 177 |\n", + "| total_timesteps | 55842 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.31 |\n", + "| n_updates | 243 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5180 |\n", + "| fps | 314 |\n", + "| time_elapsed | 177 |\n", + "| total_timesteps | 55884 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.31 |\n", + "| n_updates | 245 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.25 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5184 |\n", + "| fps | 314 |\n", + "| time_elapsed | 178 |\n", + "| total_timesteps | 55938 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.104 |\n", + "| n_updates | 247 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.25 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5188 |\n", + "| fps | 313 |\n", + "| time_elapsed | 178 |\n", + "| total_timesteps | 55980 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.51 |\n", + "| n_updates | 249 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.26 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5192 |\n", + "| fps | 313 |\n", + "| time_elapsed | 178 |\n", + "| total_timesteps | 56004 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.147 |\n", + "| n_updates | 250 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5196 |\n", + "| fps | 313 |\n", + "| time_elapsed | 178 |\n", + "| total_timesteps | 56034 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.142 |\n", + "| n_updates | 251 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5200 |\n", + "| fps | 313 |\n", + "| time_elapsed | 179 |\n", + "| total_timesteps | 56064 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.32 |\n", + "| n_updates | 252 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5204 |\n", + "| fps | 312 |\n", + "| time_elapsed | 179 |\n", + "| total_timesteps | 56124 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.35 |\n", + "| n_updates | 255 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5208 |\n", + "| fps | 312 |\n", + "| time_elapsed | 179 |\n", + "| total_timesteps | 56184 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.134 |\n", + "| n_updates | 257 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5212 |\n", + "| fps | 311 |\n", + "| time_elapsed | 180 |\n", + "| total_timesteps | 56244 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.117 |\n", + "| n_updates | 260 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5216 |\n", + "| fps | 311 |\n", + "| time_elapsed | 180 |\n", + "| total_timesteps | 56274 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.31 |\n", + "| n_updates | 261 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5220 |\n", + "| fps | 310 |\n", + "| time_elapsed | 181 |\n", + "| total_timesteps | 56310 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.11 |\n", + "| n_updates | 263 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5224 |\n", + "| fps | 310 |\n", + "| time_elapsed | 181 |\n", + "| total_timesteps | 56340 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 264 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5228 |\n", + "| fps | 310 |\n", + "| time_elapsed | 181 |\n", + "| total_timesteps | 56388 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 266 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5232 |\n", + "| fps | 309 |\n", + "| time_elapsed | 182 |\n", + "| total_timesteps | 56448 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.31 |\n", + "| n_updates | 268 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5236 |\n", + "| fps | 309 |\n", + "| time_elapsed | 182 |\n", + "| total_timesteps | 56496 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.16 |\n", + "| n_updates | 270 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5240 |\n", + "| fps | 309 |\n", + "| time_elapsed | 182 |\n", + "| total_timesteps | 56538 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.166 |\n", + "| n_updates | 272 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5244 |\n", + "| fps | 308 |\n", + "| time_elapsed | 183 |\n", + "| total_timesteps | 56634 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 276 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5248 |\n", + "| fps | 308 |\n", + "| time_elapsed | 183 |\n", + "| total_timesteps | 56670 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.156 |\n", + "| n_updates | 278 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5252 |\n", + "| fps | 308 |\n", + "| time_elapsed | 184 |\n", + "| total_timesteps | 56700 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 279 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5256 |\n", + "| fps | 307 |\n", + "| time_elapsed | 184 |\n", + "| total_timesteps | 56730 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 280 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5260 |\n", + "| fps | 307 |\n", + "| time_elapsed | 184 |\n", + "| total_timesteps | 56796 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.4 |\n", + "| n_updates | 283 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5264 |\n", + "| fps | 307 |\n", + "| time_elapsed | 185 |\n", + "| total_timesteps | 56832 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.78 |\n", + "| n_updates | 284 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5268 |\n", + "| fps | 306 |\n", + "| time_elapsed | 185 |\n", + "| total_timesteps | 56850 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.156 |\n", + "| n_updates | 285 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5272 |\n", + "| fps | 306 |\n", + "| time_elapsed | 185 |\n", + "| total_timesteps | 56874 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.5 |\n", + "| n_updates | 286 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5276 |\n", + "| fps | 306 |\n", + "| time_elapsed | 185 |\n", + "| total_timesteps | 56904 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.66 |\n", + "| n_updates | 287 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5280 |\n", + "| fps | 306 |\n", + "| time_elapsed | 185 |\n", + "| total_timesteps | 56934 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 289 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5284 |\n", + "| fps | 305 |\n", + "| time_elapsed | 186 |\n", + "| total_timesteps | 56988 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.238 |\n", + "| n_updates | 291 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5288 |\n", + "| fps | 305 |\n", + "| time_elapsed | 187 |\n", + "| total_timesteps | 57084 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 295 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5292 |\n", + "| fps | 304 |\n", + "| time_elapsed | 187 |\n", + "| total_timesteps | 57126 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.15 |\n", + "| n_updates | 297 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5296 |\n", + "| fps | 304 |\n", + "| time_elapsed | 187 |\n", + "| total_timesteps | 57150 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 298 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5300 |\n", + "| fps | 304 |\n", + "| time_elapsed | 187 |\n", + "| total_timesteps | 57162 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5304 |\n", + "| fps | 304 |\n", + "| time_elapsed | 187 |\n", + "| total_timesteps | 57192 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.335 |\n", + "| n_updates | 299 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5308 |\n", + "| fps | 303 |\n", + "| time_elapsed | 188 |\n", + "| total_timesteps | 57222 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.313 |\n", + "| n_updates | 301 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5312 |\n", + "| fps | 303 |\n", + "| time_elapsed | 188 |\n", + "| total_timesteps | 57264 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.329 |\n", + "| n_updates | 302 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5316 |\n", + "| fps | 303 |\n", + "| time_elapsed | 189 |\n", + "| total_timesteps | 57318 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.24 |\n", + "| n_updates | 305 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5320 |\n", + "| fps | 303 |\n", + "| time_elapsed | 189 |\n", + "| total_timesteps | 57360 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.209 |\n", + "| n_updates | 306 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5324 |\n", + "| fps | 302 |\n", + "| time_elapsed | 190 |\n", + "| total_timesteps | 57462 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 311 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5328 |\n", + "| fps | 302 |\n", + "| time_elapsed | 190 |\n", + "| total_timesteps | 57504 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 312 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5332 |\n", + "| fps | 301 |\n", + "| time_elapsed | 191 |\n", + "| total_timesteps | 57594 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.23 |\n", + "| n_updates | 316 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5336 |\n", + "| fps | 301 |\n", + "| time_elapsed | 191 |\n", + "| total_timesteps | 57660 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 319 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5340 |\n", + "| fps | 300 |\n", + "| time_elapsed | 191 |\n", + "| total_timesteps | 57684 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.4 |\n", + "| n_updates | 320 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5344 |\n", + "| fps | 300 |\n", + "| time_elapsed | 191 |\n", + "| total_timesteps | 57720 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 321 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5348 |\n", + "| fps | 300 |\n", + "| time_elapsed | 192 |\n", + "| total_timesteps | 57780 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.298 |\n", + "| n_updates | 324 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5352 |\n", + "| fps | 300 |\n", + "| time_elapsed | 192 |\n", + "| total_timesteps | 57816 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.24 |\n", + "| n_updates | 325 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5356 |\n", + "| fps | 299 |\n", + "| time_elapsed | 192 |\n", + "| total_timesteps | 57840 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.29 |\n", + "| n_updates | 326 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5360 |\n", + "| fps | 299 |\n", + "| time_elapsed | 193 |\n", + "| total_timesteps | 57870 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.29 |\n", + "| n_updates | 328 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5364 |\n", + "| fps | 299 |\n", + "| time_elapsed | 193 |\n", + "| total_timesteps | 57912 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.45 |\n", + "| n_updates | 329 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5368 |\n", + "| fps | 298 |\n", + "| time_elapsed | 193 |\n", + "| total_timesteps | 57948 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.387 |\n", + "| n_updates | 331 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5372 |\n", + "| fps | 298 |\n", + "| time_elapsed | 194 |\n", + "| total_timesteps | 57972 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 332 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5376 |\n", + "| fps | 298 |\n", + "| time_elapsed | 194 |\n", + "| total_timesteps | 58002 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.344 |\n", + "| n_updates | 333 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5380 |\n", + "| fps | 298 |\n", + "| time_elapsed | 194 |\n", + "| total_timesteps | 58032 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.301 |\n", + "| n_updates | 334 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5384 |\n", + "| fps | 297 |\n", + "| time_elapsed | 194 |\n", + "| total_timesteps | 58074 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.284 |\n", + "| n_updates | 336 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5388 |\n", + "| fps | 297 |\n", + "| time_elapsed | 195 |\n", + "| total_timesteps | 58104 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.36 |\n", + "| n_updates | 337 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5392 |\n", + "| fps | 297 |\n", + "| time_elapsed | 195 |\n", + "| total_timesteps | 58128 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.239 |\n", + "| n_updates | 338 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5396 |\n", + "| fps | 297 |\n", + "| time_elapsed | 195 |\n", + "| total_timesteps | 58170 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.214 |\n", + "| n_updates | 340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5400 |\n", + "| fps | 296 |\n", + "| time_elapsed | 196 |\n", + "| total_timesteps | 58212 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.215 |\n", + "| n_updates | 342 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5404 |\n", + "| fps | 296 |\n", + "| time_elapsed | 196 |\n", + "| total_timesteps | 58266 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.59 |\n", + "| n_updates | 344 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5408 |\n", + "| fps | 296 |\n", + "| time_elapsed | 196 |\n", + "| total_timesteps | 58332 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.31 |\n", + "| n_updates | 347 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5412 |\n", + "| fps | 295 |\n", + "| time_elapsed | 197 |\n", + "| total_timesteps | 58404 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.53 |\n", + "| n_updates | 350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5416 |\n", + "| fps | 295 |\n", + "| time_elapsed | 197 |\n", + "| total_timesteps | 58452 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.33 |\n", + "| n_updates | 352 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5420 |\n", + "| fps | 295 |\n", + "| time_elapsed | 198 |\n", + "| total_timesteps | 58512 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.45 |\n", + "| n_updates | 354 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5424 |\n", + "| fps | 294 |\n", + "| time_elapsed | 198 |\n", + "| total_timesteps | 58554 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.36 |\n", + "| n_updates | 356 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5428 |\n", + "| fps | 294 |\n", + "| time_elapsed | 198 |\n", + "| total_timesteps | 58578 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.2 |\n", + "| n_updates | 357 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5432 |\n", + "| fps | 293 |\n", + "| time_elapsed | 199 |\n", + "| total_timesteps | 58698 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 362 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5436 |\n", + "| fps | 293 |\n", + "| time_elapsed | 200 |\n", + "| total_timesteps | 58752 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.148 |\n", + "| n_updates | 364 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5440 |\n", + "| fps | 293 |\n", + "| time_elapsed | 200 |\n", + "| total_timesteps | 58788 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.248 |\n", + "| n_updates | 366 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5444 |\n", + "| fps | 293 |\n", + "| time_elapsed | 200 |\n", + "| total_timesteps | 58830 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.279 |\n", + "| n_updates | 368 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5448 |\n", + "| fps | 292 |\n", + "| time_elapsed | 201 |\n", + "| total_timesteps | 58884 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.24 |\n", + "| n_updates | 370 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5452 |\n", + "| fps | 292 |\n", + "| time_elapsed | 201 |\n", + "| total_timesteps | 58926 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.3 |\n", + "| n_updates | 372 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5456 |\n", + "| fps | 292 |\n", + "| time_elapsed | 202 |\n", + "| total_timesteps | 59010 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.29 |\n", + "| n_updates | 375 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5460 |\n", + "| fps | 291 |\n", + "| time_elapsed | 202 |\n", + "| total_timesteps | 59070 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.161 |\n", + "| n_updates | 378 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5464 |\n", + "| fps | 291 |\n", + "| time_elapsed | 202 |\n", + "| total_timesteps | 59124 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.24 |\n", + "| n_updates | 380 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5468 |\n", + "| fps | 290 |\n", + "| time_elapsed | 203 |\n", + "| total_timesteps | 59190 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.158 |\n", + "| n_updates | 383 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5472 |\n", + "| fps | 290 |\n", + "| time_elapsed | 203 |\n", + "| total_timesteps | 59232 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.43 |\n", + "| n_updates | 384 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5476 |\n", + "| fps | 290 |\n", + "| time_elapsed | 204 |\n", + "| total_timesteps | 59274 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.187 |\n", + "| n_updates | 386 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5480 |\n", + "| fps | 290 |\n", + "| time_elapsed | 204 |\n", + "| total_timesteps | 59370 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.28 |\n", + "| n_updates | 390 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5484 |\n", + "| fps | 289 |\n", + "| time_elapsed | 205 |\n", + "| total_timesteps | 59448 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 393 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5488 |\n", + "| fps | 289 |\n", + "| time_elapsed | 205 |\n", + "| total_timesteps | 59484 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.22 |\n", + "| n_updates | 395 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5492 |\n", + "| fps | 289 |\n", + "| time_elapsed | 205 |\n", + "| total_timesteps | 59508 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.32 |\n", + "| n_updates | 396 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5496 |\n", + "| fps | 289 |\n", + "| time_elapsed | 206 |\n", + "| total_timesteps | 59544 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.29 |\n", + "| n_updates | 397 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5500 |\n", + "| fps | 288 |\n", + "| time_elapsed | 206 |\n", + "| total_timesteps | 59586 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 399 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5504 |\n", + "| fps | 288 |\n", + "| time_elapsed | 206 |\n", + "| total_timesteps | 59616 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.172 |\n", + "| n_updates | 400 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5508 |\n", + "| fps | 288 |\n", + "| time_elapsed | 206 |\n", + "| total_timesteps | 59658 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.223 |\n", + "| n_updates | 402 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5512 |\n", + "| fps | 287 |\n", + "| time_elapsed | 207 |\n", + "| total_timesteps | 59694 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 404 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5516 |\n", + "| fps | 287 |\n", + "| time_elapsed | 207 |\n", + "| total_timesteps | 59742 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.198 |\n", + "| n_updates | 406 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5520 |\n", + "| fps | 287 |\n", + "| time_elapsed | 207 |\n", + "| total_timesteps | 59784 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 407 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5524 |\n", + "| fps | 287 |\n", + "| time_elapsed | 208 |\n", + "| total_timesteps | 59814 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.277 |\n", + "| n_updates | 409 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5528 |\n", + "| fps | 287 |\n", + "| time_elapsed | 208 |\n", + "| total_timesteps | 59856 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.3 |\n", + "| n_updates | 410 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5532 |\n", + "| fps | 286 |\n", + "| time_elapsed | 208 |\n", + "| total_timesteps | 59898 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.37 |\n", + "| n_updates | 412 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5536 |\n", + "| fps | 286 |\n", + "| time_elapsed | 209 |\n", + "| total_timesteps | 59940 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 414 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5540 |\n", + "| fps | 286 |\n", + "| time_elapsed | 209 |\n", + "| total_timesteps | 59976 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.27 |\n", + "| n_updates | 415 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5544 |\n", + "| fps | 286 |\n", + "| time_elapsed | 209 |\n", + "| total_timesteps | 60012 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.16 |\n", + "| n_updates | 417 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5548 |\n", + "| fps | 285 |\n", + "| time_elapsed | 210 |\n", + "| total_timesteps | 60048 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4 |\n", + "| n_updates | 418 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5552 |\n", + "| fps | 285 |\n", + "| time_elapsed | 210 |\n", + "| total_timesteps | 60066 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.96 |\n", + "| n_updates | 419 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5556 |\n", + "| fps | 285 |\n", + "| time_elapsed | 210 |\n", + "| total_timesteps | 60102 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.41 |\n", + "| n_updates | 421 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5560 |\n", + "| fps | 285 |\n", + "| time_elapsed | 211 |\n", + "| total_timesteps | 60174 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.39 |\n", + "| n_updates | 424 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5564 |\n", + "| fps | 284 |\n", + "| time_elapsed | 211 |\n", + "| total_timesteps | 60228 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 426 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5568 |\n", + "| fps | 284 |\n", + "| time_elapsed | 211 |\n", + "| total_timesteps | 60270 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.02 |\n", + "| n_updates | 428 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5572 |\n", + "| fps | 284 |\n", + "| time_elapsed | 212 |\n", + "| total_timesteps | 60306 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.39 |\n", + "| n_updates | 429 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5576 |\n", + "| fps | 284 |\n", + "| time_elapsed | 212 |\n", + "| total_timesteps | 60348 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.44 |\n", + "| n_updates | 431 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5580 |\n", + "| fps | 284 |\n", + "| time_elapsed | 212 |\n", + "| total_timesteps | 60384 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.7 |\n", + "| n_updates | 432 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5584 |\n", + "| fps | 283 |\n", + "| time_elapsed | 213 |\n", + "| total_timesteps | 60450 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.51 |\n", + "| n_updates | 435 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5588 |\n", + "| fps | 283 |\n", + "| time_elapsed | 213 |\n", + "| total_timesteps | 60492 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.48 |\n", + "| n_updates | 437 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5592 |\n", + "| fps | 283 |\n", + "| time_elapsed | 213 |\n", + "| total_timesteps | 60522 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.04 |\n", + "| n_updates | 438 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5596 |\n", + "| fps | 282 |\n", + "| time_elapsed | 213 |\n", + "| total_timesteps | 60552 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.03 |\n", + "| n_updates | 439 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5600 |\n", + "| fps | 282 |\n", + "| time_elapsed | 214 |\n", + "| total_timesteps | 60594 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.3 |\n", + "| n_updates | 441 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5604 |\n", + "| fps | 282 |\n", + "| time_elapsed | 214 |\n", + "| total_timesteps | 60666 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.4 |\n", + "| n_updates | 444 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5608 |\n", + "| fps | 282 |\n", + "| time_elapsed | 215 |\n", + "| total_timesteps | 60732 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.32 |\n", + "| n_updates | 447 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5612 |\n", + "| fps | 281 |\n", + "| time_elapsed | 215 |\n", + "| total_timesteps | 60780 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.09 |\n", + "| n_updates | 449 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5616 |\n", + "| fps | 281 |\n", + "| time_elapsed | 215 |\n", + "| total_timesteps | 60816 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.35 |\n", + "| n_updates | 450 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5620 |\n", + "| fps | 281 |\n", + "| time_elapsed | 216 |\n", + "| total_timesteps | 60846 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.32 |\n", + "| n_updates | 452 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5624 |\n", + "| fps | 281 |\n", + "| time_elapsed | 216 |\n", + "| total_timesteps | 60912 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 454 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5628 |\n", + "| fps | 280 |\n", + "| time_elapsed | 217 |\n", + "| total_timesteps | 60954 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.17 |\n", + "| n_updates | 456 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5632 |\n", + "| fps | 280 |\n", + "| time_elapsed | 217 |\n", + "| total_timesteps | 61032 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.06 |\n", + "| n_updates | 459 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5636 |\n", + "| fps | 280 |\n", + "| time_elapsed | 218 |\n", + "| total_timesteps | 61092 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.34 |\n", + "| n_updates | 462 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5640 |\n", + "| fps | 279 |\n", + "| time_elapsed | 218 |\n", + "| total_timesteps | 61152 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.36 |\n", + "| n_updates | 464 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5644 |\n", + "| fps | 279 |\n", + "| time_elapsed | 218 |\n", + "| total_timesteps | 61182 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.24 |\n", + "| n_updates | 466 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5648 |\n", + "| fps | 279 |\n", + "| time_elapsed | 219 |\n", + "| total_timesteps | 61224 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.958 |\n", + "| n_updates | 467 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5652 |\n", + "| fps | 279 |\n", + "| time_elapsed | 219 |\n", + "| total_timesteps | 61260 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.16 |\n", + "| n_updates | 469 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5656 |\n", + "| fps | 279 |\n", + "| time_elapsed | 219 |\n", + "| total_timesteps | 61296 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.65 |\n", + "| n_updates | 470 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5660 |\n", + "| fps | 278 |\n", + "| time_elapsed | 220 |\n", + "| total_timesteps | 61326 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.25 |\n", + "| n_updates | 472 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5664 |\n", + "| fps | 278 |\n", + "| time_elapsed | 220 |\n", + "| total_timesteps | 61434 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.21 |\n", + "| n_updates | 476 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5668 |\n", + "| fps | 278 |\n", + "| time_elapsed | 221 |\n", + "| total_timesteps | 61488 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.11 |\n", + "| n_updates | 478 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5672 |\n", + "| fps | 277 |\n", + "| time_elapsed | 221 |\n", + "| total_timesteps | 61524 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 480 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5676 |\n", + "| fps | 277 |\n", + "| time_elapsed | 221 |\n", + "| total_timesteps | 61554 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.84 |\n", + "| n_updates | 481 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5680 |\n", + "| fps | 277 |\n", + "| time_elapsed | 222 |\n", + "| total_timesteps | 61608 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.16 |\n", + "| n_updates | 483 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5684 |\n", + "| fps | 277 |\n", + "| time_elapsed | 222 |\n", + "| total_timesteps | 61656 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 485 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5688 |\n", + "| fps | 276 |\n", + "| time_elapsed | 222 |\n", + "| total_timesteps | 61710 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.08 |\n", + "| n_updates | 488 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5692 |\n", + "| fps | 276 |\n", + "| time_elapsed | 223 |\n", + "| total_timesteps | 61752 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.09 |\n", + "| n_updates | 489 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5696 |\n", + "| fps | 276 |\n", + "| time_elapsed | 223 |\n", + "| total_timesteps | 61806 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.993 |\n", + "| n_updates | 492 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5700 |\n", + "| fps | 276 |\n", + "| time_elapsed | 224 |\n", + "| total_timesteps | 61860 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.05 |\n", + "| n_updates | 494 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5704 |\n", + "| fps | 275 |\n", + "| time_elapsed | 224 |\n", + "| total_timesteps | 61926 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.03 |\n", + "| n_updates | 497 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5708 |\n", + "| fps | 275 |\n", + "| time_elapsed | 224 |\n", + "| total_timesteps | 61944 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5712 |\n", + "| fps | 275 |\n", + "| time_elapsed | 225 |\n", + "| total_timesteps | 61980 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.21 |\n", + "| n_updates | 499 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5716 |\n", + "| fps | 275 |\n", + "| time_elapsed | 225 |\n", + "| total_timesteps | 62022 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 501 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5720 |\n", + "| fps | 274 |\n", + "| time_elapsed | 225 |\n", + "| total_timesteps | 62070 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.05 |\n", + "| n_updates | 503 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5724 |\n", + "| fps | 274 |\n", + "| time_elapsed | 226 |\n", + "| total_timesteps | 62148 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.33 |\n", + "| n_updates | 506 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5728 |\n", + "| fps | 274 |\n", + "| time_elapsed | 226 |\n", + "| total_timesteps | 62190 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.16 |\n", + "| n_updates | 508 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5732 |\n", + "| fps | 274 |\n", + "| time_elapsed | 226 |\n", + "| total_timesteps | 62226 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.21 |\n", + "| n_updates | 509 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5736 |\n", + "| fps | 274 |\n", + "| time_elapsed | 227 |\n", + "| total_timesteps | 62256 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.09 |\n", + "| n_updates | 510 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5740 |\n", + "| fps | 273 |\n", + "| time_elapsed | 227 |\n", + "| total_timesteps | 62274 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.2 |\n", + "| n_updates | 511 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5744 |\n", + "| fps | 273 |\n", + "| time_elapsed | 227 |\n", + "| total_timesteps | 62304 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.04 |\n", + "| n_updates | 512 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5748 |\n", + "| fps | 273 |\n", + "| time_elapsed | 227 |\n", + "| total_timesteps | 62352 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 514 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5752 |\n", + "| fps | 273 |\n", + "| time_elapsed | 228 |\n", + "| total_timesteps | 62412 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.36 |\n", + "| n_updates | 517 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5756 |\n", + "| fps | 272 |\n", + "| time_elapsed | 229 |\n", + "| total_timesteps | 62478 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.41 |\n", + "| n_updates | 520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5760 |\n", + "| fps | 272 |\n", + "| time_elapsed | 229 |\n", + "| total_timesteps | 62544 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.13 |\n", + "| n_updates | 522 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5764 |\n", + "| fps | 272 |\n", + "| time_elapsed | 229 |\n", + "| total_timesteps | 62574 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.1 |\n", + "| n_updates | 524 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5768 |\n", + "| fps | 272 |\n", + "| time_elapsed | 230 |\n", + "| total_timesteps | 62604 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.46 |\n", + "| n_updates | 525 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5772 |\n", + "| fps | 271 |\n", + "| time_elapsed | 230 |\n", + "| total_timesteps | 62646 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.13 |\n", + "| n_updates | 527 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5776 |\n", + "| fps | 271 |\n", + "| time_elapsed | 230 |\n", + "| total_timesteps | 62664 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5780 |\n", + "| fps | 271 |\n", + "| time_elapsed | 231 |\n", + "| total_timesteps | 62706 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.46 |\n", + "| n_updates | 529 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5784 |\n", + "| fps | 271 |\n", + "| time_elapsed | 231 |\n", + "| total_timesteps | 62754 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.05 |\n", + "| n_updates | 531 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5788 |\n", + "| fps | 270 |\n", + "| time_elapsed | 232 |\n", + "| total_timesteps | 62862 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.24 |\n", + "| n_updates | 536 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5792 |\n", + "| fps | 270 |\n", + "| time_elapsed | 232 |\n", + "| total_timesteps | 62916 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.23 |\n", + "| n_updates | 538 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5796 |\n", + "| fps | 269 |\n", + "| time_elapsed | 233 |\n", + "| total_timesteps | 62946 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.27 |\n", + "| n_updates | 539 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5800 |\n", + "| fps | 269 |\n", + "| time_elapsed | 233 |\n", + "| total_timesteps | 62970 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.16 |\n", + "| n_updates | 540 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5804 |\n", + "| fps | 269 |\n", + "| time_elapsed | 233 |\n", + "| total_timesteps | 63000 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 541 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5808 |\n", + "| fps | 269 |\n", + "| time_elapsed | 234 |\n", + "| total_timesteps | 63072 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.2 |\n", + "| n_updates | 544 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5812 |\n", + "| fps | 268 |\n", + "| time_elapsed | 235 |\n", + "| total_timesteps | 63186 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.05 |\n", + "| n_updates | 549 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5816 |\n", + "| fps | 268 |\n", + "| time_elapsed | 235 |\n", + "| total_timesteps | 63216 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.36 |\n", + "| n_updates | 550 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5820 |\n", + "| fps | 268 |\n", + "| time_elapsed | 235 |\n", + "| total_timesteps | 63252 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.48 |\n", + "| n_updates | 552 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5824 |\n", + "| fps | 268 |\n", + "| time_elapsed | 235 |\n", + "| total_timesteps | 63264 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5828 |\n", + "| fps | 267 |\n", + "| time_elapsed | 236 |\n", + "| total_timesteps | 63318 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.939 |\n", + "| n_updates | 555 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5832 |\n", + "| fps | 267 |\n", + "| time_elapsed | 236 |\n", + "| total_timesteps | 63354 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.07 |\n", + "| n_updates | 556 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5836 |\n", + "| fps | 267 |\n", + "| time_elapsed | 236 |\n", + "| total_timesteps | 63390 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.38 |\n", + "| n_updates | 558 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5840 |\n", + "| fps | 267 |\n", + "| time_elapsed | 237 |\n", + "| total_timesteps | 63504 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.13 |\n", + "| n_updates | 562 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5844 |\n", + "| fps | 267 |\n", + "| time_elapsed | 237 |\n", + "| total_timesteps | 63546 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.52 |\n", + "| n_updates | 564 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5848 |\n", + "| fps | 266 |\n", + "| time_elapsed | 238 |\n", + "| total_timesteps | 63576 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 565 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5852 |\n", + "| fps | 266 |\n", + "| time_elapsed | 238 |\n", + "| total_timesteps | 63612 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 567 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5856 |\n", + "| fps | 266 |\n", + "| time_elapsed | 238 |\n", + "| total_timesteps | 63660 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.62 |\n", + "| n_updates | 569 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5860 |\n", + "| fps | 266 |\n", + "| time_elapsed | 239 |\n", + "| total_timesteps | 63702 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.93 |\n", + "| n_updates | 571 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5864 |\n", + "| fps | 266 |\n", + "| time_elapsed | 239 |\n", + "| total_timesteps | 63744 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 572 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5868 |\n", + "| fps | 266 |\n", + "| time_elapsed | 239 |\n", + "| total_timesteps | 63768 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.51 |\n", + "| n_updates | 573 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5872 |\n", + "| fps | 265 |\n", + "| time_elapsed | 240 |\n", + "| total_timesteps | 63840 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.08 |\n", + "| n_updates | 576 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5876 |\n", + "| fps | 265 |\n", + "| time_elapsed | 240 |\n", + "| total_timesteps | 63912 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.35 |\n", + "| n_updates | 579 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5880 |\n", + "| fps | 265 |\n", + "| time_elapsed | 241 |\n", + "| total_timesteps | 63948 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.95 |\n", + "| n_updates | 581 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5884 |\n", + "| fps | 265 |\n", + "| time_elapsed | 241 |\n", + "| total_timesteps | 63984 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.18 |\n", + "| n_updates | 582 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5888 |\n", + "| fps | 264 |\n", + "| time_elapsed | 241 |\n", + "| total_timesteps | 64020 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.08 |\n", + "| n_updates | 584 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5892 |\n", + "| fps | 264 |\n", + "| time_elapsed | 242 |\n", + "| total_timesteps | 64080 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.29 |\n", + "| n_updates | 586 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5896 |\n", + "| fps | 264 |\n", + "| time_elapsed | 242 |\n", + "| total_timesteps | 64164 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.32 |\n", + "| n_updates | 590 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5900 |\n", + "| fps | 264 |\n", + "| time_elapsed | 242 |\n", + "| total_timesteps | 64200 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.2 |\n", + "| n_updates | 591 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5904 |\n", + "| fps | 264 |\n", + "| time_elapsed | 243 |\n", + "| total_timesteps | 64230 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 593 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5908 |\n", + "| fps | 263 |\n", + "| time_elapsed | 243 |\n", + "| total_timesteps | 64260 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 594 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5912 |\n", + "| fps | 263 |\n", + "| time_elapsed | 243 |\n", + "| total_timesteps | 64278 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.12 |\n", + "| n_updates | 595 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5916 |\n", + "| fps | 263 |\n", + "| time_elapsed | 243 |\n", + "| total_timesteps | 64320 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.09 |\n", + "| n_updates | 596 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5920 |\n", + "| fps | 263 |\n", + "| time_elapsed | 244 |\n", + "| total_timesteps | 64362 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.05 |\n", + "| n_updates | 598 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5924 |\n", + "| fps | 263 |\n", + "| time_elapsed | 244 |\n", + "| total_timesteps | 64434 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 601 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5928 |\n", + "| fps | 262 |\n", + "| time_elapsed | 245 |\n", + "| total_timesteps | 64476 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 603 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5932 |\n", + "| fps | 262 |\n", + "| time_elapsed | 245 |\n", + "| total_timesteps | 64536 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.03 |\n", + "| n_updates | 605 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5936 |\n", + "| fps | 262 |\n", + "| time_elapsed | 246 |\n", + "| total_timesteps | 64614 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.27 |\n", + "| n_updates | 609 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5940 |\n", + "| fps | 262 |\n", + "| time_elapsed | 246 |\n", + "| total_timesteps | 64650 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.65 |\n", + "| n_updates | 610 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5944 |\n", + "| fps | 262 |\n", + "| time_elapsed | 246 |\n", + "| total_timesteps | 64698 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.99 |\n", + "| n_updates | 612 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5948 |\n", + "| fps | 261 |\n", + "| time_elapsed | 247 |\n", + "| total_timesteps | 64752 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.55 |\n", + "| n_updates | 614 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5952 |\n", + "| fps | 261 |\n", + "| time_elapsed | 247 |\n", + "| total_timesteps | 64788 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.37 |\n", + "| n_updates | 616 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5956 |\n", + "| fps | 261 |\n", + "| time_elapsed | 247 |\n", + "| total_timesteps | 64836 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.47 |\n", + "| n_updates | 618 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5960 |\n", + "| fps | 261 |\n", + "| time_elapsed | 248 |\n", + "| total_timesteps | 64920 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.53 |\n", + "| n_updates | 621 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5964 |\n", + "| fps | 260 |\n", + "| time_elapsed | 248 |\n", + "| total_timesteps | 64980 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.51 |\n", + "| n_updates | 624 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5968 |\n", + "| fps | 260 |\n", + "| time_elapsed | 249 |\n", + "| total_timesteps | 65004 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 625 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5972 |\n", + "| fps | 260 |\n", + "| time_elapsed | 249 |\n", + "| total_timesteps | 65040 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 626 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5976 |\n", + "| fps | 260 |\n", + "| time_elapsed | 249 |\n", + "| total_timesteps | 65064 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.53 |\n", + "| n_updates | 627 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5980 |\n", + "| fps | 260 |\n", + "| time_elapsed | 250 |\n", + "| total_timesteps | 65106 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.21 |\n", + "| n_updates | 629 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5984 |\n", + "| fps | 260 |\n", + "| time_elapsed | 250 |\n", + "| total_timesteps | 65142 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 631 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5988 |\n", + "| fps | 260 |\n", + "| time_elapsed | 250 |\n", + "| total_timesteps | 65178 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.59 |\n", + "| n_updates | 632 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5992 |\n", + "| fps | 259 |\n", + "| time_elapsed | 250 |\n", + "| total_timesteps | 65208 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.922 |\n", + "| n_updates | 633 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 5996 |\n", + "| fps | 259 |\n", + "| time_elapsed | 251 |\n", + "| total_timesteps | 65250 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.27 |\n", + "| n_updates | 635 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6000 |\n", + "| fps | 259 |\n", + "| time_elapsed | 251 |\n", + "| total_timesteps | 65286 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.91 |\n", + "| n_updates | 637 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6004 |\n", + "| fps | 259 |\n", + "| time_elapsed | 251 |\n", + "| total_timesteps | 65322 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 638 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6008 |\n", + "| fps | 259 |\n", + "| time_elapsed | 251 |\n", + "| total_timesteps | 65352 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.3 |\n", + "| n_updates | 639 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6012 |\n", + "| fps | 259 |\n", + "| time_elapsed | 252 |\n", + "| total_timesteps | 65436 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.29 |\n", + "| n_updates | 643 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6016 |\n", + "| fps | 258 |\n", + "| time_elapsed | 253 |\n", + "| total_timesteps | 65508 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.43 |\n", + "| n_updates | 646 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6020 |\n", + "| fps | 258 |\n", + "| time_elapsed | 253 |\n", + "| total_timesteps | 65526 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.2 |\n", + "| n_updates | 647 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6024 |\n", + "| fps | 258 |\n", + "| time_elapsed | 253 |\n", + "| total_timesteps | 65562 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.25 |\n", + "| n_updates | 648 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6028 |\n", + "| fps | 258 |\n", + "| time_elapsed | 254 |\n", + "| total_timesteps | 65646 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 652 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6032 |\n", + "| fps | 258 |\n", + "| time_elapsed | 254 |\n", + "| total_timesteps | 65706 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.39 |\n", + "| n_updates | 654 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6036 |\n", + "| fps | 257 |\n", + "| time_elapsed | 254 |\n", + "| total_timesteps | 65742 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.34 |\n", + "| n_updates | 656 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6040 |\n", + "| fps | 257 |\n", + "| time_elapsed | 255 |\n", + "| total_timesteps | 65790 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.22 |\n", + "| n_updates | 658 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6044 |\n", + "| fps | 257 |\n", + "| time_elapsed | 255 |\n", + "| total_timesteps | 65826 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.12 |\n", + "| n_updates | 659 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6048 |\n", + "| fps | 257 |\n", + "| time_elapsed | 256 |\n", + "| total_timesteps | 65886 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.08 |\n", + "| n_updates | 662 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6052 |\n", + "| fps | 257 |\n", + "| time_elapsed | 256 |\n", + "| total_timesteps | 65958 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.21 |\n", + "| n_updates | 665 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6056 |\n", + "| fps | 256 |\n", + "| time_elapsed | 256 |\n", + "| total_timesteps | 66006 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.968 |\n", + "| n_updates | 667 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6060 |\n", + "| fps | 256 |\n", + "| time_elapsed | 257 |\n", + "| total_timesteps | 66090 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.59 |\n", + "| n_updates | 670 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6064 |\n", + "| fps | 256 |\n", + "| time_elapsed | 257 |\n", + "| total_timesteps | 66132 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.98 |\n", + "| n_updates | 672 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6068 |\n", + "| fps | 256 |\n", + "| time_elapsed | 258 |\n", + "| total_timesteps | 66174 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.87 |\n", + "| n_updates | 674 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6072 |\n", + "| fps | 256 |\n", + "| time_elapsed | 258 |\n", + "| total_timesteps | 66228 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 676 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6076 |\n", + "| fps | 255 |\n", + "| time_elapsed | 258 |\n", + "| total_timesteps | 66270 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.35 |\n", + "| n_updates | 678 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6080 |\n", + "| fps | 255 |\n", + "| time_elapsed | 259 |\n", + "| total_timesteps | 66318 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.07 |\n", + "| n_updates | 680 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6084 |\n", + "| fps | 255 |\n", + "| time_elapsed | 259 |\n", + "| total_timesteps | 66366 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.69 |\n", + "| n_updates | 682 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6088 |\n", + "| fps | 255 |\n", + "| time_elapsed | 260 |\n", + "| total_timesteps | 66402 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.74 |\n", + "| n_updates | 683 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6092 |\n", + "| fps | 255 |\n", + "| time_elapsed | 260 |\n", + "| total_timesteps | 66468 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.86 |\n", + "| n_updates | 686 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6096 |\n", + "| fps | 254 |\n", + "| time_elapsed | 260 |\n", + "| total_timesteps | 66510 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.05 |\n", + "| n_updates | 688 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6100 |\n", + "| fps | 254 |\n", + "| time_elapsed | 261 |\n", + "| total_timesteps | 66564 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.41 |\n", + "| n_updates | 690 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6104 |\n", + "| fps | 254 |\n", + "| time_elapsed | 261 |\n", + "| total_timesteps | 66654 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 694 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6108 |\n", + "| fps | 254 |\n", + "| time_elapsed | 262 |\n", + "| total_timesteps | 66696 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.39 |\n", + "| n_updates | 695 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6112 |\n", + "| fps | 254 |\n", + "| time_elapsed | 262 |\n", + "| total_timesteps | 66726 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.791 |\n", + "| n_updates | 697 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6116 |\n", + "| fps | 253 |\n", + "| time_elapsed | 262 |\n", + "| total_timesteps | 66780 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.39 |\n", + "| n_updates | 699 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6120 |\n", + "| fps | 253 |\n", + "| time_elapsed | 263 |\n", + "| total_timesteps | 66852 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.14 |\n", + "| n_updates | 702 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6124 |\n", + "| fps | 253 |\n", + "| time_elapsed | 263 |\n", + "| total_timesteps | 66888 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 703 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6128 |\n", + "| fps | 253 |\n", + "| time_elapsed | 264 |\n", + "| total_timesteps | 66930 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.999 |\n", + "| n_updates | 705 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6132 |\n", + "| fps | 253 |\n", + "| time_elapsed | 264 |\n", + "| total_timesteps | 66972 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.05 |\n", + "| n_updates | 707 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6136 |\n", + "| fps | 253 |\n", + "| time_elapsed | 264 |\n", + "| total_timesteps | 67002 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.13 |\n", + "| n_updates | 708 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6140 |\n", + "| fps | 253 |\n", + "| time_elapsed | 264 |\n", + "| total_timesteps | 67056 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.59 |\n", + "| n_updates | 710 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6144 |\n", + "| fps | 252 |\n", + "| time_elapsed | 265 |\n", + "| total_timesteps | 67098 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.4 |\n", + "| n_updates | 712 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.25 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6148 |\n", + "| fps | 252 |\n", + "| time_elapsed | 265 |\n", + "| total_timesteps | 67134 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.61 |\n", + "| n_updates | 714 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6152 |\n", + "| fps | 252 |\n", + "| time_elapsed | 266 |\n", + "| total_timesteps | 67182 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.19 |\n", + "| n_updates | 716 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6156 |\n", + "| fps | 252 |\n", + "| time_elapsed | 266 |\n", + "| total_timesteps | 67218 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.03 |\n", + "| n_updates | 717 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6160 |\n", + "| fps | 252 |\n", + "| time_elapsed | 266 |\n", + "| total_timesteps | 67278 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 720 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6164 |\n", + "| fps | 252 |\n", + "| time_elapsed | 267 |\n", + "| total_timesteps | 67320 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.26 |\n", + "| n_updates | 721 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6168 |\n", + "| fps | 251 |\n", + "| time_elapsed | 267 |\n", + "| total_timesteps | 67362 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 723 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6172 |\n", + "| fps | 251 |\n", + "| time_elapsed | 267 |\n", + "| total_timesteps | 67398 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.19 |\n", + "| n_updates | 725 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6176 |\n", + "| fps | 251 |\n", + "| time_elapsed | 268 |\n", + "| total_timesteps | 67440 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.32 |\n", + "| n_updates | 726 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6180 |\n", + "| fps | 251 |\n", + "| time_elapsed | 268 |\n", + "| total_timesteps | 67476 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.96 |\n", + "| n_updates | 728 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6184 |\n", + "| fps | 251 |\n", + "| time_elapsed | 268 |\n", + "| total_timesteps | 67518 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 730 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6188 |\n", + "| fps | 251 |\n", + "| time_elapsed | 269 |\n", + "| total_timesteps | 67590 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 733 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6192 |\n", + "| fps | 250 |\n", + "| time_elapsed | 269 |\n", + "| total_timesteps | 67674 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.56 |\n", + "| n_updates | 736 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6196 |\n", + "| fps | 250 |\n", + "| time_elapsed | 270 |\n", + "| total_timesteps | 67698 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.86 |\n", + "| n_updates | 737 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6200 |\n", + "| fps | 250 |\n", + "| time_elapsed | 270 |\n", + "| total_timesteps | 67776 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.36 |\n", + "| n_updates | 740 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6204 |\n", + "| fps | 250 |\n", + "| time_elapsed | 270 |\n", + "| total_timesteps | 67818 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.44 |\n", + "| n_updates | 742 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6208 |\n", + "| fps | 250 |\n", + "| time_elapsed | 271 |\n", + "| total_timesteps | 67854 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 744 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6212 |\n", + "| fps | 250 |\n", + "| time_elapsed | 271 |\n", + "| total_timesteps | 67890 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.15 |\n", + "| n_updates | 745 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.25 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6216 |\n", + "| fps | 249 |\n", + "| time_elapsed | 271 |\n", + "| total_timesteps | 67944 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3 |\n", + "| n_updates | 747 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.25 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6220 |\n", + "| fps | 249 |\n", + "| time_elapsed | 272 |\n", + "| total_timesteps | 67962 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.08 |\n", + "| n_updates | 748 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.23 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6224 |\n", + "| fps | 249 |\n", + "| time_elapsed | 272 |\n", + "| total_timesteps | 67998 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 750 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6228 |\n", + "| fps | 249 |\n", + "| time_elapsed | 272 |\n", + "| total_timesteps | 68046 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 752 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6232 |\n", + "| fps | 249 |\n", + "| time_elapsed | 273 |\n", + "| total_timesteps | 68088 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.16 |\n", + "| n_updates | 753 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6236 |\n", + "| fps | 249 |\n", + "| time_elapsed | 273 |\n", + "| total_timesteps | 68160 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.33 |\n", + "| n_updates | 756 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6240 |\n", + "| fps | 249 |\n", + "| time_elapsed | 273 |\n", + "| total_timesteps | 68184 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.24 |\n", + "| n_updates | 757 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6244 |\n", + "| fps | 248 |\n", + "| time_elapsed | 274 |\n", + "| total_timesteps | 68214 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.16 |\n", + "| n_updates | 759 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6248 |\n", + "| fps | 248 |\n", + "| time_elapsed | 274 |\n", + "| total_timesteps | 68262 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.42 |\n", + "| n_updates | 761 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6252 |\n", + "| fps | 248 |\n", + "| time_elapsed | 274 |\n", + "| total_timesteps | 68298 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.37 |\n", + "| n_updates | 762 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6256 |\n", + "| fps | 248 |\n", + "| time_elapsed | 275 |\n", + "| total_timesteps | 68334 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.09 |\n", + "| n_updates | 764 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6260 |\n", + "| fps | 248 |\n", + "| time_elapsed | 275 |\n", + "| total_timesteps | 68370 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.32 |\n", + "| n_updates | 765 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6264 |\n", + "| fps | 248 |\n", + "| time_elapsed | 275 |\n", + "| total_timesteps | 68436 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.45 |\n", + "| n_updates | 768 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6268 |\n", + "| fps | 248 |\n", + "| time_elapsed | 276 |\n", + "| total_timesteps | 68472 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.63 |\n", + "| n_updates | 769 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6272 |\n", + "| fps | 247 |\n", + "| time_elapsed | 276 |\n", + "| total_timesteps | 68526 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.07 |\n", + "| n_updates | 772 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6276 |\n", + "| fps | 247 |\n", + "| time_elapsed | 276 |\n", + "| total_timesteps | 68568 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 773 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6280 |\n", + "| fps | 247 |\n", + "| time_elapsed | 277 |\n", + "| total_timesteps | 68610 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.39 |\n", + "| n_updates | 775 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6284 |\n", + "| fps | 247 |\n", + "| time_elapsed | 277 |\n", + "| total_timesteps | 68646 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.23 |\n", + "| n_updates | 777 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6288 |\n", + "| fps | 247 |\n", + "| time_elapsed | 277 |\n", + "| total_timesteps | 68676 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.99 |\n", + "| n_updates | 778 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6292 |\n", + "| fps | 247 |\n", + "| time_elapsed | 277 |\n", + "| total_timesteps | 68706 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.18 |\n", + "| n_updates | 779 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6296 |\n", + "| fps | 247 |\n", + "| time_elapsed | 278 |\n", + "| total_timesteps | 68736 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.33 |\n", + "| n_updates | 780 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6300 |\n", + "| fps | 246 |\n", + "| time_elapsed | 278 |\n", + "| total_timesteps | 68796 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.6 |\n", + "| n_updates | 783 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6304 |\n", + "| fps | 246 |\n", + "| time_elapsed | 279 |\n", + "| total_timesteps | 68862 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 786 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6308 |\n", + "| fps | 246 |\n", + "| time_elapsed | 279 |\n", + "| total_timesteps | 68928 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.28 |\n", + "| n_updates | 788 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6312 |\n", + "| fps | 246 |\n", + "| time_elapsed | 280 |\n", + "| total_timesteps | 68976 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.36 |\n", + "| n_updates | 790 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6316 |\n", + "| fps | 246 |\n", + "| time_elapsed | 280 |\n", + "| total_timesteps | 69030 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.31 |\n", + "| n_updates | 793 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6320 |\n", + "| fps | 245 |\n", + "| time_elapsed | 280 |\n", + "| total_timesteps | 69054 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.07 |\n", + "| n_updates | 794 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6324 |\n", + "| fps | 245 |\n", + "| time_elapsed | 280 |\n", + "| total_timesteps | 69090 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.07 |\n", + "| n_updates | 795 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6328 |\n", + "| fps | 245 |\n", + "| time_elapsed | 281 |\n", + "| total_timesteps | 69132 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.41 |\n", + "| n_updates | 797 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6332 |\n", + "| fps | 245 |\n", + "| time_elapsed | 281 |\n", + "| total_timesteps | 69168 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.36 |\n", + "| n_updates | 798 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6336 |\n", + "| fps | 245 |\n", + "| time_elapsed | 281 |\n", + "| total_timesteps | 69216 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.26 |\n", + "| n_updates | 800 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6340 |\n", + "| fps | 245 |\n", + "| time_elapsed | 282 |\n", + "| total_timesteps | 69270 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.35 |\n", + "| n_updates | 803 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6344 |\n", + "| fps | 245 |\n", + "| time_elapsed | 282 |\n", + "| total_timesteps | 69312 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 804 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6348 |\n", + "| fps | 245 |\n", + "| time_elapsed | 282 |\n", + "| total_timesteps | 69348 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 806 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6352 |\n", + "| fps | 244 |\n", + "| time_elapsed | 283 |\n", + "| total_timesteps | 69420 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.17 |\n", + "| n_updates | 809 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6356 |\n", + "| fps | 244 |\n", + "| time_elapsed | 283 |\n", + "| total_timesteps | 69474 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.07 |\n", + "| n_updates | 811 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6360 |\n", + "| fps | 244 |\n", + "| time_elapsed | 284 |\n", + "| total_timesteps | 69522 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.53 |\n", + "| n_updates | 813 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6364 |\n", + "| fps | 244 |\n", + "| time_elapsed | 284 |\n", + "| total_timesteps | 69552 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.17 |\n", + "| n_updates | 814 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6368 |\n", + "| fps | 244 |\n", + "| time_elapsed | 284 |\n", + "| total_timesteps | 69576 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.29 |\n", + "| n_updates | 815 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6372 |\n", + "| fps | 244 |\n", + "| time_elapsed | 285 |\n", + "| total_timesteps | 69624 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.54 |\n", + "| n_updates | 817 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6376 |\n", + "| fps | 243 |\n", + "| time_elapsed | 286 |\n", + "| total_timesteps | 69750 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.03 |\n", + "| n_updates | 823 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6380 |\n", + "| fps | 243 |\n", + "| time_elapsed | 286 |\n", + "| total_timesteps | 69798 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.25 |\n", + "| n_updates | 825 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6384 |\n", + "| fps | 243 |\n", + "| time_elapsed | 286 |\n", + "| total_timesteps | 69840 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.21 |\n", + "| n_updates | 826 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6388 |\n", + "| fps | 243 |\n", + "| time_elapsed | 287 |\n", + "| total_timesteps | 69912 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 829 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6392 |\n", + "| fps | 243 |\n", + "| time_elapsed | 287 |\n", + "| total_timesteps | 69966 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 832 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6396 |\n", + "| fps | 242 |\n", + "| time_elapsed | 288 |\n", + "| total_timesteps | 70020 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.2 |\n", + "| n_updates | 834 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6400 |\n", + "| fps | 242 |\n", + "| time_elapsed | 288 |\n", + "| total_timesteps | 70092 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.24 |\n", + "| n_updates | 837 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6404 |\n", + "| fps | 242 |\n", + "| time_elapsed | 289 |\n", + "| total_timesteps | 70140 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.14 |\n", + "| n_updates | 839 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6408 |\n", + "| fps | 242 |\n", + "| time_elapsed | 289 |\n", + "| total_timesteps | 70182 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.43 |\n", + "| n_updates | 841 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6412 |\n", + "| fps | 242 |\n", + "| time_elapsed | 289 |\n", + "| total_timesteps | 70242 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.2 |\n", + "| n_updates | 843 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6416 |\n", + "| fps | 242 |\n", + "| time_elapsed | 290 |\n", + "| total_timesteps | 70272 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.38 |\n", + "| n_updates | 844 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6420 |\n", + "| fps | 242 |\n", + "| time_elapsed | 290 |\n", + "| total_timesteps | 70308 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.43 |\n", + "| n_updates | 846 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6424 |\n", + "| fps | 241 |\n", + "| time_elapsed | 290 |\n", + "| total_timesteps | 70362 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.24 |\n", + "| n_updates | 848 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6428 |\n", + "| fps | 241 |\n", + "| time_elapsed | 291 |\n", + "| total_timesteps | 70416 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.3 |\n", + "| n_updates | 850 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6432 |\n", + "| fps | 241 |\n", + "| time_elapsed | 291 |\n", + "| total_timesteps | 70440 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.22 |\n", + "| n_updates | 851 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6436 |\n", + "| fps | 241 |\n", + "| time_elapsed | 291 |\n", + "| total_timesteps | 70488 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.21 |\n", + "| n_updates | 853 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6440 |\n", + "| fps | 241 |\n", + "| time_elapsed | 292 |\n", + "| total_timesteps | 70524 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.14 |\n", + "| n_updates | 855 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6444 |\n", + "| fps | 241 |\n", + "| time_elapsed | 292 |\n", + "| total_timesteps | 70566 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.8 |\n", + "| n_updates | 857 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6448 |\n", + "| fps | 241 |\n", + "| time_elapsed | 292 |\n", + "| total_timesteps | 70602 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.64 |\n", + "| n_updates | 858 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6452 |\n", + "| fps | 241 |\n", + "| time_elapsed | 293 |\n", + "| total_timesteps | 70650 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.3 |\n", + "| n_updates | 860 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6456 |\n", + "| fps | 240 |\n", + "| time_elapsed | 293 |\n", + "| total_timesteps | 70722 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.57 |\n", + "| n_updates | 863 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6460 |\n", + "| fps | 240 |\n", + "| time_elapsed | 293 |\n", + "| total_timesteps | 70758 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.19 |\n", + "| n_updates | 865 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6464 |\n", + "| fps | 240 |\n", + "| time_elapsed | 294 |\n", + "| total_timesteps | 70794 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.16 |\n", + "| n_updates | 866 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6468 |\n", + "| fps | 240 |\n", + "| time_elapsed | 294 |\n", + "| total_timesteps | 70872 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.29 |\n", + "| n_updates | 869 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6472 |\n", + "| fps | 240 |\n", + "| time_elapsed | 295 |\n", + "| total_timesteps | 70926 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.24 |\n", + "| n_updates | 872 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6476 |\n", + "| fps | 240 |\n", + "| time_elapsed | 295 |\n", + "| total_timesteps | 70962 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.15 |\n", + "| n_updates | 873 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6480 |\n", + "| fps | 240 |\n", + "| time_elapsed | 295 |\n", + "| total_timesteps | 70980 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.5 |\n", + "| n_updates | 874 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6484 |\n", + "| fps | 240 |\n", + "| time_elapsed | 295 |\n", + "| total_timesteps | 71004 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 875 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6488 |\n", + "| fps | 239 |\n", + "| time_elapsed | 296 |\n", + "| total_timesteps | 71046 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.23 |\n", + "| n_updates | 877 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6492 |\n", + "| fps | 239 |\n", + "| time_elapsed | 296 |\n", + "| total_timesteps | 71124 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.42 |\n", + "| n_updates | 880 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6496 |\n", + "| fps | 239 |\n", + "| time_elapsed | 297 |\n", + "| total_timesteps | 71178 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.53 |\n", + "| n_updates | 882 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6500 |\n", + "| fps | 239 |\n", + "| time_elapsed | 297 |\n", + "| total_timesteps | 71244 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.31 |\n", + "| n_updates | 885 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6504 |\n", + "| fps | 239 |\n", + "| time_elapsed | 297 |\n", + "| total_timesteps | 71292 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.978 |\n", + "| n_updates | 887 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6508 |\n", + "| fps | 239 |\n", + "| time_elapsed | 298 |\n", + "| total_timesteps | 71322 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.35 |\n", + "| n_updates | 888 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6512 |\n", + "| fps | 239 |\n", + "| time_elapsed | 298 |\n", + "| total_timesteps | 71346 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.3 |\n", + "| n_updates | 889 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6516 |\n", + "| fps | 239 |\n", + "| time_elapsed | 298 |\n", + "| total_timesteps | 71388 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.28 |\n", + "| n_updates | 891 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6520 |\n", + "| fps | 238 |\n", + "| time_elapsed | 299 |\n", + "| total_timesteps | 71436 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 893 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6524 |\n", + "| fps | 238 |\n", + "| time_elapsed | 299 |\n", + "| total_timesteps | 71508 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 896 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6528 |\n", + "| fps | 238 |\n", + "| time_elapsed | 300 |\n", + "| total_timesteps | 71562 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.42 |\n", + "| n_updates | 898 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6532 |\n", + "| fps | 238 |\n", + "| time_elapsed | 300 |\n", + "| total_timesteps | 71598 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.31 |\n", + "| n_updates | 900 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6536 |\n", + "| fps | 238 |\n", + "| time_elapsed | 300 |\n", + "| total_timesteps | 71658 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.15 |\n", + "| n_updates | 902 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6540 |\n", + "| fps | 238 |\n", + "| time_elapsed | 301 |\n", + "| total_timesteps | 71706 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.7 |\n", + "| n_updates | 904 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6544 |\n", + "| fps | 237 |\n", + "| time_elapsed | 301 |\n", + "| total_timesteps | 71772 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.36 |\n", + "| n_updates | 907 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6548 |\n", + "| fps | 237 |\n", + "| time_elapsed | 302 |\n", + "| total_timesteps | 71838 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.2 |\n", + "| n_updates | 910 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6552 |\n", + "| fps | 237 |\n", + "| time_elapsed | 302 |\n", + "| total_timesteps | 71862 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.25 |\n", + "| n_updates | 911 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6556 |\n", + "| fps | 237 |\n", + "| time_elapsed | 302 |\n", + "| total_timesteps | 71886 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.27 |\n", + "| n_updates | 912 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6560 |\n", + "| fps | 237 |\n", + "| time_elapsed | 302 |\n", + "| total_timesteps | 71928 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.03 |\n", + "| n_updates | 913 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6564 |\n", + "| fps | 237 |\n", + "| time_elapsed | 303 |\n", + "| total_timesteps | 71970 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.89 |\n", + "| n_updates | 915 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6568 |\n", + "| fps | 237 |\n", + "| time_elapsed | 303 |\n", + "| total_timesteps | 72006 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.1 |\n", + "| n_updates | 917 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6572 |\n", + "| fps | 237 |\n", + "| time_elapsed | 303 |\n", + "| total_timesteps | 72060 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.25 |\n", + "| n_updates | 919 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6576 |\n", + "| fps | 236 |\n", + "| time_elapsed | 304 |\n", + "| total_timesteps | 72096 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.17 |\n", + "| n_updates | 920 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6580 |\n", + "| fps | 236 |\n", + "| time_elapsed | 304 |\n", + "| total_timesteps | 72120 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.43 |\n", + "| n_updates | 921 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6584 |\n", + "| fps | 236 |\n", + "| time_elapsed | 304 |\n", + "| total_timesteps | 72150 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.35 |\n", + "| n_updates | 923 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6588 |\n", + "| fps | 236 |\n", + "| time_elapsed | 305 |\n", + "| total_timesteps | 72198 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.32 |\n", + "| n_updates | 925 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6592 |\n", + "| fps | 236 |\n", + "| time_elapsed | 305 |\n", + "| total_timesteps | 72282 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.47 |\n", + "| n_updates | 928 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6596 |\n", + "| fps | 236 |\n", + "| time_elapsed | 306 |\n", + "| total_timesteps | 72366 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.25 |\n", + "| n_updates | 932 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6600 |\n", + "| fps | 236 |\n", + "| time_elapsed | 306 |\n", + "| total_timesteps | 72402 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 933 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6604 |\n", + "| fps | 236 |\n", + "| time_elapsed | 306 |\n", + "| total_timesteps | 72438 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.11 |\n", + "| n_updates | 935 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6608 |\n", + "| fps | 235 |\n", + "| time_elapsed | 307 |\n", + "| total_timesteps | 72510 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 938 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6612 |\n", + "| fps | 235 |\n", + "| time_elapsed | 307 |\n", + "| total_timesteps | 72576 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.24 |\n", + "| n_updates | 940 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6616 |\n", + "| fps | 235 |\n", + "| time_elapsed | 308 |\n", + "| total_timesteps | 72612 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.31 |\n", + "| n_updates | 942 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6620 |\n", + "| fps | 235 |\n", + "| time_elapsed | 308 |\n", + "| total_timesteps | 72642 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.07 |\n", + "| n_updates | 943 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6624 |\n", + "| fps | 235 |\n", + "| time_elapsed | 308 |\n", + "| total_timesteps | 72678 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 945 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6628 |\n", + "| fps | 235 |\n", + "| time_elapsed | 309 |\n", + "| total_timesteps | 72720 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.18 |\n", + "| n_updates | 946 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6632 |\n", + "| fps | 235 |\n", + "| time_elapsed | 309 |\n", + "| total_timesteps | 72780 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 949 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6636 |\n", + "| fps | 234 |\n", + "| time_elapsed | 310 |\n", + "| total_timesteps | 72912 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 954 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6640 |\n", + "| fps | 234 |\n", + "| time_elapsed | 310 |\n", + "| total_timesteps | 72954 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.2 |\n", + "| n_updates | 956 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6644 |\n", + "| fps | 234 |\n", + "| time_elapsed | 311 |\n", + "| total_timesteps | 72990 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.02 |\n", + "| n_updates | 958 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6648 |\n", + "| fps | 234 |\n", + "| time_elapsed | 311 |\n", + "| total_timesteps | 73020 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.26 |\n", + "| n_updates | 959 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6652 |\n", + "| fps | 234 |\n", + "| time_elapsed | 311 |\n", + "| total_timesteps | 73044 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.33 |\n", + "| n_updates | 960 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6656 |\n", + "| fps | 234 |\n", + "| time_elapsed | 311 |\n", + "| total_timesteps | 73074 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.41 |\n", + "| n_updates | 961 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6660 |\n", + "| fps | 234 |\n", + "| time_elapsed | 311 |\n", + "| total_timesteps | 73104 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.17 |\n", + "| n_updates | 962 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6664 |\n", + "| fps | 234 |\n", + "| time_elapsed | 312 |\n", + "| total_timesteps | 73140 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.36 |\n", + "| n_updates | 964 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6668 |\n", + "| fps | 234 |\n", + "| time_elapsed | 312 |\n", + "| total_timesteps | 73194 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.04 |\n", + "| n_updates | 966 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6672 |\n", + "| fps | 233 |\n", + "| time_elapsed | 313 |\n", + "| total_timesteps | 73242 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.947 |\n", + "| n_updates | 968 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6676 |\n", + "| fps | 233 |\n", + "| time_elapsed | 313 |\n", + "| total_timesteps | 73278 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.33 |\n", + "| n_updates | 970 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6680 |\n", + "| fps | 233 |\n", + "| time_elapsed | 313 |\n", + "| total_timesteps | 73362 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.18 |\n", + "| n_updates | 973 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6684 |\n", + "| fps | 233 |\n", + "| time_elapsed | 314 |\n", + "| total_timesteps | 73416 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.01 |\n", + "| n_updates | 975 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6688 |\n", + "| fps | 233 |\n", + "| time_elapsed | 314 |\n", + "| total_timesteps | 73446 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.33 |\n", + "| n_updates | 977 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6692 |\n", + "| fps | 233 |\n", + "| time_elapsed | 314 |\n", + "| total_timesteps | 73482 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.94 |\n", + "| n_updates | 978 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6696 |\n", + "| fps | 233 |\n", + "| time_elapsed | 315 |\n", + "| total_timesteps | 73524 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.08 |\n", + "| n_updates | 980 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6700 |\n", + "| fps | 233 |\n", + "| time_elapsed | 315 |\n", + "| total_timesteps | 73590 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.38 |\n", + "| n_updates | 983 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6704 |\n", + "| fps | 233 |\n", + "| time_elapsed | 315 |\n", + "| total_timesteps | 73632 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.52 |\n", + "| n_updates | 984 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6708 |\n", + "| fps | 232 |\n", + "| time_elapsed | 316 |\n", + "| total_timesteps | 73704 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.15 |\n", + "| n_updates | 987 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6712 |\n", + "| fps | 232 |\n", + "| time_elapsed | 316 |\n", + "| total_timesteps | 73752 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 989 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6716 |\n", + "| fps | 232 |\n", + "| time_elapsed | 317 |\n", + "| total_timesteps | 73788 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 991 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6720 |\n", + "| fps | 232 |\n", + "| time_elapsed | 317 |\n", + "| total_timesteps | 73854 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.28 |\n", + "| n_updates | 994 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6724 |\n", + "| fps | 232 |\n", + "| time_elapsed | 318 |\n", + "| total_timesteps | 73896 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.5 |\n", + "| n_updates | 995 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6728 |\n", + "| fps | 232 |\n", + "| time_elapsed | 318 |\n", + "| total_timesteps | 73926 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.95 |\n", + "| n_updates | 997 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6732 |\n", + "| fps | 232 |\n", + "| time_elapsed | 318 |\n", + "| total_timesteps | 73944 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6736 |\n", + "| fps | 232 |\n", + "| time_elapsed | 318 |\n", + "| total_timesteps | 73986 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.31 |\n", + "| n_updates | 999 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6740 |\n", + "| fps | 232 |\n", + "| time_elapsed | 318 |\n", + "| total_timesteps | 74016 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.17 |\n", + "| n_updates | 1000 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6744 |\n", + "| fps | 231 |\n", + "| time_elapsed | 319 |\n", + "| total_timesteps | 74046 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.36 |\n", + "| n_updates | 1002 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6748 |\n", + "| fps | 231 |\n", + "| time_elapsed | 319 |\n", + "| total_timesteps | 74082 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.29 |\n", + "| n_updates | 1003 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6752 |\n", + "| fps | 231 |\n", + "| time_elapsed | 319 |\n", + "| total_timesteps | 74112 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.97 |\n", + "| n_updates | 1004 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6756 |\n", + "| fps | 231 |\n", + "| time_elapsed | 320 |\n", + "| total_timesteps | 74148 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.12 |\n", + "| n_updates | 1006 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6760 |\n", + "| fps | 231 |\n", + "| time_elapsed | 320 |\n", + "| total_timesteps | 74190 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 1008 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6764 |\n", + "| fps | 231 |\n", + "| time_elapsed | 321 |\n", + "| total_timesteps | 74328 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.17 |\n", + "| n_updates | 1013 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6768 |\n", + "| fps | 231 |\n", + "| time_elapsed | 321 |\n", + "| total_timesteps | 74364 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.41 |\n", + "| n_updates | 1015 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6772 |\n", + "| fps | 231 |\n", + "| time_elapsed | 321 |\n", + "| total_timesteps | 74394 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.32 |\n", + "| n_updates | 1016 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6776 |\n", + "| fps | 231 |\n", + "| time_elapsed | 322 |\n", + "| total_timesteps | 74424 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.18 |\n", + "| n_updates | 1017 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6780 |\n", + "| fps | 230 |\n", + "| time_elapsed | 322 |\n", + "| total_timesteps | 74460 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.94 |\n", + "| n_updates | 1019 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6784 |\n", + "| fps | 230 |\n", + "| time_elapsed | 322 |\n", + "| total_timesteps | 74496 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.1 |\n", + "| n_updates | 1020 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6788 |\n", + "| fps | 230 |\n", + "| time_elapsed | 323 |\n", + "| total_timesteps | 74562 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.3 |\n", + "| n_updates | 1023 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6792 |\n", + "| fps | 230 |\n", + "| time_elapsed | 323 |\n", + "| total_timesteps | 74616 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.29 |\n", + "| n_updates | 1025 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6796 |\n", + "| fps | 230 |\n", + "| time_elapsed | 323 |\n", + "| total_timesteps | 74664 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.22 |\n", + "| n_updates | 1027 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6800 |\n", + "| fps | 230 |\n", + "| time_elapsed | 324 |\n", + "| total_timesteps | 74712 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 1029 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6804 |\n", + "| fps | 230 |\n", + "| time_elapsed | 324 |\n", + "| total_timesteps | 74736 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.45 |\n", + "| n_updates | 1030 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6808 |\n", + "| fps | 230 |\n", + "| time_elapsed | 324 |\n", + "| total_timesteps | 74766 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.21 |\n", + "| n_updates | 1032 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6812 |\n", + "| fps | 230 |\n", + "| time_elapsed | 325 |\n", + "| total_timesteps | 74814 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.56 |\n", + "| n_updates | 1034 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6816 |\n", + "| fps | 229 |\n", + "| time_elapsed | 325 |\n", + "| total_timesteps | 74844 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.06 |\n", + "| n_updates | 1035 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6820 |\n", + "| fps | 229 |\n", + "| time_elapsed | 325 |\n", + "| total_timesteps | 74868 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 1036 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6824 |\n", + "| fps | 229 |\n", + "| time_elapsed | 325 |\n", + "| total_timesteps | 74892 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 1037 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6828 |\n", + "| fps | 229 |\n", + "| time_elapsed | 326 |\n", + "| total_timesteps | 74922 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.25 |\n", + "| n_updates | 1038 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6832 |\n", + "| fps | 229 |\n", + "| time_elapsed | 326 |\n", + "| total_timesteps | 75030 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.56 |\n", + "| n_updates | 1043 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6836 |\n", + "| fps | 229 |\n", + "| time_elapsed | 327 |\n", + "| total_timesteps | 75054 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.34 |\n", + "| n_updates | 1044 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6840 |\n", + "| fps | 229 |\n", + "| time_elapsed | 327 |\n", + "| total_timesteps | 75066 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6844 |\n", + "| fps | 229 |\n", + "| time_elapsed | 327 |\n", + "| total_timesteps | 75096 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.51 |\n", + "| n_updates | 1045 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6848 |\n", + "| fps | 229 |\n", + "| time_elapsed | 327 |\n", + "| total_timesteps | 75156 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.36 |\n", + "| n_updates | 1048 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6852 |\n", + "| fps | 229 |\n", + "| time_elapsed | 328 |\n", + "| total_timesteps | 75240 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.16 |\n", + "| n_updates | 1051 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6856 |\n", + "| fps | 228 |\n", + "| time_elapsed | 328 |\n", + "| total_timesteps | 75270 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 1053 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6860 |\n", + "| fps | 228 |\n", + "| time_elapsed | 329 |\n", + "| total_timesteps | 75324 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.966 |\n", + "| n_updates | 1055 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6864 |\n", + "| fps | 228 |\n", + "| time_elapsed | 329 |\n", + "| total_timesteps | 75378 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 1057 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6868 |\n", + "| fps | 228 |\n", + "| time_elapsed | 330 |\n", + "| total_timesteps | 75450 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.15 |\n", + "| n_updates | 1060 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6872 |\n", + "| fps | 228 |\n", + "| time_elapsed | 330 |\n", + "| total_timesteps | 75498 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 1062 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6876 |\n", + "| fps | 228 |\n", + "| time_elapsed | 330 |\n", + "| total_timesteps | 75534 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.64 |\n", + "| n_updates | 1064 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6880 |\n", + "| fps | 228 |\n", + "| time_elapsed | 331 |\n", + "| total_timesteps | 75570 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.27 |\n", + "| n_updates | 1065 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6884 |\n", + "| fps | 228 |\n", + "| time_elapsed | 331 |\n", + "| total_timesteps | 75588 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.01 |\n", + "| n_updates | 1066 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6888 |\n", + "| fps | 228 |\n", + "| time_elapsed | 331 |\n", + "| total_timesteps | 75630 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 1068 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6892 |\n", + "| fps | 227 |\n", + "| time_elapsed | 331 |\n", + "| total_timesteps | 75690 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.3 |\n", + "| n_updates | 1070 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6896 |\n", + "| fps | 227 |\n", + "| time_elapsed | 332 |\n", + "| total_timesteps | 75744 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.39 |\n", + "| n_updates | 1072 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6900 |\n", + "| fps | 227 |\n", + "| time_elapsed | 332 |\n", + "| total_timesteps | 75786 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.06 |\n", + "| n_updates | 1074 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6904 |\n", + "| fps | 227 |\n", + "| time_elapsed | 333 |\n", + "| total_timesteps | 75822 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.39 |\n", + "| n_updates | 1076 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6908 |\n", + "| fps | 227 |\n", + "| time_elapsed | 333 |\n", + "| total_timesteps | 75858 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2 |\n", + "| n_updates | 1077 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6912 |\n", + "| fps | 227 |\n", + "| time_elapsed | 333 |\n", + "| total_timesteps | 75900 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.3 |\n", + "| n_updates | 1079 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6916 |\n", + "| fps | 227 |\n", + "| time_elapsed | 334 |\n", + "| total_timesteps | 75942 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.11 |\n", + "| n_updates | 1081 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6920 |\n", + "| fps | 227 |\n", + "| time_elapsed | 334 |\n", + "| total_timesteps | 76038 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.33 |\n", + "| n_updates | 1085 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6924 |\n", + "| fps | 227 |\n", + "| time_elapsed | 334 |\n", + "| total_timesteps | 76074 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 1086 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6928 |\n", + "| fps | 226 |\n", + "| time_elapsed | 335 |\n", + "| total_timesteps | 76116 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.13 |\n", + "| n_updates | 1088 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6932 |\n", + "| fps | 226 |\n", + "| time_elapsed | 335 |\n", + "| total_timesteps | 76140 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.55 |\n", + "| n_updates | 1089 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6936 |\n", + "| fps | 226 |\n", + "| time_elapsed | 335 |\n", + "| total_timesteps | 76194 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 1091 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6940 |\n", + "| fps | 226 |\n", + "| time_elapsed | 336 |\n", + "| total_timesteps | 76236 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.27 |\n", + "| n_updates | 1093 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6944 |\n", + "| fps | 226 |\n", + "| time_elapsed | 336 |\n", + "| total_timesteps | 76278 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 1095 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6948 |\n", + "| fps | 226 |\n", + "| time_elapsed | 337 |\n", + "| total_timesteps | 76356 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.1 |\n", + "| n_updates | 1098 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6952 |\n", + "| fps | 226 |\n", + "| time_elapsed | 337 |\n", + "| total_timesteps | 76392 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 1099 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6956 |\n", + "| fps | 226 |\n", + "| time_elapsed | 337 |\n", + "| total_timesteps | 76428 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 1101 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6960 |\n", + "| fps | 226 |\n", + "| time_elapsed | 338 |\n", + "| total_timesteps | 76494 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.21 |\n", + "| n_updates | 1104 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6964 |\n", + "| fps | 225 |\n", + "| time_elapsed | 338 |\n", + "| total_timesteps | 76542 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.03 |\n", + "| n_updates | 1106 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6968 |\n", + "| fps | 225 |\n", + "| time_elapsed | 338 |\n", + "| total_timesteps | 76584 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 1107 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6972 |\n", + "| fps | 225 |\n", + "| time_elapsed | 339 |\n", + "| total_timesteps | 76614 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.32 |\n", + "| n_updates | 1109 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6976 |\n", + "| fps | 225 |\n", + "| time_elapsed | 339 |\n", + "| total_timesteps | 76644 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.6 |\n", + "| n_updates | 1110 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6980 |\n", + "| fps | 225 |\n", + "| time_elapsed | 339 |\n", + "| total_timesteps | 76704 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.33 |\n", + "| n_updates | 1112 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6984 |\n", + "| fps | 225 |\n", + "| time_elapsed | 340 |\n", + "| total_timesteps | 76734 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.31 |\n", + "| n_updates | 1114 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6988 |\n", + "| fps | 225 |\n", + "| time_elapsed | 340 |\n", + "| total_timesteps | 76764 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.39 |\n", + "| n_updates | 1115 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6992 |\n", + "| fps | 225 |\n", + "| time_elapsed | 340 |\n", + "| total_timesteps | 76800 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.21 |\n", + "| n_updates | 1116 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 6996 |\n", + "| fps | 225 |\n", + "| time_elapsed | 341 |\n", + "| total_timesteps | 76830 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.33 |\n", + "| n_updates | 1118 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7000 |\n", + "| fps | 225 |\n", + "| time_elapsed | 341 |\n", + "| total_timesteps | 76842 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7004 |\n", + "| fps | 224 |\n", + "| time_elapsed | 342 |\n", + "| total_timesteps | 77016 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.18 |\n", + "| n_updates | 1125 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7008 |\n", + "| fps | 224 |\n", + "| time_elapsed | 342 |\n", + "| total_timesteps | 77040 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.44 |\n", + "| n_updates | 1126 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7012 |\n", + "| fps | 224 |\n", + "| time_elapsed | 342 |\n", + "| total_timesteps | 77076 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 1128 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7016 |\n", + "| fps | 224 |\n", + "| time_elapsed | 343 |\n", + "| total_timesteps | 77112 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.72 |\n", + "| n_updates | 1129 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7020 |\n", + "| fps | 224 |\n", + "| time_elapsed | 343 |\n", + "| total_timesteps | 77202 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 1133 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7024 |\n", + "| fps | 224 |\n", + "| time_elapsed | 344 |\n", + "| total_timesteps | 77250 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.25 |\n", + "| n_updates | 1135 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7028 |\n", + "| fps | 224 |\n", + "| time_elapsed | 344 |\n", + "| total_timesteps | 77286 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.28 |\n", + "| n_updates | 1137 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7032 |\n", + "| fps | 224 |\n", + "| time_elapsed | 344 |\n", + "| total_timesteps | 77352 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.3 |\n", + "| n_updates | 1139 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7036 |\n", + "| fps | 224 |\n", + "| time_elapsed | 345 |\n", + "| total_timesteps | 77412 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.01 |\n", + "| n_updates | 1142 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7040 |\n", + "| fps | 224 |\n", + "| time_elapsed | 345 |\n", + "| total_timesteps | 77442 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.4 |\n", + "| n_updates | 1143 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7044 |\n", + "| fps | 223 |\n", + "| time_elapsed | 346 |\n", + "| total_timesteps | 77496 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.94 |\n", + "| n_updates | 1145 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7048 |\n", + "| fps | 223 |\n", + "| time_elapsed | 346 |\n", + "| total_timesteps | 77532 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.15 |\n", + "| n_updates | 1147 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7052 |\n", + "| fps | 223 |\n", + "| time_elapsed | 346 |\n", + "| total_timesteps | 77574 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.963 |\n", + "| n_updates | 1149 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7056 |\n", + "| fps | 223 |\n", + "| time_elapsed | 347 |\n", + "| total_timesteps | 77610 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.25 |\n", + "| n_updates | 1150 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7060 |\n", + "| fps | 223 |\n", + "| time_elapsed | 347 |\n", + "| total_timesteps | 77646 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.09 |\n", + "| n_updates | 1152 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7064 |\n", + "| fps | 223 |\n", + "| time_elapsed | 347 |\n", + "| total_timesteps | 77688 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.09 |\n", + "| n_updates | 1153 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7068 |\n", + "| fps | 223 |\n", + "| time_elapsed | 348 |\n", + "| total_timesteps | 77736 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.34 |\n", + "| n_updates | 1155 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7072 |\n", + "| fps | 223 |\n", + "| time_elapsed | 348 |\n", + "| total_timesteps | 77796 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.11 |\n", + "| n_updates | 1158 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7076 |\n", + "| fps | 223 |\n", + "| time_elapsed | 348 |\n", + "| total_timesteps | 77856 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.33 |\n", + "| n_updates | 1160 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7080 |\n", + "| fps | 222 |\n", + "| time_elapsed | 349 |\n", + "| total_timesteps | 77916 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.19 |\n", + "| n_updates | 1163 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7084 |\n", + "| fps | 222 |\n", + "| time_elapsed | 349 |\n", + "| total_timesteps | 77958 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.979 |\n", + "| n_updates | 1165 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7088 |\n", + "| fps | 222 |\n", + "| time_elapsed | 350 |\n", + "| total_timesteps | 78006 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.28 |\n", + "| n_updates | 1167 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7092 |\n", + "| fps | 222 |\n", + "| time_elapsed | 350 |\n", + "| total_timesteps | 78042 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.41 |\n", + "| n_updates | 1168 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7096 |\n", + "| fps | 222 |\n", + "| time_elapsed | 350 |\n", + "| total_timesteps | 78090 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.35 |\n", + "| n_updates | 1170 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7100 |\n", + "| fps | 222 |\n", + "| time_elapsed | 351 |\n", + "| total_timesteps | 78126 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.27 |\n", + "| n_updates | 1172 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7104 |\n", + "| fps | 222 |\n", + "| time_elapsed | 351 |\n", + "| total_timesteps | 78204 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.49 |\n", + "| n_updates | 1175 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7108 |\n", + "| fps | 222 |\n", + "| time_elapsed | 351 |\n", + "| total_timesteps | 78240 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.21 |\n", + "| n_updates | 1176 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7112 |\n", + "| fps | 222 |\n", + "| time_elapsed | 352 |\n", + "| total_timesteps | 78288 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.14 |\n", + "| n_updates | 1178 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7116 |\n", + "| fps | 222 |\n", + "| time_elapsed | 352 |\n", + "| total_timesteps | 78324 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.58 |\n", + "| n_updates | 1180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7120 |\n", + "| fps | 222 |\n", + "| time_elapsed | 352 |\n", + "| total_timesteps | 78366 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.66 |\n", + "| n_updates | 1182 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7124 |\n", + "| fps | 221 |\n", + "| time_elapsed | 353 |\n", + "| total_timesteps | 78384 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7128 |\n", + "| fps | 221 |\n", + "| time_elapsed | 353 |\n", + "| total_timesteps | 78456 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.01 |\n", + "| n_updates | 1185 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7132 |\n", + "| fps | 221 |\n", + "| time_elapsed | 353 |\n", + "| total_timesteps | 78498 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 1187 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7136 |\n", + "| fps | 221 |\n", + "| time_elapsed | 354 |\n", + "| total_timesteps | 78564 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.39 |\n", + "| n_updates | 1190 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7140 |\n", + "| fps | 221 |\n", + "| time_elapsed | 354 |\n", + "| total_timesteps | 78612 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.29 |\n", + "| n_updates | 1192 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7144 |\n", + "| fps | 221 |\n", + "| time_elapsed | 355 |\n", + "| total_timesteps | 78630 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.851 |\n", + "| n_updates | 1193 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7148 |\n", + "| fps | 221 |\n", + "| time_elapsed | 355 |\n", + "| total_timesteps | 78654 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.29 |\n", + "| n_updates | 1194 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7152 |\n", + "| fps | 221 |\n", + "| time_elapsed | 355 |\n", + "| total_timesteps | 78714 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.4 |\n", + "| n_updates | 1196 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7156 |\n", + "| fps | 221 |\n", + "| time_elapsed | 355 |\n", + "| total_timesteps | 78750 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.04 |\n", + "| n_updates | 1198 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7160 |\n", + "| fps | 221 |\n", + "| time_elapsed | 356 |\n", + "| total_timesteps | 78786 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.967 |\n", + "| n_updates | 1199 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7164 |\n", + "| fps | 221 |\n", + "| time_elapsed | 356 |\n", + "| total_timesteps | 78816 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.22 |\n", + "| n_updates | 1200 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7168 |\n", + "| fps | 221 |\n", + "| time_elapsed | 356 |\n", + "| total_timesteps | 78864 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 1202 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7172 |\n", + "| fps | 220 |\n", + "| time_elapsed | 357 |\n", + "| total_timesteps | 78900 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.15 |\n", + "| n_updates | 1204 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7176 |\n", + "| fps | 220 |\n", + "| time_elapsed | 357 |\n", + "| total_timesteps | 78924 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.39 |\n", + "| n_updates | 1205 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7180 |\n", + "| fps | 220 |\n", + "| time_elapsed | 357 |\n", + "| total_timesteps | 78978 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.58 |\n", + "| n_updates | 1207 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7184 |\n", + "| fps | 220 |\n", + "| time_elapsed | 357 |\n", + "| total_timesteps | 79008 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.46 |\n", + "| n_updates | 1208 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7188 |\n", + "| fps | 220 |\n", + "| time_elapsed | 358 |\n", + "| total_timesteps | 79038 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 1210 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7192 |\n", + "| fps | 220 |\n", + "| time_elapsed | 358 |\n", + "| total_timesteps | 79062 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 1211 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7196 |\n", + "| fps | 220 |\n", + "| time_elapsed | 358 |\n", + "| total_timesteps | 79104 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.14 |\n", + "| n_updates | 1212 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7200 |\n", + "| fps | 220 |\n", + "| time_elapsed | 359 |\n", + "| total_timesteps | 79146 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 1214 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7204 |\n", + "| fps | 220 |\n", + "| time_elapsed | 359 |\n", + "| total_timesteps | 79170 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.53 |\n", + "| n_updates | 1215 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7208 |\n", + "| fps | 220 |\n", + "| time_elapsed | 359 |\n", + "| total_timesteps | 79194 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.05 |\n", + "| n_updates | 1216 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7212 |\n", + "| fps | 220 |\n", + "| time_elapsed | 359 |\n", + "| total_timesteps | 79230 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.11 |\n", + "| n_updates | 1218 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7216 |\n", + "| fps | 220 |\n", + "| time_elapsed | 360 |\n", + "| total_timesteps | 79284 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.27 |\n", + "| n_updates | 1220 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7220 |\n", + "| fps | 219 |\n", + "| time_elapsed | 360 |\n", + "| total_timesteps | 79332 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 1222 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7224 |\n", + "| fps | 219 |\n", + "| time_elapsed | 360 |\n", + "| total_timesteps | 79362 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.49 |\n", + "| n_updates | 1223 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7228 |\n", + "| fps | 219 |\n", + "| time_elapsed | 361 |\n", + "| total_timesteps | 79422 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.11 |\n", + "| n_updates | 1226 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7232 |\n", + "| fps | 219 |\n", + "| time_elapsed | 361 |\n", + "| total_timesteps | 79464 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.43 |\n", + "| n_updates | 1227 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7236 |\n", + "| fps | 219 |\n", + "| time_elapsed | 361 |\n", + "| total_timesteps | 79488 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 1228 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7240 |\n", + "| fps | 219 |\n", + "| time_elapsed | 362 |\n", + "| total_timesteps | 79524 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 1230 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7244 |\n", + "| fps | 219 |\n", + "| time_elapsed | 362 |\n", + "| total_timesteps | 79560 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.23 |\n", + "| n_updates | 1231 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7248 |\n", + "| fps | 219 |\n", + "| time_elapsed | 362 |\n", + "| total_timesteps | 79596 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.41 |\n", + "| n_updates | 1233 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7252 |\n", + "| fps | 219 |\n", + "| time_elapsed | 363 |\n", + "| total_timesteps | 79662 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 1236 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7256 |\n", + "| fps | 219 |\n", + "| time_elapsed | 363 |\n", + "| total_timesteps | 79704 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 1237 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7260 |\n", + "| fps | 219 |\n", + "| time_elapsed | 363 |\n", + "| total_timesteps | 79746 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.07 |\n", + "| n_updates | 1239 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7264 |\n", + "| fps | 219 |\n", + "| time_elapsed | 364 |\n", + "| total_timesteps | 79782 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.49 |\n", + "| n_updates | 1241 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7268 |\n", + "| fps | 219 |\n", + "| time_elapsed | 364 |\n", + "| total_timesteps | 79818 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 1242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7272 |\n", + "| fps | 218 |\n", + "| time_elapsed | 364 |\n", + "| total_timesteps | 79884 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.24 |\n", + "| n_updates | 1245 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7276 |\n", + "| fps | 218 |\n", + "| time_elapsed | 365 |\n", + "| total_timesteps | 79950 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.24 |\n", + "| n_updates | 1248 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7280 |\n", + "| fps | 218 |\n", + "| time_elapsed | 365 |\n", + "| total_timesteps | 79992 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.36 |\n", + "| n_updates | 1249 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7284 |\n", + "| fps | 218 |\n", + "| time_elapsed | 366 |\n", + "| total_timesteps | 80034 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.1 |\n", + "| n_updates | 1251 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7288 |\n", + "| fps | 218 |\n", + "| time_elapsed | 366 |\n", + "| total_timesteps | 80076 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.29 |\n", + "| n_updates | 1253 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7292 |\n", + "| fps | 218 |\n", + "| time_elapsed | 366 |\n", + "| total_timesteps | 80124 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.11 |\n", + "| n_updates | 1255 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7296 |\n", + "| fps | 218 |\n", + "| time_elapsed | 367 |\n", + "| total_timesteps | 80184 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 1257 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7300 |\n", + "| fps | 218 |\n", + "| time_elapsed | 367 |\n", + "| total_timesteps | 80256 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 1260 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7304 |\n", + "| fps | 218 |\n", + "| time_elapsed | 368 |\n", + "| total_timesteps | 80310 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.1 |\n", + "| n_updates | 1263 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7308 |\n", + "| fps | 218 |\n", + "| time_elapsed | 368 |\n", + "| total_timesteps | 80352 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.43 |\n", + "| n_updates | 1264 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7312 |\n", + "| fps | 217 |\n", + "| time_elapsed | 369 |\n", + "| total_timesteps | 80418 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.07 |\n", + "| n_updates | 1267 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7316 |\n", + "| fps | 217 |\n", + "| time_elapsed | 369 |\n", + "| total_timesteps | 80454 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.21 |\n", + "| n_updates | 1269 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7320 |\n", + "| fps | 217 |\n", + "| time_elapsed | 369 |\n", + "| total_timesteps | 80514 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.24 |\n", + "| n_updates | 1271 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7324 |\n", + "| fps | 217 |\n", + "| time_elapsed | 370 |\n", + "| total_timesteps | 80580 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.45 |\n", + "| n_updates | 1274 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7328 |\n", + "| fps | 217 |\n", + "| time_elapsed | 370 |\n", + "| total_timesteps | 80634 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.36 |\n", + "| n_updates | 1276 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7332 |\n", + "| fps | 217 |\n", + "| time_elapsed | 371 |\n", + "| total_timesteps | 80676 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.27 |\n", + "| n_updates | 1278 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7336 |\n", + "| fps | 217 |\n", + "| time_elapsed | 371 |\n", + "| total_timesteps | 80712 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.19 |\n", + "| n_updates | 1279 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7340 |\n", + "| fps | 217 |\n", + "| time_elapsed | 371 |\n", + "| total_timesteps | 80748 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.53 |\n", + "| n_updates | 1281 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7344 |\n", + "| fps | 217 |\n", + "| time_elapsed | 371 |\n", + "| total_timesteps | 80784 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.93 |\n", + "| n_updates | 1282 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7348 |\n", + "| fps | 217 |\n", + "| time_elapsed | 372 |\n", + "| total_timesteps | 80826 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.28 |\n", + "| n_updates | 1284 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7352 |\n", + "| fps | 217 |\n", + "| time_elapsed | 372 |\n", + "| total_timesteps | 80874 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.4 |\n", + "| n_updates | 1286 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7356 |\n", + "| fps | 216 |\n", + "| time_elapsed | 372 |\n", + "| total_timesteps | 80904 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.11 |\n", + "| n_updates | 1287 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7360 |\n", + "| fps | 216 |\n", + "| time_elapsed | 373 |\n", + "| total_timesteps | 80940 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.6 |\n", + "| n_updates | 1289 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7364 |\n", + "| fps | 216 |\n", + "| time_elapsed | 374 |\n", + "| total_timesteps | 81036 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.32 |\n", + "| n_updates | 1293 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7368 |\n", + "| fps | 216 |\n", + "| time_elapsed | 374 |\n", + "| total_timesteps | 81078 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 1295 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7372 |\n", + "| fps | 216 |\n", + "| time_elapsed | 374 |\n", + "| total_timesteps | 81114 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.35 |\n", + "| n_updates | 1296 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7376 |\n", + "| fps | 216 |\n", + "| time_elapsed | 375 |\n", + "| total_timesteps | 81156 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.17 |\n", + "| n_updates | 1298 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7380 |\n", + "| fps | 216 |\n", + "| time_elapsed | 375 |\n", + "| total_timesteps | 81246 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.4 |\n", + "| n_updates | 1302 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7384 |\n", + "| fps | 216 |\n", + "| time_elapsed | 376 |\n", + "| total_timesteps | 81306 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.32 |\n", + "| n_updates | 1304 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7388 |\n", + "| fps | 215 |\n", + "| time_elapsed | 376 |\n", + "| total_timesteps | 81372 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.13 |\n", + "| n_updates | 1307 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7392 |\n", + "| fps | 215 |\n", + "| time_elapsed | 377 |\n", + "| total_timesteps | 81414 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.83 |\n", + "| n_updates | 1309 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7396 |\n", + "| fps | 215 |\n", + "| time_elapsed | 377 |\n", + "| total_timesteps | 81444 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.32 |\n", + "| n_updates | 1310 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7400 |\n", + "| fps | 215 |\n", + "| time_elapsed | 377 |\n", + "| total_timesteps | 81498 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.14 |\n", + "| n_updates | 1312 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7404 |\n", + "| fps | 215 |\n", + "| time_elapsed | 378 |\n", + "| total_timesteps | 81558 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.947 |\n", + "| n_updates | 1315 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7408 |\n", + "| fps | 215 |\n", + "| time_elapsed | 378 |\n", + "| total_timesteps | 81624 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.44 |\n", + "| n_updates | 1317 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7412 |\n", + "| fps | 215 |\n", + "| time_elapsed | 379 |\n", + "| total_timesteps | 81654 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 1319 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7416 |\n", + "| fps | 215 |\n", + "| time_elapsed | 379 |\n", + "| total_timesteps | 81684 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.53 |\n", + "| n_updates | 1320 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7420 |\n", + "| fps | 215 |\n", + "| time_elapsed | 379 |\n", + "| total_timesteps | 81714 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.99 |\n", + "| n_updates | 1321 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7424 |\n", + "| fps | 215 |\n", + "| time_elapsed | 379 |\n", + "| total_timesteps | 81750 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.3 |\n", + "| n_updates | 1323 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7428 |\n", + "| fps | 215 |\n", + "| time_elapsed | 380 |\n", + "| total_timesteps | 81810 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.14 |\n", + "| n_updates | 1325 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7432 |\n", + "| fps | 215 |\n", + "| time_elapsed | 380 |\n", + "| total_timesteps | 81846 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.55 |\n", + "| n_updates | 1327 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7436 |\n", + "| fps | 214 |\n", + "| time_elapsed | 381 |\n", + "| total_timesteps | 81912 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 1329 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7440 |\n", + "| fps | 214 |\n", + "| time_elapsed | 381 |\n", + "| total_timesteps | 82020 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.03 |\n", + "| n_updates | 1334 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7444 |\n", + "| fps | 214 |\n", + "| time_elapsed | 382 |\n", + "| total_timesteps | 82104 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.2 |\n", + "| n_updates | 1337 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7448 |\n", + "| fps | 214 |\n", + "| time_elapsed | 382 |\n", + "| total_timesteps | 82134 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.62 |\n", + "| n_updates | 1339 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7452 |\n", + "| fps | 214 |\n", + "| time_elapsed | 383 |\n", + "| total_timesteps | 82158 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.35 |\n", + "| n_updates | 1340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7456 |\n", + "| fps | 214 |\n", + "| time_elapsed | 383 |\n", + "| total_timesteps | 82194 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.32 |\n", + "| n_updates | 1341 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7460 |\n", + "| fps | 214 |\n", + "| time_elapsed | 383 |\n", + "| total_timesteps | 82242 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.14 |\n", + "| n_updates | 1343 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7464 |\n", + "| fps | 214 |\n", + "| time_elapsed | 383 |\n", + "| total_timesteps | 82278 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.16 |\n", + "| n_updates | 1345 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7468 |\n", + "| fps | 214 |\n", + "| time_elapsed | 384 |\n", + "| total_timesteps | 82320 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.24 |\n", + "| n_updates | 1346 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7472 |\n", + "| fps | 214 |\n", + "| time_elapsed | 384 |\n", + "| total_timesteps | 82368 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.991 |\n", + "| n_updates | 1348 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7476 |\n", + "| fps | 214 |\n", + "| time_elapsed | 384 |\n", + "| total_timesteps | 82410 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 1350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7480 |\n", + "| fps | 213 |\n", + "| time_elapsed | 385 |\n", + "| total_timesteps | 82446 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.34 |\n", + "| n_updates | 1352 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7484 |\n", + "| fps | 213 |\n", + "| time_elapsed | 385 |\n", + "| total_timesteps | 82476 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.19 |\n", + "| n_updates | 1353 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7488 |\n", + "| fps | 213 |\n", + "| time_elapsed | 385 |\n", + "| total_timesteps | 82524 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.24 |\n", + "| n_updates | 1355 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7492 |\n", + "| fps | 213 |\n", + "| time_elapsed | 386 |\n", + "| total_timesteps | 82662 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.23 |\n", + "| n_updates | 1361 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7496 |\n", + "| fps | 213 |\n", + "| time_elapsed | 387 |\n", + "| total_timesteps | 82692 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 1362 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7500 |\n", + "| fps | 213 |\n", + "| time_elapsed | 387 |\n", + "| total_timesteps | 82716 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 1363 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7504 |\n", + "| fps | 213 |\n", + "| time_elapsed | 387 |\n", + "| total_timesteps | 82746 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.08 |\n", + "| n_updates | 1364 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7508 |\n", + "| fps | 213 |\n", + "| time_elapsed | 387 |\n", + "| total_timesteps | 82770 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.16 |\n", + "| n_updates | 1365 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7512 |\n", + "| fps | 213 |\n", + "| time_elapsed | 388 |\n", + "| total_timesteps | 82806 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.56 |\n", + "| n_updates | 1367 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7516 |\n", + "| fps | 213 |\n", + "| time_elapsed | 388 |\n", + "| total_timesteps | 82836 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.21 |\n", + "| n_updates | 1368 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7520 |\n", + "| fps | 213 |\n", + "| time_elapsed | 388 |\n", + "| total_timesteps | 82878 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.11 |\n", + "| n_updates | 1370 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7524 |\n", + "| fps | 213 |\n", + "| time_elapsed | 388 |\n", + "| total_timesteps | 82914 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.23 |\n", + "| n_updates | 1371 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7528 |\n", + "| fps | 213 |\n", + "| time_elapsed | 389 |\n", + "| total_timesteps | 82944 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.35 |\n", + "| n_updates | 1372 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7532 |\n", + "| fps | 213 |\n", + "| time_elapsed | 389 |\n", + "| total_timesteps | 82986 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.04 |\n", + "| n_updates | 1374 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7536 |\n", + "| fps | 212 |\n", + "| time_elapsed | 389 |\n", + "| total_timesteps | 83022 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.14 |\n", + "| n_updates | 1376 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7540 |\n", + "| fps | 212 |\n", + "| time_elapsed | 390 |\n", + "| total_timesteps | 83058 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.47 |\n", + "| n_updates | 1377 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7544 |\n", + "| fps | 212 |\n", + "| time_elapsed | 390 |\n", + "| total_timesteps | 83106 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 1379 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7548 |\n", + "| fps | 212 |\n", + "| time_elapsed | 390 |\n", + "| total_timesteps | 83118 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.4 |\n", + "| n_updates | 1380 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7552 |\n", + "| fps | 212 |\n", + "| time_elapsed | 390 |\n", + "| total_timesteps | 83148 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.36 |\n", + "| n_updates | 1381 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7556 |\n", + "| fps | 212 |\n", + "| time_elapsed | 391 |\n", + "| total_timesteps | 83178 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.21 |\n", + "| n_updates | 1382 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7560 |\n", + "| fps | 212 |\n", + "| time_elapsed | 391 |\n", + "| total_timesteps | 83214 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 1384 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7564 |\n", + "| fps | 212 |\n", + "| time_elapsed | 392 |\n", + "| total_timesteps | 83358 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.43 |\n", + "| n_updates | 1390 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7568 |\n", + "| fps | 212 |\n", + "| time_elapsed | 392 |\n", + "| total_timesteps | 83388 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.39 |\n", + "| n_updates | 1391 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7572 |\n", + "| fps | 212 |\n", + "| time_elapsed | 392 |\n", + "| total_timesteps | 83418 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.14 |\n", + "| n_updates | 1392 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7576 |\n", + "| fps | 212 |\n", + "| time_elapsed | 393 |\n", + "| total_timesteps | 83454 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.14 |\n", + "| n_updates | 1394 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7580 |\n", + "| fps | 212 |\n", + "| time_elapsed | 393 |\n", + "| total_timesteps | 83478 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 1395 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7584 |\n", + "| fps | 212 |\n", + "| time_elapsed | 393 |\n", + "| total_timesteps | 83502 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.38 |\n", + "| n_updates | 1396 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7588 |\n", + "| fps | 212 |\n", + "| time_elapsed | 393 |\n", + "| total_timesteps | 83532 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 1397 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7592 |\n", + "| fps | 211 |\n", + "| time_elapsed | 394 |\n", + "| total_timesteps | 83628 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.03 |\n", + "| n_updates | 1401 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7596 |\n", + "| fps | 211 |\n", + "| time_elapsed | 394 |\n", + "| total_timesteps | 83682 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.1 |\n", + "| n_updates | 1403 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7600 |\n", + "| fps | 211 |\n", + "| time_elapsed | 395 |\n", + "| total_timesteps | 83718 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.31 |\n", + "| n_updates | 1405 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7604 |\n", + "| fps | 211 |\n", + "| time_elapsed | 395 |\n", + "| total_timesteps | 83754 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.75 |\n", + "| n_updates | 1406 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7608 |\n", + "| fps | 211 |\n", + "| time_elapsed | 396 |\n", + "| total_timesteps | 83838 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 1410 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7612 |\n", + "| fps | 211 |\n", + "| time_elapsed | 396 |\n", + "| total_timesteps | 83910 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.68 |\n", + "| n_updates | 1413 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7616 |\n", + "| fps | 211 |\n", + "| time_elapsed | 397 |\n", + "| total_timesteps | 83958 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 1415 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7620 |\n", + "| fps | 211 |\n", + "| time_elapsed | 397 |\n", + "| total_timesteps | 83988 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.39 |\n", + "| n_updates | 1416 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7624 |\n", + "| fps | 211 |\n", + "| time_elapsed | 397 |\n", + "| total_timesteps | 84030 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.17 |\n", + "| n_updates | 1418 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7628 |\n", + "| fps | 211 |\n", + "| time_elapsed | 397 |\n", + "| total_timesteps | 84060 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.32 |\n", + "| n_updates | 1419 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7632 |\n", + "| fps | 211 |\n", + "| time_elapsed | 398 |\n", + "| total_timesteps | 84126 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.19 |\n", + "| n_updates | 1422 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7636 |\n", + "| fps | 211 |\n", + "| time_elapsed | 398 |\n", + "| total_timesteps | 84162 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.08 |\n", + "| n_updates | 1423 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7640 |\n", + "| fps | 210 |\n", + "| time_elapsed | 399 |\n", + "| total_timesteps | 84204 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 1425 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7644 |\n", + "| fps | 210 |\n", + "| time_elapsed | 399 |\n", + "| total_timesteps | 84270 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.71 |\n", + "| n_updates | 1428 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7648 |\n", + "| fps | 210 |\n", + "| time_elapsed | 399 |\n", + "| total_timesteps | 84312 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.2 |\n", + "| n_updates | 1429 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7652 |\n", + "| fps | 210 |\n", + "| time_elapsed | 400 |\n", + "| total_timesteps | 84348 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.64 |\n", + "| n_updates | 1431 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7656 |\n", + "| fps | 210 |\n", + "| time_elapsed | 400 |\n", + "| total_timesteps | 84396 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.2 |\n", + "| n_updates | 1433 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7660 |\n", + "| fps | 210 |\n", + "| time_elapsed | 400 |\n", + "| total_timesteps | 84432 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.633 |\n", + "| n_updates | 1434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7664 |\n", + "| fps | 210 |\n", + "| time_elapsed | 401 |\n", + "| total_timesteps | 84474 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.993 |\n", + "| n_updates | 1436 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7668 |\n", + "| fps | 210 |\n", + "| time_elapsed | 401 |\n", + "| total_timesteps | 84516 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.26 |\n", + "| n_updates | 1438 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7672 |\n", + "| fps | 210 |\n", + "| time_elapsed | 401 |\n", + "| total_timesteps | 84564 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.39 |\n", + "| n_updates | 1440 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7676 |\n", + "| fps | 210 |\n", + "| time_elapsed | 402 |\n", + "| total_timesteps | 84660 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.46 |\n", + "| n_updates | 1444 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7680 |\n", + "| fps | 210 |\n", + "| time_elapsed | 403 |\n", + "| total_timesteps | 84720 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.24 |\n", + "| n_updates | 1446 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7684 |\n", + "| fps | 210 |\n", + "| time_elapsed | 403 |\n", + "| total_timesteps | 84762 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.08 |\n", + "| n_updates | 1448 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7688 |\n", + "| fps | 210 |\n", + "| time_elapsed | 403 |\n", + "| total_timesteps | 84798 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.26 |\n", + "| n_updates | 1450 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7692 |\n", + "| fps | 210 |\n", + "| time_elapsed | 403 |\n", + "| total_timesteps | 84834 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.09 |\n", + "| n_updates | 1451 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7696 |\n", + "| fps | 209 |\n", + "| time_elapsed | 404 |\n", + "| total_timesteps | 84870 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.48 |\n", + "| n_updates | 1453 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7700 |\n", + "| fps | 209 |\n", + "| time_elapsed | 404 |\n", + "| total_timesteps | 84936 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.06 |\n", + "| n_updates | 1455 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7704 |\n", + "| fps | 209 |\n", + "| time_elapsed | 405 |\n", + "| total_timesteps | 84972 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.32 |\n", + "| n_updates | 1457 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7708 |\n", + "| fps | 209 |\n", + "| time_elapsed | 405 |\n", + "| total_timesteps | 85056 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.35 |\n", + "| n_updates | 1460 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7712 |\n", + "| fps | 209 |\n", + "| time_elapsed | 406 |\n", + "| total_timesteps | 85110 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.3 |\n", + "| n_updates | 1463 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7716 |\n", + "| fps | 209 |\n", + "| time_elapsed | 406 |\n", + "| total_timesteps | 85158 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.13 |\n", + "| n_updates | 1465 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7720 |\n", + "| fps | 209 |\n", + "| time_elapsed | 406 |\n", + "| total_timesteps | 85194 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.2 |\n", + "| n_updates | 1466 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7724 |\n", + "| fps | 209 |\n", + "| time_elapsed | 407 |\n", + "| total_timesteps | 85254 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.45 |\n", + "| n_updates | 1469 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.26 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7728 |\n", + "| fps | 209 |\n", + "| time_elapsed | 407 |\n", + "| total_timesteps | 85284 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.14 |\n", + "| n_updates | 1470 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.27 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7732 |\n", + "| fps | 209 |\n", + "| time_elapsed | 407 |\n", + "| total_timesteps | 85314 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.59 |\n", + "| n_updates | 1471 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.27 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7736 |\n", + "| fps | 209 |\n", + "| time_elapsed | 408 |\n", + "| total_timesteps | 85350 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.17 |\n", + "| n_updates | 1473 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.27 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7740 |\n", + "| fps | 209 |\n", + "| time_elapsed | 408 |\n", + "| total_timesteps | 85380 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.21 |\n", + "| n_updates | 1474 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.27 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7744 |\n", + "| fps | 209 |\n", + "| time_elapsed | 408 |\n", + "| total_timesteps | 85410 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 1475 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.29 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7748 |\n", + "| fps | 208 |\n", + "| time_elapsed | 409 |\n", + "| total_timesteps | 85518 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.3 |\n", + "| n_updates | 1480 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.28 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7752 |\n", + "| fps | 208 |\n", + "| time_elapsed | 409 |\n", + "| total_timesteps | 85572 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.34 |\n", + "| n_updates | 1482 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.3 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7756 |\n", + "| fps | 208 |\n", + "| time_elapsed | 410 |\n", + "| total_timesteps | 85614 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 1484 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.31 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7760 |\n", + "| fps | 208 |\n", + "| time_elapsed | 410 |\n", + "| total_timesteps | 85632 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.31 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7764 |\n", + "| fps | 208 |\n", + "| time_elapsed | 410 |\n", + "| total_timesteps | 85668 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.27 |\n", + "| n_updates | 1486 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.31 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7768 |\n", + "| fps | 208 |\n", + "| time_elapsed | 410 |\n", + "| total_timesteps | 85692 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.2 |\n", + "| n_updates | 1487 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.33 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7772 |\n", + "| fps | 208 |\n", + "| time_elapsed | 411 |\n", + "| total_timesteps | 85818 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.35 |\n", + "| n_updates | 1492 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.33 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7776 |\n", + "| fps | 208 |\n", + "| time_elapsed | 411 |\n", + "| total_timesteps | 85860 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.43 |\n", + "| n_updates | 1494 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.33 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7780 |\n", + "| fps | 208 |\n", + "| time_elapsed | 412 |\n", + "| total_timesteps | 85890 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.3 |\n", + "| n_updates | 1495 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.33 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7784 |\n", + "| fps | 208 |\n", + "| time_elapsed | 412 |\n", + "| total_timesteps | 85926 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.813 |\n", + "| n_updates | 1497 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.3 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7788 |\n", + "| fps | 208 |\n", + "| time_elapsed | 412 |\n", + "| total_timesteps | 85956 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 1498 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.3 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7792 |\n", + "| fps | 208 |\n", + "| time_elapsed | 412 |\n", + "| total_timesteps | 85992 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.61 |\n", + "| n_updates | 1499 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.32 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7796 |\n", + "| fps | 208 |\n", + "| time_elapsed | 413 |\n", + "| total_timesteps | 86028 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.922 |\n", + "| n_updates | 1501 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.3 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7800 |\n", + "| fps | 208 |\n", + "| time_elapsed | 414 |\n", + "| total_timesteps | 86130 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.15 |\n", + "| n_updates | 1505 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.3 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7804 |\n", + "| fps | 207 |\n", + "| time_elapsed | 414 |\n", + "| total_timesteps | 86172 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.25 |\n", + "| n_updates | 1507 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.3 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7808 |\n", + "| fps | 207 |\n", + "| time_elapsed | 414 |\n", + "| total_timesteps | 86184 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.28 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7812 |\n", + "| fps | 207 |\n", + "| time_elapsed | 414 |\n", + "| total_timesteps | 86214 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.19 |\n", + "| n_updates | 1509 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.28 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7816 |\n", + "| fps | 207 |\n", + "| time_elapsed | 415 |\n", + "| total_timesteps | 86268 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.59 |\n", + "| n_updates | 1511 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.27 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7820 |\n", + "| fps | 207 |\n", + "| time_elapsed | 415 |\n", + "| total_timesteps | 86322 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.27 |\n", + "| n_updates | 1513 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.26 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7824 |\n", + "| fps | 207 |\n", + "| time_elapsed | 415 |\n", + "| total_timesteps | 86352 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.33 |\n", + "| n_updates | 1514 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.26 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7828 |\n", + "| fps | 207 |\n", + "| time_elapsed | 416 |\n", + "| total_timesteps | 86382 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.49 |\n", + "| n_updates | 1516 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7832 |\n", + "| fps | 207 |\n", + "| time_elapsed | 416 |\n", + "| total_timesteps | 86412 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.59 |\n", + "| n_updates | 1517 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.24 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7836 |\n", + "| fps | 207 |\n", + "| time_elapsed | 416 |\n", + "| total_timesteps | 86454 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.3 |\n", + "| n_updates | 1519 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7840 |\n", + "| fps | 207 |\n", + "| time_elapsed | 416 |\n", + "| total_timesteps | 86496 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.37 |\n", + "| n_updates | 1520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7844 |\n", + "| fps | 207 |\n", + "| time_elapsed | 417 |\n", + "| total_timesteps | 86544 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 1522 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7848 |\n", + "| fps | 207 |\n", + "| time_elapsed | 417 |\n", + "| total_timesteps | 86610 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.32 |\n", + "| n_updates | 1525 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.21 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7852 |\n", + "| fps | 207 |\n", + "| time_elapsed | 418 |\n", + "| total_timesteps | 86652 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.62 |\n", + "| n_updates | 1527 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7856 |\n", + "| fps | 207 |\n", + "| time_elapsed | 418 |\n", + "| total_timesteps | 86682 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.22 |\n", + "| n_updates | 1528 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7860 |\n", + "| fps | 207 |\n", + "| time_elapsed | 418 |\n", + "| total_timesteps | 86712 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 1529 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7864 |\n", + "| fps | 207 |\n", + "| time_elapsed | 418 |\n", + "| total_timesteps | 86760 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 1531 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7868 |\n", + "| fps | 206 |\n", + "| time_elapsed | 419 |\n", + "| total_timesteps | 86826 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 1534 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7872 |\n", + "| fps | 206 |\n", + "| time_elapsed | 419 |\n", + "| total_timesteps | 86862 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.14 |\n", + "| n_updates | 1536 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7876 |\n", + "| fps | 206 |\n", + "| time_elapsed | 419 |\n", + "| total_timesteps | 86892 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.21 |\n", + "| n_updates | 1537 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7880 |\n", + "| fps | 206 |\n", + "| time_elapsed | 420 |\n", + "| total_timesteps | 86934 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.15 |\n", + "| n_updates | 1539 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7884 |\n", + "| fps | 206 |\n", + "| time_elapsed | 420 |\n", + "| total_timesteps | 86970 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 1540 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7888 |\n", + "| fps | 206 |\n", + "| time_elapsed | 420 |\n", + "| total_timesteps | 87000 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.74 |\n", + "| n_updates | 1541 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7892 |\n", + "| fps | 206 |\n", + "| time_elapsed | 421 |\n", + "| total_timesteps | 87030 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.39 |\n", + "| n_updates | 1543 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7896 |\n", + "| fps | 206 |\n", + "| time_elapsed | 421 |\n", + "| total_timesteps | 87066 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 1544 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7900 |\n", + "| fps | 206 |\n", + "| time_elapsed | 421 |\n", + "| total_timesteps | 87102 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 1546 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7904 |\n", + "| fps | 206 |\n", + "| time_elapsed | 421 |\n", + "| total_timesteps | 87144 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.23 |\n", + "| n_updates | 1547 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7908 |\n", + "| fps | 206 |\n", + "| time_elapsed | 422 |\n", + "| total_timesteps | 87186 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.22 |\n", + "| n_updates | 1549 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7912 |\n", + "| fps | 206 |\n", + "| time_elapsed | 422 |\n", + "| total_timesteps | 87228 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.964 |\n", + "| n_updates | 1551 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7916 |\n", + "| fps | 206 |\n", + "| time_elapsed | 422 |\n", + "| total_timesteps | 87264 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 1552 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7920 |\n", + "| fps | 206 |\n", + "| time_elapsed | 423 |\n", + "| total_timesteps | 87306 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 1554 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7924 |\n", + "| fps | 206 |\n", + "| time_elapsed | 423 |\n", + "| total_timesteps | 87342 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.22 |\n", + "| n_updates | 1556 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7928 |\n", + "| fps | 206 |\n", + "| time_elapsed | 423 |\n", + "| total_timesteps | 87396 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.47 |\n", + "| n_updates | 1558 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7932 |\n", + "| fps | 206 |\n", + "| time_elapsed | 424 |\n", + "| total_timesteps | 87420 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.29 |\n", + "| n_updates | 1559 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7936 |\n", + "| fps | 206 |\n", + "| time_elapsed | 424 |\n", + "| total_timesteps | 87444 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.2 |\n", + "| n_updates | 1560 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7940 |\n", + "| fps | 206 |\n", + "| time_elapsed | 424 |\n", + "| total_timesteps | 87492 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 1562 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7944 |\n", + "| fps | 205 |\n", + "| time_elapsed | 425 |\n", + "| total_timesteps | 87534 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.05 |\n", + "| n_updates | 1564 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7948 |\n", + "| fps | 205 |\n", + "| time_elapsed | 425 |\n", + "| total_timesteps | 87582 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.52 |\n", + "| n_updates | 1566 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7952 |\n", + "| fps | 205 |\n", + "| time_elapsed | 425 |\n", + "| total_timesteps | 87648 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 1568 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7956 |\n", + "| fps | 205 |\n", + "| time_elapsed | 426 |\n", + "| total_timesteps | 87690 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.44 |\n", + "| n_updates | 1570 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7960 |\n", + "| fps | 205 |\n", + "| time_elapsed | 426 |\n", + "| total_timesteps | 87702 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.19 |\n", + "| n_updates | 1571 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7964 |\n", + "| fps | 205 |\n", + "| time_elapsed | 426 |\n", + "| total_timesteps | 87732 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.75 |\n", + "| n_updates | 1572 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7968 |\n", + "| fps | 205 |\n", + "| time_elapsed | 426 |\n", + "| total_timesteps | 87762 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.4 |\n", + "| n_updates | 1573 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7972 |\n", + "| fps | 205 |\n", + "| time_elapsed | 426 |\n", + "| total_timesteps | 87774 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.15 |\n", + "| n_updates | 1574 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7976 |\n", + "| fps | 205 |\n", + "| time_elapsed | 427 |\n", + "| total_timesteps | 87804 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.37 |\n", + "| n_updates | 1575 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7980 |\n", + "| fps | 205 |\n", + "| time_elapsed | 427 |\n", + "| total_timesteps | 87876 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.36 |\n", + "| n_updates | 1578 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7984 |\n", + "| fps | 205 |\n", + "| time_elapsed | 428 |\n", + "| total_timesteps | 87972 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.95 |\n", + "| n_updates | 1582 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7988 |\n", + "| fps | 205 |\n", + "| time_elapsed | 428 |\n", + "| total_timesteps | 87996 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.979 |\n", + "| n_updates | 1583 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7992 |\n", + "| fps | 205 |\n", + "| time_elapsed | 428 |\n", + "| total_timesteps | 88038 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.34 |\n", + "| n_updates | 1585 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 7996 |\n", + "| fps | 205 |\n", + "| time_elapsed | 429 |\n", + "| total_timesteps | 88074 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.33 |\n", + "| n_updates | 1586 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8000 |\n", + "| fps | 205 |\n", + "| time_elapsed | 429 |\n", + "| total_timesteps | 88116 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.33 |\n", + "| n_updates | 1588 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8004 |\n", + "| fps | 205 |\n", + "| time_elapsed | 429 |\n", + "| total_timesteps | 88158 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.56 |\n", + "| n_updates | 1590 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8008 |\n", + "| fps | 205 |\n", + "| time_elapsed | 430 |\n", + "| total_timesteps | 88200 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.21 |\n", + "| n_updates | 1591 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8012 |\n", + "| fps | 204 |\n", + "| time_elapsed | 430 |\n", + "| total_timesteps | 88278 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.49 |\n", + "| n_updates | 1595 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8016 |\n", + "| fps | 204 |\n", + "| time_elapsed | 431 |\n", + "| total_timesteps | 88350 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.47 |\n", + "| n_updates | 1598 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8020 |\n", + "| fps | 204 |\n", + "| time_elapsed | 431 |\n", + "| total_timesteps | 88386 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.78 |\n", + "| n_updates | 1599 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8024 |\n", + "| fps | 204 |\n", + "| time_elapsed | 431 |\n", + "| total_timesteps | 88428 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.36 |\n", + "| n_updates | 1601 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8028 |\n", + "| fps | 204 |\n", + "| time_elapsed | 432 |\n", + "| total_timesteps | 88464 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.82 |\n", + "| n_updates | 1602 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8032 |\n", + "| fps | 204 |\n", + "| time_elapsed | 432 |\n", + "| total_timesteps | 88536 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 1605 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8036 |\n", + "| fps | 204 |\n", + "| time_elapsed | 433 |\n", + "| total_timesteps | 88590 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.53 |\n", + "| n_updates | 1608 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8040 |\n", + "| fps | 204 |\n", + "| time_elapsed | 433 |\n", + "| total_timesteps | 88620 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.11 |\n", + "| n_updates | 1609 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8044 |\n", + "| fps | 204 |\n", + "| time_elapsed | 433 |\n", + "| total_timesteps | 88674 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 1611 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8048 |\n", + "| fps | 204 |\n", + "| time_elapsed | 434 |\n", + "| total_timesteps | 88716 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.43 |\n", + "| n_updates | 1613 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8052 |\n", + "| fps | 204 |\n", + "| time_elapsed | 434 |\n", + "| total_timesteps | 88758 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.39 |\n", + "| n_updates | 1615 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8056 |\n", + "| fps | 204 |\n", + "| time_elapsed | 434 |\n", + "| total_timesteps | 88794 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 1616 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8060 |\n", + "| fps | 204 |\n", + "| time_elapsed | 435 |\n", + "| total_timesteps | 88842 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.26 |\n", + "| n_updates | 1618 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8064 |\n", + "| fps | 204 |\n", + "| time_elapsed | 435 |\n", + "| total_timesteps | 88872 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1 |\n", + "| n_updates | 1619 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8068 |\n", + "| fps | 204 |\n", + "| time_elapsed | 435 |\n", + "| total_timesteps | 88902 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.11 |\n", + "| n_updates | 1621 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8072 |\n", + "| fps | 203 |\n", + "| time_elapsed | 435 |\n", + "| total_timesteps | 88932 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.15 |\n", + "| n_updates | 1622 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8076 |\n", + "| fps | 203 |\n", + "| time_elapsed | 436 |\n", + "| total_timesteps | 89058 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 1627 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8080 |\n", + "| fps | 203 |\n", + "| time_elapsed | 437 |\n", + "| total_timesteps | 89088 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.02 |\n", + "| n_updates | 1628 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8084 |\n", + "| fps | 203 |\n", + "| time_elapsed | 437 |\n", + "| total_timesteps | 89124 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.46 |\n", + "| n_updates | 1630 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8088 |\n", + "| fps | 203 |\n", + "| time_elapsed | 437 |\n", + "| total_timesteps | 89148 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.48 |\n", + "| n_updates | 1631 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8092 |\n", + "| fps | 203 |\n", + "| time_elapsed | 437 |\n", + "| total_timesteps | 89178 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.29 |\n", + "| n_updates | 1632 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8096 |\n", + "| fps | 203 |\n", + "| time_elapsed | 438 |\n", + "| total_timesteps | 89208 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.14 |\n", + "| n_updates | 1633 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8100 |\n", + "| fps | 203 |\n", + "| time_elapsed | 438 |\n", + "| total_timesteps | 89316 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.48 |\n", + "| n_updates | 1638 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8104 |\n", + "| fps | 203 |\n", + "| time_elapsed | 439 |\n", + "| total_timesteps | 89388 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.58 |\n", + "| n_updates | 1641 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8108 |\n", + "| fps | 203 |\n", + "| time_elapsed | 439 |\n", + "| total_timesteps | 89430 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.3 |\n", + "| n_updates | 1643 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8112 |\n", + "| fps | 203 |\n", + "| time_elapsed | 440 |\n", + "| total_timesteps | 89466 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.59 |\n", + "| n_updates | 1644 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8116 |\n", + "| fps | 203 |\n", + "| time_elapsed | 440 |\n", + "| total_timesteps | 89514 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.33 |\n", + "| n_updates | 1646 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8120 |\n", + "| fps | 203 |\n", + "| time_elapsed | 440 |\n", + "| total_timesteps | 89574 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.68 |\n", + "| n_updates | 1649 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8124 |\n", + "| fps | 203 |\n", + "| time_elapsed | 441 |\n", + "| total_timesteps | 89622 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 1651 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8128 |\n", + "| fps | 203 |\n", + "| time_elapsed | 441 |\n", + "| total_timesteps | 89694 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.847 |\n", + "| n_updates | 1654 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8132 |\n", + "| fps | 202 |\n", + "| time_elapsed | 442 |\n", + "| total_timesteps | 89736 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.03 |\n", + "| n_updates | 1655 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8136 |\n", + "| fps | 202 |\n", + "| time_elapsed | 442 |\n", + "| total_timesteps | 89796 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.57 |\n", + "| n_updates | 1658 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8140 |\n", + "| fps | 202 |\n", + "| time_elapsed | 442 |\n", + "| total_timesteps | 89844 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.44 |\n", + "| n_updates | 1660 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8144 |\n", + "| fps | 202 |\n", + "| time_elapsed | 443 |\n", + "| total_timesteps | 89874 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 1661 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8148 |\n", + "| fps | 202 |\n", + "| time_elapsed | 443 |\n", + "| total_timesteps | 89898 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.49 |\n", + "| n_updates | 1662 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8152 |\n", + "| fps | 202 |\n", + "| time_elapsed | 443 |\n", + "| total_timesteps | 89958 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.27 |\n", + "| n_updates | 1665 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8156 |\n", + "| fps | 202 |\n", + "| time_elapsed | 444 |\n", + "| total_timesteps | 90000 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.35 |\n", + "| n_updates | 1666 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8160 |\n", + "| fps | 202 |\n", + "| time_elapsed | 444 |\n", + "| total_timesteps | 90036 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.79 |\n", + "| n_updates | 1668 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8164 |\n", + "| fps | 202 |\n", + "| time_elapsed | 444 |\n", + "| total_timesteps | 90072 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.13 |\n", + "| n_updates | 1669 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8168 |\n", + "| fps | 202 |\n", + "| time_elapsed | 445 |\n", + "| total_timesteps | 90120 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 1671 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8172 |\n", + "| fps | 202 |\n", + "| time_elapsed | 446 |\n", + "| total_timesteps | 90234 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.64 |\n", + "| n_updates | 1676 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8176 |\n", + "| fps | 202 |\n", + "| time_elapsed | 446 |\n", + "| total_timesteps | 90270 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.1 |\n", + "| n_updates | 1678 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8180 |\n", + "| fps | 202 |\n", + "| time_elapsed | 446 |\n", + "| total_timesteps | 90288 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8184 |\n", + "| fps | 202 |\n", + "| time_elapsed | 446 |\n", + "| total_timesteps | 90318 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.1 |\n", + "| n_updates | 1680 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8188 |\n", + "| fps | 202 |\n", + "| time_elapsed | 447 |\n", + "| total_timesteps | 90354 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.6 |\n", + "| n_updates | 1681 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8192 |\n", + "| fps | 202 |\n", + "| time_elapsed | 447 |\n", + "| total_timesteps | 90396 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.82 |\n", + "| n_updates | 1683 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8196 |\n", + "| fps | 201 |\n", + "| time_elapsed | 447 |\n", + "| total_timesteps | 90450 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.42 |\n", + "| n_updates | 1685 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8200 |\n", + "| fps | 201 |\n", + "| time_elapsed | 448 |\n", + "| total_timesteps | 90492 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 1687 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8204 |\n", + "| fps | 201 |\n", + "| time_elapsed | 448 |\n", + "| total_timesteps | 90600 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.41 |\n", + "| n_updates | 1691 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8208 |\n", + "| fps | 201 |\n", + "| time_elapsed | 449 |\n", + "| total_timesteps | 90636 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.81 |\n", + "| n_updates | 1693 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8212 |\n", + "| fps | 201 |\n", + "| time_elapsed | 449 |\n", + "| total_timesteps | 90666 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 1694 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8216 |\n", + "| fps | 201 |\n", + "| time_elapsed | 449 |\n", + "| total_timesteps | 90690 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.39 |\n", + "| n_updates | 1695 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8220 |\n", + "| fps | 201 |\n", + "| time_elapsed | 449 |\n", + "| total_timesteps | 90708 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.93 |\n", + "| n_updates | 1696 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8224 |\n", + "| fps | 201 |\n", + "| time_elapsed | 450 |\n", + "| total_timesteps | 90738 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.82 |\n", + "| n_updates | 1697 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8228 |\n", + "| fps | 201 |\n", + "| time_elapsed | 450 |\n", + "| total_timesteps | 90768 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.25 |\n", + "| n_updates | 1698 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8232 |\n", + "| fps | 201 |\n", + "| time_elapsed | 450 |\n", + "| total_timesteps | 90804 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.44 |\n", + "| n_updates | 1700 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8236 |\n", + "| fps | 201 |\n", + "| time_elapsed | 451 |\n", + "| total_timesteps | 90924 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.78 |\n", + "| n_updates | 1705 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8240 |\n", + "| fps | 201 |\n", + "| time_elapsed | 451 |\n", + "| total_timesteps | 90978 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 1707 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8244 |\n", + "| fps | 201 |\n", + "| time_elapsed | 452 |\n", + "| total_timesteps | 91002 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.45 |\n", + "| n_updates | 1708 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8248 |\n", + "| fps | 201 |\n", + "| time_elapsed | 452 |\n", + "| total_timesteps | 91032 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.38 |\n", + "| n_updates | 1709 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8252 |\n", + "| fps | 201 |\n", + "| time_elapsed | 452 |\n", + "| total_timesteps | 91062 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.01 |\n", + "| n_updates | 1711 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8256 |\n", + "| fps | 201 |\n", + "| time_elapsed | 452 |\n", + "| total_timesteps | 91122 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 1713 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8260 |\n", + "| fps | 201 |\n", + "| time_elapsed | 453 |\n", + "| total_timesteps | 91164 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.77 |\n", + "| n_updates | 1715 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8264 |\n", + "| fps | 201 |\n", + "| time_elapsed | 453 |\n", + "| total_timesteps | 91182 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.12 |\n", + "| n_updates | 1716 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8268 |\n", + "| fps | 201 |\n", + "| time_elapsed | 453 |\n", + "| total_timesteps | 91224 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.65 |\n", + "| n_updates | 1717 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8272 |\n", + "| fps | 200 |\n", + "| time_elapsed | 454 |\n", + "| total_timesteps | 91296 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.5 |\n", + "| n_updates | 1720 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8276 |\n", + "| fps | 200 |\n", + "| time_elapsed | 454 |\n", + "| total_timesteps | 91314 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.89 |\n", + "| n_updates | 1721 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8280 |\n", + "| fps | 200 |\n", + "| time_elapsed | 454 |\n", + "| total_timesteps | 91350 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.51 |\n", + "| n_updates | 1723 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8284 |\n", + "| fps | 200 |\n", + "| time_elapsed | 455 |\n", + "| total_timesteps | 91386 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.58 |\n", + "| n_updates | 1724 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8288 |\n", + "| fps | 200 |\n", + "| time_elapsed | 455 |\n", + "| total_timesteps | 91434 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.92 |\n", + "| n_updates | 1726 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8292 |\n", + "| fps | 200 |\n", + "| time_elapsed | 455 |\n", + "| total_timesteps | 91482 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.73 |\n", + "| n_updates | 1728 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8296 |\n", + "| fps | 200 |\n", + "| time_elapsed | 456 |\n", + "| total_timesteps | 91530 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.66 |\n", + "| n_updates | 1730 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8300 |\n", + "| fps | 200 |\n", + "| time_elapsed | 456 |\n", + "| total_timesteps | 91572 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.72 |\n", + "| n_updates | 1732 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8304 |\n", + "| fps | 200 |\n", + "| time_elapsed | 457 |\n", + "| total_timesteps | 91668 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.67 |\n", + "| n_updates | 1736 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8308 |\n", + "| fps | 200 |\n", + "| time_elapsed | 457 |\n", + "| total_timesteps | 91716 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.84 |\n", + "| n_updates | 1738 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8312 |\n", + "| fps | 200 |\n", + "| time_elapsed | 457 |\n", + "| total_timesteps | 91746 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.78 |\n", + "| n_updates | 1739 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8316 |\n", + "| fps | 200 |\n", + "| time_elapsed | 458 |\n", + "| total_timesteps | 91782 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.46 |\n", + "| n_updates | 1741 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8320 |\n", + "| fps | 200 |\n", + "| time_elapsed | 458 |\n", + "| total_timesteps | 91824 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.42 |\n", + "| n_updates | 1742 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8324 |\n", + "| fps | 200 |\n", + "| time_elapsed | 458 |\n", + "| total_timesteps | 91866 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.64 |\n", + "| n_updates | 1744 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8328 |\n", + "| fps | 200 |\n", + "| time_elapsed | 459 |\n", + "| total_timesteps | 91926 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.92 |\n", + "| n_updates | 1747 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8332 |\n", + "| fps | 200 |\n", + "| time_elapsed | 459 |\n", + "| total_timesteps | 91974 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.64 |\n", + "| n_updates | 1749 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8336 |\n", + "| fps | 200 |\n", + "| time_elapsed | 459 |\n", + "| total_timesteps | 92016 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.08 |\n", + "| n_updates | 1750 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8340 |\n", + "| fps | 200 |\n", + "| time_elapsed | 460 |\n", + "| total_timesteps | 92028 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.52 |\n", + "| n_updates | 1751 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8344 |\n", + "| fps | 199 |\n", + "| time_elapsed | 460 |\n", + "| total_timesteps | 92094 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.59 |\n", + "| n_updates | 1754 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8348 |\n", + "| fps | 199 |\n", + "| time_elapsed | 461 |\n", + "| total_timesteps | 92226 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.43 |\n", + "| n_updates | 1759 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8352 |\n", + "| fps | 199 |\n", + "| time_elapsed | 461 |\n", + "| total_timesteps | 92268 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 1761 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8356 |\n", + "| fps | 199 |\n", + "| time_elapsed | 462 |\n", + "| total_timesteps | 92292 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.03 |\n", + "| n_updates | 1762 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8360 |\n", + "| fps | 199 |\n", + "| time_elapsed | 462 |\n", + "| total_timesteps | 92328 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.64 |\n", + "| n_updates | 1763 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8364 |\n", + "| fps | 199 |\n", + "| time_elapsed | 462 |\n", + "| total_timesteps | 92370 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.96 |\n", + "| n_updates | 1765 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8368 |\n", + "| fps | 199 |\n", + "| time_elapsed | 463 |\n", + "| total_timesteps | 92412 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.73 |\n", + "| n_updates | 1767 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8372 |\n", + "| fps | 199 |\n", + "| time_elapsed | 463 |\n", + "| total_timesteps | 92454 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.6 |\n", + "| n_updates | 1769 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8376 |\n", + "| fps | 199 |\n", + "| time_elapsed | 463 |\n", + "| total_timesteps | 92490 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.44 |\n", + "| n_updates | 1770 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8380 |\n", + "| fps | 199 |\n", + "| time_elapsed | 464 |\n", + "| total_timesteps | 92532 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.91 |\n", + "| n_updates | 1772 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8384 |\n", + "| fps | 199 |\n", + "| time_elapsed | 464 |\n", + "| total_timesteps | 92556 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.64 |\n", + "| n_updates | 1773 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8388 |\n", + "| fps | 199 |\n", + "| time_elapsed | 464 |\n", + "| total_timesteps | 92592 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.975 |\n", + "| n_updates | 1774 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8392 |\n", + "| fps | 199 |\n", + "| time_elapsed | 464 |\n", + "| total_timesteps | 92628 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.38 |\n", + "| n_updates | 1776 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8396 |\n", + "| fps | 199 |\n", + "| time_elapsed | 465 |\n", + "| total_timesteps | 92664 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.69 |\n", + "| n_updates | 1777 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8400 |\n", + "| fps | 199 |\n", + "| time_elapsed | 465 |\n", + "| total_timesteps | 92688 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3 |\n", + "| n_updates | 1778 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8404 |\n", + "| fps | 199 |\n", + "| time_elapsed | 465 |\n", + "| total_timesteps | 92748 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.47 |\n", + "| n_updates | 1781 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8408 |\n", + "| fps | 199 |\n", + "| time_elapsed | 466 |\n", + "| total_timesteps | 92820 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 1784 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8412 |\n", + "| fps | 198 |\n", + "| time_elapsed | 466 |\n", + "| total_timesteps | 92898 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.02 |\n", + "| n_updates | 1787 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8416 |\n", + "| fps | 198 |\n", + "| time_elapsed | 467 |\n", + "| total_timesteps | 92940 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 1789 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8420 |\n", + "| fps | 198 |\n", + "| time_elapsed | 467 |\n", + "| total_timesteps | 92982 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.7 |\n", + "| n_updates | 1791 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8424 |\n", + "| fps | 198 |\n", + "| time_elapsed | 467 |\n", + "| total_timesteps | 93000 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8428 |\n", + "| fps | 198 |\n", + "| time_elapsed | 467 |\n", + "| total_timesteps | 93030 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.52 |\n", + "| n_updates | 1793 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8432 |\n", + "| fps | 198 |\n", + "| time_elapsed | 468 |\n", + "| total_timesteps | 93084 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.54 |\n", + "| n_updates | 1795 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8436 |\n", + "| fps | 198 |\n", + "| time_elapsed | 468 |\n", + "| total_timesteps | 93150 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.87 |\n", + "| n_updates | 1798 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8440 |\n", + "| fps | 198 |\n", + "| time_elapsed | 469 |\n", + "| total_timesteps | 93210 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 1800 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8444 |\n", + "| fps | 198 |\n", + "| time_elapsed | 469 |\n", + "| total_timesteps | 93264 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 1802 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8448 |\n", + "| fps | 198 |\n", + "| time_elapsed | 469 |\n", + "| total_timesteps | 93288 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.73 |\n", + "| n_updates | 1803 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8452 |\n", + "| fps | 198 |\n", + "| time_elapsed | 470 |\n", + "| total_timesteps | 93330 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.71 |\n", + "| n_updates | 1805 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8456 |\n", + "| fps | 198 |\n", + "| time_elapsed | 470 |\n", + "| total_timesteps | 93372 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 1807 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8460 |\n", + "| fps | 198 |\n", + "| time_elapsed | 471 |\n", + "| total_timesteps | 93432 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.38 |\n", + "| n_updates | 1809 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8464 |\n", + "| fps | 198 |\n", + "| time_elapsed | 471 |\n", + "| total_timesteps | 93498 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.62 |\n", + "| n_updates | 1812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8468 |\n", + "| fps | 198 |\n", + "| time_elapsed | 472 |\n", + "| total_timesteps | 93546 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.07 |\n", + "| n_updates | 1814 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8472 |\n", + "| fps | 198 |\n", + "| time_elapsed | 472 |\n", + "| total_timesteps | 93594 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.69 |\n", + "| n_updates | 1816 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8476 |\n", + "| fps | 198 |\n", + "| time_elapsed | 472 |\n", + "| total_timesteps | 93636 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.88 |\n", + "| n_updates | 1818 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8480 |\n", + "| fps | 198 |\n", + "| time_elapsed | 473 |\n", + "| total_timesteps | 93672 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.73 |\n", + "| n_updates | 1819 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8484 |\n", + "| fps | 197 |\n", + "| time_elapsed | 473 |\n", + "| total_timesteps | 93732 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.43 |\n", + "| n_updates | 1822 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8488 |\n", + "| fps | 197 |\n", + "| time_elapsed | 474 |\n", + "| total_timesteps | 93804 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.81 |\n", + "| n_updates | 1825 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8492 |\n", + "| fps | 197 |\n", + "| time_elapsed | 474 |\n", + "| total_timesteps | 93858 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.74 |\n", + "| n_updates | 1827 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8496 |\n", + "| fps | 197 |\n", + "| time_elapsed | 474 |\n", + "| total_timesteps | 93888 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.71 |\n", + "| n_updates | 1828 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8500 |\n", + "| fps | 197 |\n", + "| time_elapsed | 475 |\n", + "| total_timesteps | 93924 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.49 |\n", + "| n_updates | 1830 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8504 |\n", + "| fps | 197 |\n", + "| time_elapsed | 475 |\n", + "| total_timesteps | 93984 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.83 |\n", + "| n_updates | 1832 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8508 |\n", + "| fps | 197 |\n", + "| time_elapsed | 475 |\n", + "| total_timesteps | 94020 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.21 |\n", + "| n_updates | 1834 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8512 |\n", + "| fps | 197 |\n", + "| time_elapsed | 476 |\n", + "| total_timesteps | 94062 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.65 |\n", + "| n_updates | 1836 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8516 |\n", + "| fps | 197 |\n", + "| time_elapsed | 476 |\n", + "| total_timesteps | 94086 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.86 |\n", + "| n_updates | 1837 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8520 |\n", + "| fps | 197 |\n", + "| time_elapsed | 476 |\n", + "| total_timesteps | 94122 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.4 |\n", + "| n_updates | 1838 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8524 |\n", + "| fps | 197 |\n", + "| time_elapsed | 476 |\n", + "| total_timesteps | 94134 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 1839 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8528 |\n", + "| fps | 197 |\n", + "| time_elapsed | 477 |\n", + "| total_timesteps | 94164 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 1840 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8532 |\n", + "| fps | 197 |\n", + "| time_elapsed | 477 |\n", + "| total_timesteps | 94200 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 1841 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8536 |\n", + "| fps | 197 |\n", + "| time_elapsed | 477 |\n", + "| total_timesteps | 94242 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.65 |\n", + "| n_updates | 1843 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8540 |\n", + "| fps | 197 |\n", + "| time_elapsed | 478 |\n", + "| total_timesteps | 94290 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.43 |\n", + "| n_updates | 1845 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8544 |\n", + "| fps | 197 |\n", + "| time_elapsed | 478 |\n", + "| total_timesteps | 94332 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.84 |\n", + "| n_updates | 1847 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8548 |\n", + "| fps | 197 |\n", + "| time_elapsed | 478 |\n", + "| total_timesteps | 94386 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.65 |\n", + "| n_updates | 1849 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8552 |\n", + "| fps | 197 |\n", + "| time_elapsed | 479 |\n", + "| total_timesteps | 94452 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.83 |\n", + "| n_updates | 1852 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8556 |\n", + "| fps | 196 |\n", + "| time_elapsed | 479 |\n", + "| total_timesteps | 94500 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.57 |\n", + "| n_updates | 1854 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8560 |\n", + "| fps | 196 |\n", + "| time_elapsed | 480 |\n", + "| total_timesteps | 94542 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 1856 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8564 |\n", + "| fps | 196 |\n", + "| time_elapsed | 480 |\n", + "| total_timesteps | 94584 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.87 |\n", + "| n_updates | 1857 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8568 |\n", + "| fps | 196 |\n", + "| time_elapsed | 480 |\n", + "| total_timesteps | 94650 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 1860 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8572 |\n", + "| fps | 196 |\n", + "| time_elapsed | 481 |\n", + "| total_timesteps | 94686 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.97 |\n", + "| n_updates | 1862 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8576 |\n", + "| fps | 196 |\n", + "| time_elapsed | 481 |\n", + "| total_timesteps | 94752 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.81 |\n", + "| n_updates | 1864 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8580 |\n", + "| fps | 196 |\n", + "| time_elapsed | 482 |\n", + "| total_timesteps | 94818 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.69 |\n", + "| n_updates | 1867 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8584 |\n", + "| fps | 196 |\n", + "| time_elapsed | 482 |\n", + "| total_timesteps | 94854 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.41 |\n", + "| n_updates | 1869 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8588 |\n", + "| fps | 196 |\n", + "| time_elapsed | 482 |\n", + "| total_timesteps | 94908 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.9 |\n", + "| n_updates | 1871 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8592 |\n", + "| fps | 196 |\n", + "| time_elapsed | 483 |\n", + "| total_timesteps | 94956 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 1873 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8596 |\n", + "| fps | 196 |\n", + "| time_elapsed | 483 |\n", + "| total_timesteps | 94992 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.76 |\n", + "| n_updates | 1874 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8600 |\n", + "| fps | 196 |\n", + "| time_elapsed | 483 |\n", + "| total_timesteps | 95022 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.4 |\n", + "| n_updates | 1876 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8604 |\n", + "| fps | 196 |\n", + "| time_elapsed | 484 |\n", + "| total_timesteps | 95058 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 1877 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8608 |\n", + "| fps | 196 |\n", + "| time_elapsed | 484 |\n", + "| total_timesteps | 95088 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.7 |\n", + "| n_updates | 1878 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8612 |\n", + "| fps | 196 |\n", + "| time_elapsed | 484 |\n", + "| total_timesteps | 95118 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.25 |\n", + "| n_updates | 1880 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8616 |\n", + "| fps | 196 |\n", + "| time_elapsed | 484 |\n", + "| total_timesteps | 95136 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8620 |\n", + "| fps | 196 |\n", + "| time_elapsed | 485 |\n", + "| total_timesteps | 95172 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.77 |\n", + "| n_updates | 1882 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8624 |\n", + "| fps | 196 |\n", + "| time_elapsed | 485 |\n", + "| total_timesteps | 95214 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.89 |\n", + "| n_updates | 1884 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8628 |\n", + "| fps | 195 |\n", + "| time_elapsed | 486 |\n", + "| total_timesteps | 95334 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.38 |\n", + "| n_updates | 1889 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8632 |\n", + "| fps | 195 |\n", + "| time_elapsed | 486 |\n", + "| total_timesteps | 95376 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.53 |\n", + "| n_updates | 1890 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8636 |\n", + "| fps | 195 |\n", + "| time_elapsed | 487 |\n", + "| total_timesteps | 95406 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 1892 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8640 |\n", + "| fps | 195 |\n", + "| time_elapsed | 487 |\n", + "| total_timesteps | 95436 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.84 |\n", + "| n_updates | 1893 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8644 |\n", + "| fps | 195 |\n", + "| time_elapsed | 487 |\n", + "| total_timesteps | 95466 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.55 |\n", + "| n_updates | 1894 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8648 |\n", + "| fps | 195 |\n", + "| time_elapsed | 487 |\n", + "| total_timesteps | 95502 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.44 |\n", + "| n_updates | 1896 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8652 |\n", + "| fps | 195 |\n", + "| time_elapsed | 488 |\n", + "| total_timesteps | 95622 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.56 |\n", + "| n_updates | 1901 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8656 |\n", + "| fps | 195 |\n", + "| time_elapsed | 489 |\n", + "| total_timesteps | 95664 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 1902 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8660 |\n", + "| fps | 195 |\n", + "| time_elapsed | 489 |\n", + "| total_timesteps | 95688 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.01 |\n", + "| n_updates | 1903 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8664 |\n", + "| fps | 195 |\n", + "| time_elapsed | 489 |\n", + "| total_timesteps | 95712 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.35 |\n", + "| n_updates | 1904 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8668 |\n", + "| fps | 195 |\n", + "| time_elapsed | 489 |\n", + "| total_timesteps | 95742 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 1906 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8672 |\n", + "| fps | 195 |\n", + "| time_elapsed | 489 |\n", + "| total_timesteps | 95766 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.22 |\n", + "| n_updates | 1907 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8676 |\n", + "| fps | 195 |\n", + "| time_elapsed | 490 |\n", + "| total_timesteps | 95784 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8680 |\n", + "| fps | 195 |\n", + "| time_elapsed | 490 |\n", + "| total_timesteps | 95814 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.92 |\n", + "| n_updates | 1909 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8684 |\n", + "| fps | 195 |\n", + "| time_elapsed | 490 |\n", + "| total_timesteps | 95874 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.24 |\n", + "| n_updates | 1911 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8688 |\n", + "| fps | 195 |\n", + "| time_elapsed | 491 |\n", + "| total_timesteps | 95970 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.93 |\n", + "| n_updates | 1915 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8692 |\n", + "| fps | 195 |\n", + "| time_elapsed | 491 |\n", + "| total_timesteps | 96000 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.62 |\n", + "| n_updates | 1916 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8696 |\n", + "| fps | 195 |\n", + "| time_elapsed | 492 |\n", + "| total_timesteps | 96030 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.7 |\n", + "| n_updates | 1918 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8700 |\n", + "| fps | 195 |\n", + "| time_elapsed | 492 |\n", + "| total_timesteps | 96060 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 1919 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8704 |\n", + "| fps | 195 |\n", + "| time_elapsed | 492 |\n", + "| total_timesteps | 96096 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.69 |\n", + "| n_updates | 1920 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8708 |\n", + "| fps | 194 |\n", + "| time_elapsed | 493 |\n", + "| total_timesteps | 96174 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.76 |\n", + "| n_updates | 1924 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8712 |\n", + "| fps | 194 |\n", + "| time_elapsed | 493 |\n", + "| total_timesteps | 96282 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.56 |\n", + "| n_updates | 1928 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8716 |\n", + "| fps | 194 |\n", + "| time_elapsed | 494 |\n", + "| total_timesteps | 96312 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.61 |\n", + "| n_updates | 1929 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8720 |\n", + "| fps | 194 |\n", + "| time_elapsed | 494 |\n", + "| total_timesteps | 96330 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.27 |\n", + "| n_updates | 1930 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8724 |\n", + "| fps | 194 |\n", + "| time_elapsed | 494 |\n", + "| total_timesteps | 96402 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 1933 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8728 |\n", + "| fps | 194 |\n", + "| time_elapsed | 495 |\n", + "| total_timesteps | 96480 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.62 |\n", + "| n_updates | 1936 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8732 |\n", + "| fps | 194 |\n", + "| time_elapsed | 495 |\n", + "| total_timesteps | 96528 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.58 |\n", + "| n_updates | 1938 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8736 |\n", + "| fps | 194 |\n", + "| time_elapsed | 496 |\n", + "| total_timesteps | 96564 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.53 |\n", + "| n_updates | 1940 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8740 |\n", + "| fps | 194 |\n", + "| time_elapsed | 496 |\n", + "| total_timesteps | 96594 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 1941 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8744 |\n", + "| fps | 194 |\n", + "| time_elapsed | 496 |\n", + "| total_timesteps | 96636 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 1943 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8748 |\n", + "| fps | 194 |\n", + "| time_elapsed | 497 |\n", + "| total_timesteps | 96690 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.29 |\n", + "| n_updates | 1945 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8752 |\n", + "| fps | 194 |\n", + "| time_elapsed | 497 |\n", + "| total_timesteps | 96744 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.41 |\n", + "| n_updates | 1947 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8756 |\n", + "| fps | 194 |\n", + "| time_elapsed | 497 |\n", + "| total_timesteps | 96774 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.48 |\n", + "| n_updates | 1949 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8760 |\n", + "| fps | 194 |\n", + "| time_elapsed | 498 |\n", + "| total_timesteps | 96810 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.77 |\n", + "| n_updates | 1950 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8764 |\n", + "| fps | 194 |\n", + "| time_elapsed | 498 |\n", + "| total_timesteps | 96888 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 1953 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8768 |\n", + "| fps | 194 |\n", + "| time_elapsed | 498 |\n", + "| total_timesteps | 96924 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.71 |\n", + "| n_updates | 1955 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8772 |\n", + "| fps | 194 |\n", + "| time_elapsed | 499 |\n", + "| total_timesteps | 96936 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8776 |\n", + "| fps | 194 |\n", + "| time_elapsed | 499 |\n", + "| total_timesteps | 97020 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.97 |\n", + "| n_updates | 1959 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8780 |\n", + "| fps | 194 |\n", + "| time_elapsed | 499 |\n", + "| total_timesteps | 97050 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.38 |\n", + "| n_updates | 1960 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8784 |\n", + "| fps | 194 |\n", + "| time_elapsed | 500 |\n", + "| total_timesteps | 97122 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.5 |\n", + "| n_updates | 1963 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8788 |\n", + "| fps | 194 |\n", + "| time_elapsed | 500 |\n", + "| total_timesteps | 97134 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.87 |\n", + "| n_updates | 1964 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8792 |\n", + "| fps | 193 |\n", + "| time_elapsed | 500 |\n", + "| total_timesteps | 97158 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.89 |\n", + "| n_updates | 1965 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8796 |\n", + "| fps | 193 |\n", + "| time_elapsed | 501 |\n", + "| total_timesteps | 97188 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.96 |\n", + "| n_updates | 1966 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8800 |\n", + "| fps | 193 |\n", + "| time_elapsed | 501 |\n", + "| total_timesteps | 97230 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.5 |\n", + "| n_updates | 1968 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8804 |\n", + "| fps | 193 |\n", + "| time_elapsed | 501 |\n", + "| total_timesteps | 97260 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.1 |\n", + "| n_updates | 1969 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8808 |\n", + "| fps | 193 |\n", + "| time_elapsed | 501 |\n", + "| total_timesteps | 97290 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.31 |\n", + "| n_updates | 1970 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8812 |\n", + "| fps | 193 |\n", + "| time_elapsed | 502 |\n", + "| total_timesteps | 97422 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 1976 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8816 |\n", + "| fps | 193 |\n", + "| time_elapsed | 503 |\n", + "| total_timesteps | 97458 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 1977 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8820 |\n", + "| fps | 193 |\n", + "| time_elapsed | 503 |\n", + "| total_timesteps | 97500 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.7 |\n", + "| n_updates | 1979 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8824 |\n", + "| fps | 193 |\n", + "| time_elapsed | 503 |\n", + "| total_timesteps | 97536 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 1980 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8828 |\n", + "| fps | 193 |\n", + "| time_elapsed | 504 |\n", + "| total_timesteps | 97572 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.56 |\n", + "| n_updates | 1982 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8832 |\n", + "| fps | 193 |\n", + "| time_elapsed | 504 |\n", + "| total_timesteps | 97620 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.17 |\n", + "| n_updates | 1984 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8836 |\n", + "| fps | 193 |\n", + "| time_elapsed | 504 |\n", + "| total_timesteps | 97668 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.31 |\n", + "| n_updates | 1986 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8840 |\n", + "| fps | 193 |\n", + "| time_elapsed | 505 |\n", + "| total_timesteps | 97704 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 1987 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8844 |\n", + "| fps | 193 |\n", + "| time_elapsed | 505 |\n", + "| total_timesteps | 97758 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 1990 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8848 |\n", + "| fps | 193 |\n", + "| time_elapsed | 505 |\n", + "| total_timesteps | 97776 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8852 |\n", + "| fps | 193 |\n", + "| time_elapsed | 506 |\n", + "| total_timesteps | 97818 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.46 |\n", + "| n_updates | 1992 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8856 |\n", + "| fps | 193 |\n", + "| time_elapsed | 506 |\n", + "| total_timesteps | 97860 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.66 |\n", + "| n_updates | 1994 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8860 |\n", + "| fps | 193 |\n", + "| time_elapsed | 506 |\n", + "| total_timesteps | 97896 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.42 |\n", + "| n_updates | 1995 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8864 |\n", + "| fps | 193 |\n", + "| time_elapsed | 507 |\n", + "| total_timesteps | 97938 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 1997 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8868 |\n", + "| fps | 193 |\n", + "| time_elapsed | 507 |\n", + "| total_timesteps | 97968 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.59 |\n", + "| n_updates | 1998 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8872 |\n", + "| fps | 193 |\n", + "| time_elapsed | 507 |\n", + "| total_timesteps | 98040 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.25 |\n", + "| n_updates | 2001 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8876 |\n", + "| fps | 192 |\n", + "| time_elapsed | 508 |\n", + "| total_timesteps | 98106 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.52 |\n", + "| n_updates | 2004 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8880 |\n", + "| fps | 192 |\n", + "| time_elapsed | 508 |\n", + "| total_timesteps | 98160 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.71 |\n", + "| n_updates | 2006 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8884 |\n", + "| fps | 192 |\n", + "| time_elapsed | 508 |\n", + "| total_timesteps | 98184 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.25 |\n", + "| n_updates | 2007 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8888 |\n", + "| fps | 192 |\n", + "| time_elapsed | 509 |\n", + "| total_timesteps | 98238 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.73 |\n", + "| n_updates | 2010 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8892 |\n", + "| fps | 192 |\n", + "| time_elapsed | 509 |\n", + "| total_timesteps | 98292 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.78 |\n", + "| n_updates | 2012 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8896 |\n", + "| fps | 192 |\n", + "| time_elapsed | 510 |\n", + "| total_timesteps | 98352 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.68 |\n", + "| n_updates | 2014 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8900 |\n", + "| fps | 192 |\n", + "| time_elapsed | 510 |\n", + "| total_timesteps | 98394 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.35 |\n", + "| n_updates | 2016 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8904 |\n", + "| fps | 192 |\n", + "| time_elapsed | 510 |\n", + "| total_timesteps | 98424 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.87 |\n", + "| n_updates | 2017 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8908 |\n", + "| fps | 192 |\n", + "| time_elapsed | 511 |\n", + "| total_timesteps | 98496 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.65 |\n", + "| n_updates | 2020 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8912 |\n", + "| fps | 192 |\n", + "| time_elapsed | 511 |\n", + "| total_timesteps | 98568 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.45 |\n", + "| n_updates | 2023 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8916 |\n", + "| fps | 192 |\n", + "| time_elapsed | 512 |\n", + "| total_timesteps | 98604 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.29 |\n", + "| n_updates | 2025 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8920 |\n", + "| fps | 192 |\n", + "| time_elapsed | 512 |\n", + "| total_timesteps | 98634 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 2026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8924 |\n", + "| fps | 192 |\n", + "| time_elapsed | 512 |\n", + "| total_timesteps | 98670 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.57 |\n", + "| n_updates | 2028 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8928 |\n", + "| fps | 192 |\n", + "| time_elapsed | 513 |\n", + "| total_timesteps | 98730 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.71 |\n", + "| n_updates | 2030 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8932 |\n", + "| fps | 192 |\n", + "| time_elapsed | 514 |\n", + "| total_timesteps | 98838 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.51 |\n", + "| n_updates | 2035 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8936 |\n", + "| fps | 192 |\n", + "| time_elapsed | 514 |\n", + "| total_timesteps | 98868 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.6 |\n", + "| n_updates | 2036 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8940 |\n", + "| fps | 192 |\n", + "| time_elapsed | 514 |\n", + "| total_timesteps | 98898 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.74 |\n", + "| n_updates | 2037 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8944 |\n", + "| fps | 192 |\n", + "| time_elapsed | 514 |\n", + "| total_timesteps | 98934 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.68 |\n", + "| n_updates | 2039 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8948 |\n", + "| fps | 192 |\n", + "| time_elapsed | 515 |\n", + "| total_timesteps | 98982 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.03 |\n", + "| n_updates | 2041 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8952 |\n", + "| fps | 192 |\n", + "| time_elapsed | 515 |\n", + "| total_timesteps | 99018 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 2042 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8956 |\n", + "| fps | 191 |\n", + "| time_elapsed | 515 |\n", + "| total_timesteps | 99060 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.38 |\n", + "| n_updates | 2044 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8960 |\n", + "| fps | 191 |\n", + "| time_elapsed | 516 |\n", + "| total_timesteps | 99102 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.74 |\n", + "| n_updates | 2046 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8964 |\n", + "| fps | 191 |\n", + "| time_elapsed | 516 |\n", + "| total_timesteps | 99156 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.19 |\n", + "| n_updates | 2048 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8968 |\n", + "| fps | 191 |\n", + "| time_elapsed | 517 |\n", + "| total_timesteps | 99210 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 2050 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8972 |\n", + "| fps | 191 |\n", + "| time_elapsed | 517 |\n", + "| total_timesteps | 99252 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 2052 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8976 |\n", + "| fps | 191 |\n", + "| time_elapsed | 517 |\n", + "| total_timesteps | 99294 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.68 |\n", + "| n_updates | 2054 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8980 |\n", + "| fps | 191 |\n", + "| time_elapsed | 518 |\n", + "| total_timesteps | 99336 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 2055 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8984 |\n", + "| fps | 191 |\n", + "| time_elapsed | 518 |\n", + "| total_timesteps | 99396 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.95 |\n", + "| n_updates | 2058 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8988 |\n", + "| fps | 191 |\n", + "| time_elapsed | 518 |\n", + "| total_timesteps | 99432 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 2059 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8992 |\n", + "| fps | 191 |\n", + "| time_elapsed | 519 |\n", + "| total_timesteps | 99468 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.79 |\n", + "| n_updates | 2061 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 8996 |\n", + "| fps | 191 |\n", + "| time_elapsed | 519 |\n", + "| total_timesteps | 99516 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.6 |\n", + "| n_updates | 2063 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9000 |\n", + "| fps | 191 |\n", + "| time_elapsed | 520 |\n", + "| total_timesteps | 99600 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.69 |\n", + "| n_updates | 2066 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9004 |\n", + "| fps | 191 |\n", + "| time_elapsed | 520 |\n", + "| total_timesteps | 99642 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.5 |\n", + "| n_updates | 2068 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9008 |\n", + "| fps | 191 |\n", + "| time_elapsed | 521 |\n", + "| total_timesteps | 99702 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.75 |\n", + "| n_updates | 2071 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9012 |\n", + "| fps | 191 |\n", + "| time_elapsed | 521 |\n", + "| total_timesteps | 99738 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.55 |\n", + "| n_updates | 2072 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9016 |\n", + "| fps | 191 |\n", + "| time_elapsed | 521 |\n", + "| total_timesteps | 99774 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.78 |\n", + "| n_updates | 2074 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9020 |\n", + "| fps | 191 |\n", + "| time_elapsed | 522 |\n", + "| total_timesteps | 99822 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 2076 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9024 |\n", + "| fps | 191 |\n", + "| time_elapsed | 522 |\n", + "| total_timesteps | 99864 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.91 |\n", + "| n_updates | 2077 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9028 |\n", + "| fps | 191 |\n", + "| time_elapsed | 522 |\n", + "| total_timesteps | 99900 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.8 |\n", + "| n_updates | 2079 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9032 |\n", + "| fps | 191 |\n", + "| time_elapsed | 523 |\n", + "| total_timesteps | 99942 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.46 |\n", + "| n_updates | 2081 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9036 |\n", + "| fps | 191 |\n", + "| time_elapsed | 523 |\n", + "| total_timesteps | 99984 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.9 |\n", + "| n_updates | 2082 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9040 |\n", + "| fps | 191 |\n", + "| time_elapsed | 523 |\n", + "| total_timesteps | 100020 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.81 |\n", + "| n_updates | 2084 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9044 |\n", + "| fps | 190 |\n", + "| time_elapsed | 524 |\n", + "| total_timesteps | 100062 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.53 |\n", + "| n_updates | 2086 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9048 |\n", + "| fps | 190 |\n", + "| time_elapsed | 524 |\n", + "| total_timesteps | 100098 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.72 |\n", + "| n_updates | 2087 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9052 |\n", + "| fps | 190 |\n", + "| time_elapsed | 524 |\n", + "| total_timesteps | 100122 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.87 |\n", + "| n_updates | 2088 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9056 |\n", + "| fps | 190 |\n", + "| time_elapsed | 524 |\n", + "| total_timesteps | 100164 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.86 |\n", + "| n_updates | 2090 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9060 |\n", + "| fps | 190 |\n", + "| time_elapsed | 525 |\n", + "| total_timesteps | 100206 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.38 |\n", + "| n_updates | 2092 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9064 |\n", + "| fps | 190 |\n", + "| time_elapsed | 525 |\n", + "| total_timesteps | 100260 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.22 |\n", + "| n_updates | 2094 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9068 |\n", + "| fps | 190 |\n", + "| time_elapsed | 526 |\n", + "| total_timesteps | 100296 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.85 |\n", + "| n_updates | 2095 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9072 |\n", + "| fps | 190 |\n", + "| time_elapsed | 526 |\n", + "| total_timesteps | 100368 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 2098 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9076 |\n", + "| fps | 190 |\n", + "| time_elapsed | 527 |\n", + "| total_timesteps | 100440 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.66 |\n", + "| n_updates | 2101 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9080 |\n", + "| fps | 190 |\n", + "| time_elapsed | 527 |\n", + "| total_timesteps | 100488 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.53 |\n", + "| n_updates | 2103 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9084 |\n", + "| fps | 190 |\n", + "| time_elapsed | 528 |\n", + "| total_timesteps | 100530 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.31 |\n", + "| n_updates | 2105 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9088 |\n", + "| fps | 190 |\n", + "| time_elapsed | 529 |\n", + "| total_timesteps | 100614 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.65 |\n", + "| n_updates | 2109 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9092 |\n", + "| fps | 190 |\n", + "| time_elapsed | 529 |\n", + "| total_timesteps | 100662 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 2111 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9096 |\n", + "| fps | 190 |\n", + "| time_elapsed | 530 |\n", + "| total_timesteps | 100728 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.65 |\n", + "| n_updates | 2113 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9100 |\n", + "| fps | 189 |\n", + "| time_elapsed | 530 |\n", + "| total_timesteps | 100764 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.66 |\n", + "| n_updates | 2115 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9104 |\n", + "| fps | 189 |\n", + "| time_elapsed | 530 |\n", + "| total_timesteps | 100806 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.77 |\n", + "| n_updates | 2117 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9108 |\n", + "| fps | 189 |\n", + "| time_elapsed | 531 |\n", + "| total_timesteps | 100842 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 2118 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9112 |\n", + "| fps | 189 |\n", + "| time_elapsed | 531 |\n", + "| total_timesteps | 100914 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.41 |\n", + "| n_updates | 2121 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9116 |\n", + "| fps | 189 |\n", + "| time_elapsed | 531 |\n", + "| total_timesteps | 100962 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.7 |\n", + "| n_updates | 2123 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9120 |\n", + "| fps | 189 |\n", + "| time_elapsed | 532 |\n", + "| total_timesteps | 101010 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.38 |\n", + "| n_updates | 2125 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9124 |\n", + "| fps | 189 |\n", + "| time_elapsed | 532 |\n", + "| total_timesteps | 101052 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.55 |\n", + "| n_updates | 2127 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9128 |\n", + "| fps | 189 |\n", + "| time_elapsed | 533 |\n", + "| total_timesteps | 101082 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.74 |\n", + "| n_updates | 2128 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9132 |\n", + "| fps | 189 |\n", + "| time_elapsed | 533 |\n", + "| total_timesteps | 101124 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 2130 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9136 |\n", + "| fps | 189 |\n", + "| time_elapsed | 533 |\n", + "| total_timesteps | 101166 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.89 |\n", + "| n_updates | 2132 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9140 |\n", + "| fps | 189 |\n", + "| time_elapsed | 534 |\n", + "| total_timesteps | 101214 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.77 |\n", + "| n_updates | 2134 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9144 |\n", + "| fps | 189 |\n", + "| time_elapsed | 534 |\n", + "| total_timesteps | 101262 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.52 |\n", + "| n_updates | 2136 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9148 |\n", + "| fps | 189 |\n", + "| time_elapsed | 534 |\n", + "| total_timesteps | 101292 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.39 |\n", + "| n_updates | 2137 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9152 |\n", + "| fps | 189 |\n", + "| time_elapsed | 534 |\n", + "| total_timesteps | 101316 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.74 |\n", + "| n_updates | 2138 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9156 |\n", + "| fps | 189 |\n", + "| time_elapsed | 535 |\n", + "| total_timesteps | 101346 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.25 |\n", + "| n_updates | 2139 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9160 |\n", + "| fps | 189 |\n", + "| time_elapsed | 535 |\n", + "| total_timesteps | 101388 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.95 |\n", + "| n_updates | 2141 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9164 |\n", + "| fps | 189 |\n", + "| time_elapsed | 535 |\n", + "| total_timesteps | 101412 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.45 |\n", + "| n_updates | 2142 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9168 |\n", + "| fps | 189 |\n", + "| time_elapsed | 536 |\n", + "| total_timesteps | 101442 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.33 |\n", + "| n_updates | 2143 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9172 |\n", + "| fps | 189 |\n", + "| time_elapsed | 536 |\n", + "| total_timesteps | 101478 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 2145 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9176 |\n", + "| fps | 189 |\n", + "| time_elapsed | 537 |\n", + "| total_timesteps | 101610 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.33 |\n", + "| n_updates | 2150 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9180 |\n", + "| fps | 189 |\n", + "| time_elapsed | 537 |\n", + "| total_timesteps | 101646 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.97 |\n", + "| n_updates | 2152 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9184 |\n", + "| fps | 189 |\n", + "| time_elapsed | 537 |\n", + "| total_timesteps | 101664 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9188 |\n", + "| fps | 189 |\n", + "| time_elapsed | 538 |\n", + "| total_timesteps | 101706 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.74 |\n", + "| n_updates | 2154 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9192 |\n", + "| fps | 188 |\n", + "| time_elapsed | 538 |\n", + "| total_timesteps | 101742 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.78 |\n", + "| n_updates | 2156 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9196 |\n", + "| fps | 188 |\n", + "| time_elapsed | 538 |\n", + "| total_timesteps | 101790 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.8 |\n", + "| n_updates | 2158 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9200 |\n", + "| fps | 188 |\n", + "| time_elapsed | 539 |\n", + "| total_timesteps | 101838 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 2160 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9204 |\n", + "| fps | 188 |\n", + "| time_elapsed | 539 |\n", + "| total_timesteps | 101880 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 2161 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9208 |\n", + "| fps | 188 |\n", + "| time_elapsed | 539 |\n", + "| total_timesteps | 101916 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.5 |\n", + "| n_updates | 2163 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9212 |\n", + "| fps | 188 |\n", + "| time_elapsed | 540 |\n", + "| total_timesteps | 101946 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.31 |\n", + "| n_updates | 2164 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9216 |\n", + "| fps | 188 |\n", + "| time_elapsed | 540 |\n", + "| total_timesteps | 101982 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.43 |\n", + "| n_updates | 2166 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9220 |\n", + "| fps | 188 |\n", + "| time_elapsed | 540 |\n", + "| total_timesteps | 102024 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.51 |\n", + "| n_updates | 2167 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9224 |\n", + "| fps | 188 |\n", + "| time_elapsed | 541 |\n", + "| total_timesteps | 102054 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.62 |\n", + "| n_updates | 2169 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9228 |\n", + "| fps | 188 |\n", + "| time_elapsed | 541 |\n", + "| total_timesteps | 102108 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 2171 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9232 |\n", + "| fps | 188 |\n", + "| time_elapsed | 541 |\n", + "| total_timesteps | 102138 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.77 |\n", + "| n_updates | 2172 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9236 |\n", + "| fps | 188 |\n", + "| time_elapsed | 541 |\n", + "| total_timesteps | 102168 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.89 |\n", + "| n_updates | 2173 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9240 |\n", + "| fps | 188 |\n", + "| time_elapsed | 542 |\n", + "| total_timesteps | 102228 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.6 |\n", + "| n_updates | 2176 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9244 |\n", + "| fps | 188 |\n", + "| time_elapsed | 542 |\n", + "| total_timesteps | 102246 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.3 |\n", + "| n_updates | 2177 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9248 |\n", + "| fps | 188 |\n", + "| time_elapsed | 542 |\n", + "| total_timesteps | 102282 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.91 |\n", + "| n_updates | 2178 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9252 |\n", + "| fps | 188 |\n", + "| time_elapsed | 543 |\n", + "| total_timesteps | 102318 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 2180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9256 |\n", + "| fps | 188 |\n", + "| time_elapsed | 543 |\n", + "| total_timesteps | 102348 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.82 |\n", + "| n_updates | 2181 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9260 |\n", + "| fps | 188 |\n", + "| time_elapsed | 543 |\n", + "| total_timesteps | 102378 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.99 |\n", + "| n_updates | 2182 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9264 |\n", + "| fps | 188 |\n", + "| time_elapsed | 544 |\n", + "| total_timesteps | 102438 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.64 |\n", + "| n_updates | 2185 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9268 |\n", + "| fps | 188 |\n", + "| time_elapsed | 544 |\n", + "| total_timesteps | 102468 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.67 |\n", + "| n_updates | 2186 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9272 |\n", + "| fps | 188 |\n", + "| time_elapsed | 544 |\n", + "| total_timesteps | 102504 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.59 |\n", + "| n_updates | 2187 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9276 |\n", + "| fps | 188 |\n", + "| time_elapsed | 544 |\n", + "| total_timesteps | 102540 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.82 |\n", + "| n_updates | 2189 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9280 |\n", + "| fps | 188 |\n", + "| time_elapsed | 546 |\n", + "| total_timesteps | 102690 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 2195 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9284 |\n", + "| fps | 188 |\n", + "| time_elapsed | 546 |\n", + "| total_timesteps | 102720 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.32 |\n", + "| n_updates | 2196 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9288 |\n", + "| fps | 187 |\n", + "| time_elapsed | 546 |\n", + "| total_timesteps | 102750 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.8 |\n", + "| n_updates | 2198 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9292 |\n", + "| fps | 187 |\n", + "| time_elapsed | 546 |\n", + "| total_timesteps | 102768 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9296 |\n", + "| fps | 187 |\n", + "| time_elapsed | 546 |\n", + "| total_timesteps | 102792 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.7 |\n", + "| n_updates | 2199 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9300 |\n", + "| fps | 187 |\n", + "| time_elapsed | 547 |\n", + "| total_timesteps | 102828 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.8 |\n", + "| n_updates | 2201 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9304 |\n", + "| fps | 187 |\n", + "| time_elapsed | 548 |\n", + "| total_timesteps | 102918 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 2205 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9308 |\n", + "| fps | 187 |\n", + "| time_elapsed | 548 |\n", + "| total_timesteps | 102990 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.57 |\n", + "| n_updates | 2208 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9312 |\n", + "| fps | 187 |\n", + "| time_elapsed | 548 |\n", + "| total_timesteps | 103014 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.7 |\n", + "| n_updates | 2209 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9316 |\n", + "| fps | 187 |\n", + "| time_elapsed | 548 |\n", + "| total_timesteps | 103038 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 2210 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9320 |\n", + "| fps | 187 |\n", + "| time_elapsed | 549 |\n", + "| total_timesteps | 103098 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.45 |\n", + "| n_updates | 2212 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9324 |\n", + "| fps | 187 |\n", + "| time_elapsed | 549 |\n", + "| total_timesteps | 103152 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.86 |\n", + "| n_updates | 2214 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9328 |\n", + "| fps | 187 |\n", + "| time_elapsed | 550 |\n", + "| total_timesteps | 103212 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 2217 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9332 |\n", + "| fps | 187 |\n", + "| time_elapsed | 551 |\n", + "| total_timesteps | 103302 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 2221 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9336 |\n", + "| fps | 187 |\n", + "| time_elapsed | 551 |\n", + "| total_timesteps | 103356 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.5 |\n", + "| n_updates | 2223 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9340 |\n", + "| fps | 187 |\n", + "| time_elapsed | 551 |\n", + "| total_timesteps | 103392 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.66 |\n", + "| n_updates | 2224 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9344 |\n", + "| fps | 187 |\n", + "| time_elapsed | 552 |\n", + "| total_timesteps | 103470 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 2228 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9348 |\n", + "| fps | 187 |\n", + "| time_elapsed | 552 |\n", + "| total_timesteps | 103512 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.08 |\n", + "| n_updates | 2229 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9352 |\n", + "| fps | 187 |\n", + "| time_elapsed | 553 |\n", + "| total_timesteps | 103554 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.69 |\n", + "| n_updates | 2231 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9356 |\n", + "| fps | 187 |\n", + "| time_elapsed | 553 |\n", + "| total_timesteps | 103596 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.63 |\n", + "| n_updates | 2233 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9360 |\n", + "| fps | 187 |\n", + "| time_elapsed | 553 |\n", + "| total_timesteps | 103638 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.8 |\n", + "| n_updates | 2235 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9364 |\n", + "| fps | 187 |\n", + "| time_elapsed | 554 |\n", + "| total_timesteps | 103710 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.53 |\n", + "| n_updates | 2238 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9368 |\n", + "| fps | 187 |\n", + "| time_elapsed | 554 |\n", + "| total_timesteps | 103776 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.1 |\n", + "| n_updates | 2240 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9372 |\n", + "| fps | 187 |\n", + "| time_elapsed | 555 |\n", + "| total_timesteps | 103818 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.35 |\n", + "| n_updates | 2242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9376 |\n", + "| fps | 186 |\n", + "| time_elapsed | 555 |\n", + "| total_timesteps | 103854 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.03 |\n", + "| n_updates | 2244 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9380 |\n", + "| fps | 186 |\n", + "| time_elapsed | 555 |\n", + "| total_timesteps | 103896 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 2245 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9384 |\n", + "| fps | 186 |\n", + "| time_elapsed | 556 |\n", + "| total_timesteps | 103932 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.19 |\n", + "| n_updates | 2247 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9388 |\n", + "| fps | 186 |\n", + "| time_elapsed | 556 |\n", + "| total_timesteps | 104004 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.52 |\n", + "| n_updates | 2250 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9392 |\n", + "| fps | 186 |\n", + "| time_elapsed | 556 |\n", + "| total_timesteps | 104034 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.53 |\n", + "| n_updates | 2251 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9396 |\n", + "| fps | 186 |\n", + "| time_elapsed | 557 |\n", + "| total_timesteps | 104064 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 2252 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9400 |\n", + "| fps | 186 |\n", + "| time_elapsed | 557 |\n", + "| total_timesteps | 104106 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.38 |\n", + "| n_updates | 2254 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9404 |\n", + "| fps | 186 |\n", + "| time_elapsed | 557 |\n", + "| total_timesteps | 104148 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 2256 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9408 |\n", + "| fps | 186 |\n", + "| time_elapsed | 558 |\n", + "| total_timesteps | 104196 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.57 |\n", + "| n_updates | 2258 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9412 |\n", + "| fps | 186 |\n", + "| time_elapsed | 558 |\n", + "| total_timesteps | 104256 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.71 |\n", + "| n_updates | 2260 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9416 |\n", + "| fps | 186 |\n", + "| time_elapsed | 559 |\n", + "| total_timesteps | 104328 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 2263 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9420 |\n", + "| fps | 186 |\n", + "| time_elapsed | 559 |\n", + "| total_timesteps | 104376 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.68 |\n", + "| n_updates | 2265 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9424 |\n", + "| fps | 186 |\n", + "| time_elapsed | 560 |\n", + "| total_timesteps | 104436 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.75 |\n", + "| n_updates | 2268 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9428 |\n", + "| fps | 186 |\n", + "| time_elapsed | 560 |\n", + "| total_timesteps | 104502 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.68 |\n", + "| n_updates | 2271 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9432 |\n", + "| fps | 186 |\n", + "| time_elapsed | 560 |\n", + "| total_timesteps | 104538 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.6 |\n", + "| n_updates | 2272 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9436 |\n", + "| fps | 186 |\n", + "| time_elapsed | 561 |\n", + "| total_timesteps | 104574 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.85 |\n", + "| n_updates | 2274 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9440 |\n", + "| fps | 186 |\n", + "| time_elapsed | 561 |\n", + "| total_timesteps | 104610 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.25 |\n", + "| n_updates | 2275 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9444 |\n", + "| fps | 186 |\n", + "| time_elapsed | 562 |\n", + "| total_timesteps | 104670 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.44 |\n", + "| n_updates | 2278 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9448 |\n", + "| fps | 186 |\n", + "| time_elapsed | 562 |\n", + "| total_timesteps | 104730 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.53 |\n", + "| n_updates | 2280 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9452 |\n", + "| fps | 186 |\n", + "| time_elapsed | 562 |\n", + "| total_timesteps | 104760 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.44 |\n", + "| n_updates | 2281 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9456 |\n", + "| fps | 186 |\n", + "| time_elapsed | 563 |\n", + "| total_timesteps | 104790 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.35 |\n", + "| n_updates | 2283 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9460 |\n", + "| fps | 186 |\n", + "| time_elapsed | 563 |\n", + "| total_timesteps | 104820 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.18 |\n", + "| n_updates | 2284 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9464 |\n", + "| fps | 186 |\n", + "| time_elapsed | 563 |\n", + "| total_timesteps | 104844 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.6 |\n", + "| n_updates | 2285 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9468 |\n", + "| fps | 186 |\n", + "| time_elapsed | 563 |\n", + "| total_timesteps | 104868 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.43 |\n", + "| n_updates | 2286 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9472 |\n", + "| fps | 186 |\n", + "| time_elapsed | 563 |\n", + "| total_timesteps | 104904 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.89 |\n", + "| n_updates | 2287 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9476 |\n", + "| fps | 185 |\n", + "| time_elapsed | 564 |\n", + "| total_timesteps | 104988 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.68 |\n", + "| n_updates | 2291 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9480 |\n", + "| fps | 185 |\n", + "| time_elapsed | 565 |\n", + "| total_timesteps | 105042 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.79 |\n", + "| n_updates | 2293 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9484 |\n", + "| fps | 185 |\n", + "| time_elapsed | 565 |\n", + "| total_timesteps | 105072 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.59 |\n", + "| n_updates | 2294 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9488 |\n", + "| fps | 185 |\n", + "| time_elapsed | 565 |\n", + "| total_timesteps | 105102 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 2296 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9492 |\n", + "| fps | 185 |\n", + "| time_elapsed | 565 |\n", + "| total_timesteps | 105144 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 2297 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9496 |\n", + "| fps | 185 |\n", + "| time_elapsed | 566 |\n", + "| total_timesteps | 105186 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 2299 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9500 |\n", + "| fps | 185 |\n", + "| time_elapsed | 566 |\n", + "| total_timesteps | 105246 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 2302 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9504 |\n", + "| fps | 185 |\n", + "| time_elapsed | 567 |\n", + "| total_timesteps | 105324 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 2305 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9508 |\n", + "| fps | 185 |\n", + "| time_elapsed | 568 |\n", + "| total_timesteps | 105402 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.86 |\n", + "| n_updates | 2308 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9512 |\n", + "| fps | 185 |\n", + "| time_elapsed | 568 |\n", + "| total_timesteps | 105450 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.73 |\n", + "| n_updates | 2310 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9516 |\n", + "| fps | 185 |\n", + "| time_elapsed | 568 |\n", + "| total_timesteps | 105492 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 2312 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9520 |\n", + "| fps | 185 |\n", + "| time_elapsed | 569 |\n", + "| total_timesteps | 105534 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 2314 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9524 |\n", + "| fps | 185 |\n", + "| time_elapsed | 569 |\n", + "| total_timesteps | 105612 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 2317 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9528 |\n", + "| fps | 185 |\n", + "| time_elapsed | 570 |\n", + "| total_timesteps | 105660 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.56 |\n", + "| n_updates | 2319 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9532 |\n", + "| fps | 185 |\n", + "| time_elapsed | 570 |\n", + "| total_timesteps | 105708 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 2321 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9536 |\n", + "| fps | 185 |\n", + "| time_elapsed | 571 |\n", + "| total_timesteps | 105792 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.52 |\n", + "| n_updates | 2324 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9540 |\n", + "| fps | 185 |\n", + "| time_elapsed | 571 |\n", + "| total_timesteps | 105834 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.33 |\n", + "| n_updates | 2326 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9544 |\n", + "| fps | 185 |\n", + "| time_elapsed | 571 |\n", + "| total_timesteps | 105876 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.46 |\n", + "| n_updates | 2328 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9548 |\n", + "| fps | 185 |\n", + "| time_elapsed | 572 |\n", + "| total_timesteps | 105912 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.64 |\n", + "| n_updates | 2329 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9552 |\n", + "| fps | 185 |\n", + "| time_elapsed | 572 |\n", + "| total_timesteps | 105942 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.34 |\n", + "| n_updates | 2331 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9556 |\n", + "| fps | 185 |\n", + "| time_elapsed | 572 |\n", + "| total_timesteps | 105954 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9560 |\n", + "| fps | 184 |\n", + "| time_elapsed | 572 |\n", + "| total_timesteps | 105990 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.72 |\n", + "| n_updates | 2333 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9564 |\n", + "| fps | 184 |\n", + "| time_elapsed | 573 |\n", + "| total_timesteps | 106026 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.76 |\n", + "| n_updates | 2334 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9568 |\n", + "| fps | 184 |\n", + "| time_elapsed | 573 |\n", + "| total_timesteps | 106062 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.69 |\n", + "| n_updates | 2336 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9572 |\n", + "| fps | 184 |\n", + "| time_elapsed | 573 |\n", + "| total_timesteps | 106098 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.65 |\n", + "| n_updates | 2337 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9576 |\n", + "| fps | 184 |\n", + "| time_elapsed | 574 |\n", + "| total_timesteps | 106110 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.89 |\n", + "| n_updates | 2338 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9580 |\n", + "| fps | 184 |\n", + "| time_elapsed | 574 |\n", + "| total_timesteps | 106146 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.5 |\n", + "| n_updates | 2339 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9584 |\n", + "| fps | 184 |\n", + "| time_elapsed | 574 |\n", + "| total_timesteps | 106182 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 2341 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9588 |\n", + "| fps | 184 |\n", + "| time_elapsed | 574 |\n", + "| total_timesteps | 106212 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.19 |\n", + "| n_updates | 2342 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9592 |\n", + "| fps | 184 |\n", + "| time_elapsed | 575 |\n", + "| total_timesteps | 106272 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.47 |\n", + "| n_updates | 2344 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9596 |\n", + "| fps | 184 |\n", + "| time_elapsed | 575 |\n", + "| total_timesteps | 106308 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.59 |\n", + "| n_updates | 2346 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9600 |\n", + "| fps | 184 |\n", + "| time_elapsed | 576 |\n", + "| total_timesteps | 106374 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.57 |\n", + "| n_updates | 2349 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9604 |\n", + "| fps | 184 |\n", + "| time_elapsed | 576 |\n", + "| total_timesteps | 106410 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.8 |\n", + "| n_updates | 2350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9608 |\n", + "| fps | 184 |\n", + "| time_elapsed | 576 |\n", + "| total_timesteps | 106446 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.75 |\n", + "| n_updates | 2352 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9612 |\n", + "| fps | 184 |\n", + "| time_elapsed | 576 |\n", + "| total_timesteps | 106488 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.76 |\n", + "| n_updates | 2353 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9616 |\n", + "| fps | 184 |\n", + "| time_elapsed | 577 |\n", + "| total_timesteps | 106500 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.81 |\n", + "| n_updates | 2354 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9620 |\n", + "| fps | 184 |\n", + "| time_elapsed | 577 |\n", + "| total_timesteps | 106530 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.05 |\n", + "| n_updates | 2355 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9624 |\n", + "| fps | 184 |\n", + "| time_elapsed | 577 |\n", + "| total_timesteps | 106566 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.76 |\n", + "| n_updates | 2357 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9628 |\n", + "| fps | 184 |\n", + "| time_elapsed | 577 |\n", + "| total_timesteps | 106608 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.6 |\n", + "| n_updates | 2358 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9632 |\n", + "| fps | 184 |\n", + "| time_elapsed | 578 |\n", + "| total_timesteps | 106650 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 2360 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9636 |\n", + "| fps | 184 |\n", + "| time_elapsed | 578 |\n", + "| total_timesteps | 106698 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.66 |\n", + "| n_updates | 2362 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9640 |\n", + "| fps | 184 |\n", + "| time_elapsed | 578 |\n", + "| total_timesteps | 106728 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.16 |\n", + "| n_updates | 2363 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9644 |\n", + "| fps | 184 |\n", + "| time_elapsed | 579 |\n", + "| total_timesteps | 106764 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.46 |\n", + "| n_updates | 2365 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9648 |\n", + "| fps | 184 |\n", + "| time_elapsed | 579 |\n", + "| total_timesteps | 106806 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 2367 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9652 |\n", + "| fps | 184 |\n", + "| time_elapsed | 579 |\n", + "| total_timesteps | 106836 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.78 |\n", + "| n_updates | 2368 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9656 |\n", + "| fps | 184 |\n", + "| time_elapsed | 580 |\n", + "| total_timesteps | 106896 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.76 |\n", + "| n_updates | 2370 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9660 |\n", + "| fps | 184 |\n", + "| time_elapsed | 580 |\n", + "| total_timesteps | 106932 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.72 |\n", + "| n_updates | 2372 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9664 |\n", + "| fps | 184 |\n", + "| time_elapsed | 580 |\n", + "| total_timesteps | 106956 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.43 |\n", + "| n_updates | 2373 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9668 |\n", + "| fps | 184 |\n", + "| time_elapsed | 581 |\n", + "| total_timesteps | 106986 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.4 |\n", + "| n_updates | 2374 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9672 |\n", + "| fps | 184 |\n", + "| time_elapsed | 581 |\n", + "| total_timesteps | 107022 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.77 |\n", + "| n_updates | 2376 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9676 |\n", + "| fps | 184 |\n", + "| time_elapsed | 581 |\n", + "| total_timesteps | 107070 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.91 |\n", + "| n_updates | 2378 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9680 |\n", + "| fps | 183 |\n", + "| time_elapsed | 582 |\n", + "| total_timesteps | 107112 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 2379 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9684 |\n", + "| fps | 183 |\n", + "| time_elapsed | 582 |\n", + "| total_timesteps | 107160 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.64 |\n", + "| n_updates | 2381 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9688 |\n", + "| fps | 183 |\n", + "| time_elapsed | 582 |\n", + "| total_timesteps | 107196 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.11 |\n", + "| n_updates | 2383 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9692 |\n", + "| fps | 183 |\n", + "| time_elapsed | 583 |\n", + "| total_timesteps | 107220 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 2384 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9696 |\n", + "| fps | 183 |\n", + "| time_elapsed | 583 |\n", + "| total_timesteps | 107244 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.92 |\n", + "| n_updates | 2385 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9700 |\n", + "| fps | 183 |\n", + "| time_elapsed | 583 |\n", + "| total_timesteps | 107280 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.52 |\n", + "| n_updates | 2386 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9704 |\n", + "| fps | 183 |\n", + "| time_elapsed | 583 |\n", + "| total_timesteps | 107316 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.79 |\n", + "| n_updates | 2388 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9708 |\n", + "| fps | 183 |\n", + "| time_elapsed | 584 |\n", + "| total_timesteps | 107364 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.8 |\n", + "| n_updates | 2390 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9712 |\n", + "| fps | 183 |\n", + "| time_elapsed | 584 |\n", + "| total_timesteps | 107406 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.29 |\n", + "| n_updates | 2392 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9716 |\n", + "| fps | 183 |\n", + "| time_elapsed | 584 |\n", + "| total_timesteps | 107436 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.26 |\n", + "| n_updates | 2393 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9720 |\n", + "| fps | 183 |\n", + "| time_elapsed | 585 |\n", + "| total_timesteps | 107478 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 2395 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9724 |\n", + "| fps | 183 |\n", + "| time_elapsed | 585 |\n", + "| total_timesteps | 107514 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 2396 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9728 |\n", + "| fps | 183 |\n", + "| time_elapsed | 585 |\n", + "| total_timesteps | 107550 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.53 |\n", + "| n_updates | 2398 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9732 |\n", + "| fps | 183 |\n", + "| time_elapsed | 586 |\n", + "| total_timesteps | 107574 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 2399 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9736 |\n", + "| fps | 183 |\n", + "| time_elapsed | 586 |\n", + "| total_timesteps | 107604 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.27 |\n", + "| n_updates | 2400 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9740 |\n", + "| fps | 183 |\n", + "| time_elapsed | 586 |\n", + "| total_timesteps | 107640 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.33 |\n", + "| n_updates | 2401 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9744 |\n", + "| fps | 183 |\n", + "| time_elapsed | 586 |\n", + "| total_timesteps | 107682 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 2403 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9748 |\n", + "| fps | 183 |\n", + "| time_elapsed | 587 |\n", + "| total_timesteps | 107724 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.86 |\n", + "| n_updates | 2405 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9752 |\n", + "| fps | 183 |\n", + "| time_elapsed | 587 |\n", + "| total_timesteps | 107742 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.92 |\n", + "| n_updates | 2406 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9756 |\n", + "| fps | 183 |\n", + "| time_elapsed | 587 |\n", + "| total_timesteps | 107778 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.66 |\n", + "| n_updates | 2407 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9760 |\n", + "| fps | 183 |\n", + "| time_elapsed | 588 |\n", + "| total_timesteps | 107820 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 2409 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9764 |\n", + "| fps | 183 |\n", + "| time_elapsed | 588 |\n", + "| total_timesteps | 107874 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.45 |\n", + "| n_updates | 2411 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9768 |\n", + "| fps | 183 |\n", + "| time_elapsed | 588 |\n", + "| total_timesteps | 107910 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.57 |\n", + "| n_updates | 2413 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9772 |\n", + "| fps | 183 |\n", + "| time_elapsed | 589 |\n", + "| total_timesteps | 107952 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.76 |\n", + "| n_updates | 2414 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9776 |\n", + "| fps | 183 |\n", + "| time_elapsed | 589 |\n", + "| total_timesteps | 107994 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.7 |\n", + "| n_updates | 2416 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9780 |\n", + "| fps | 183 |\n", + "| time_elapsed | 589 |\n", + "| total_timesteps | 108018 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.95 |\n", + "| n_updates | 2417 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9784 |\n", + "| fps | 183 |\n", + "| time_elapsed | 590 |\n", + "| total_timesteps | 108102 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.1 |\n", + "| n_updates | 2421 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9788 |\n", + "| fps | 183 |\n", + "| time_elapsed | 590 |\n", + "| total_timesteps | 108150 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.08 |\n", + "| n_updates | 2423 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9792 |\n", + "| fps | 182 |\n", + "| time_elapsed | 591 |\n", + "| total_timesteps | 108246 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.85 |\n", + "| n_updates | 2427 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9796 |\n", + "| fps | 182 |\n", + "| time_elapsed | 591 |\n", + "| total_timesteps | 108306 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.72 |\n", + "| n_updates | 2429 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9800 |\n", + "| fps | 182 |\n", + "| time_elapsed | 592 |\n", + "| total_timesteps | 108336 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.91 |\n", + "| n_updates | 2430 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9804 |\n", + "| fps | 182 |\n", + "| time_elapsed | 592 |\n", + "| total_timesteps | 108372 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 2432 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9808 |\n", + "| fps | 182 |\n", + "| time_elapsed | 592 |\n", + "| total_timesteps | 108420 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.59 |\n", + "| n_updates | 2434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9812 |\n", + "| fps | 182 |\n", + "| time_elapsed | 592 |\n", + "| total_timesteps | 108426 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9816 |\n", + "| fps | 182 |\n", + "| time_elapsed | 593 |\n", + "| total_timesteps | 108498 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.55 |\n", + "| n_updates | 2437 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9820 |\n", + "| fps | 182 |\n", + "| time_elapsed | 593 |\n", + "| total_timesteps | 108552 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.5 |\n", + "| n_updates | 2439 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9824 |\n", + "| fps | 182 |\n", + "| time_elapsed | 594 |\n", + "| total_timesteps | 108570 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.7 |\n", + "| n_updates | 2440 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9828 |\n", + "| fps | 182 |\n", + "| time_elapsed | 594 |\n", + "| total_timesteps | 108600 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.66 |\n", + "| n_updates | 2441 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9832 |\n", + "| fps | 182 |\n", + "| time_elapsed | 594 |\n", + "| total_timesteps | 108636 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 2443 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9836 |\n", + "| fps | 182 |\n", + "| time_elapsed | 595 |\n", + "| total_timesteps | 108684 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.43 |\n", + "| n_updates | 2445 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9840 |\n", + "| fps | 182 |\n", + "| time_elapsed | 595 |\n", + "| total_timesteps | 108732 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.6 |\n", + "| n_updates | 2447 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9844 |\n", + "| fps | 182 |\n", + "| time_elapsed | 595 |\n", + "| total_timesteps | 108768 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.85 |\n", + "| n_updates | 2448 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9848 |\n", + "| fps | 182 |\n", + "| time_elapsed | 596 |\n", + "| total_timesteps | 108816 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.82 |\n", + "| n_updates | 2450 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9852 |\n", + "| fps | 182 |\n", + "| time_elapsed | 596 |\n", + "| total_timesteps | 108858 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 2452 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9856 |\n", + "| fps | 182 |\n", + "| time_elapsed | 596 |\n", + "| total_timesteps | 108894 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.68 |\n", + "| n_updates | 2454 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9860 |\n", + "| fps | 182 |\n", + "| time_elapsed | 597 |\n", + "| total_timesteps | 108930 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.07 |\n", + "| n_updates | 2455 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9864 |\n", + "| fps | 182 |\n", + "| time_elapsed | 597 |\n", + "| total_timesteps | 108942 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.46 |\n", + "| n_updates | 2456 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9868 |\n", + "| fps | 182 |\n", + "| time_elapsed | 597 |\n", + "| total_timesteps | 109008 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.64 |\n", + "| n_updates | 2458 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9872 |\n", + "| fps | 182 |\n", + "| time_elapsed | 597 |\n", + "| total_timesteps | 109038 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.62 |\n", + "| n_updates | 2460 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9876 |\n", + "| fps | 182 |\n", + "| time_elapsed | 598 |\n", + "| total_timesteps | 109074 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.58 |\n", + "| n_updates | 2461 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9880 |\n", + "| fps | 182 |\n", + "| time_elapsed | 598 |\n", + "| total_timesteps | 109116 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.39 |\n", + "| n_updates | 2463 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9884 |\n", + "| fps | 182 |\n", + "| time_elapsed | 598 |\n", + "| total_timesteps | 109134 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.63 |\n", + "| n_updates | 2464 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9888 |\n", + "| fps | 182 |\n", + "| time_elapsed | 599 |\n", + "| total_timesteps | 109212 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.48 |\n", + "| n_updates | 2467 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9892 |\n", + "| fps | 182 |\n", + "| time_elapsed | 599 |\n", + "| total_timesteps | 109230 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 2468 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9896 |\n", + "| fps | 182 |\n", + "| time_elapsed | 599 |\n", + "| total_timesteps | 109260 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.83 |\n", + "| n_updates | 2469 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9900 |\n", + "| fps | 182 |\n", + "| time_elapsed | 600 |\n", + "| total_timesteps | 109308 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.71 |\n", + "| n_updates | 2471 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9904 |\n", + "| fps | 182 |\n", + "| time_elapsed | 600 |\n", + "| total_timesteps | 109362 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.08 |\n", + "| n_updates | 2473 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9908 |\n", + "| fps | 182 |\n", + "| time_elapsed | 600 |\n", + "| total_timesteps | 109398 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 2475 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9912 |\n", + "| fps | 182 |\n", + "| time_elapsed | 601 |\n", + "| total_timesteps | 109422 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.48 |\n", + "| n_updates | 2476 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9916 |\n", + "| fps | 182 |\n", + "| time_elapsed | 601 |\n", + "| total_timesteps | 109452 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.4 |\n", + "| n_updates | 2477 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9920 |\n", + "| fps | 181 |\n", + "| time_elapsed | 601 |\n", + "| total_timesteps | 109506 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.67 |\n", + "| n_updates | 2479 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9924 |\n", + "| fps | 181 |\n", + "| time_elapsed | 602 |\n", + "| total_timesteps | 109542 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.49 |\n", + "| n_updates | 2481 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9928 |\n", + "| fps | 181 |\n", + "| time_elapsed | 602 |\n", + "| total_timesteps | 109578 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.24 |\n", + "| n_updates | 2482 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9932 |\n", + "| fps | 181 |\n", + "| time_elapsed | 602 |\n", + "| total_timesteps | 109602 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.69 |\n", + "| n_updates | 2483 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9936 |\n", + "| fps | 181 |\n", + "| time_elapsed | 602 |\n", + "| total_timesteps | 109632 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.98 |\n", + "| n_updates | 2484 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9940 |\n", + "| fps | 181 |\n", + "| time_elapsed | 603 |\n", + "| total_timesteps | 109662 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 2486 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9944 |\n", + "| fps | 181 |\n", + "| time_elapsed | 603 |\n", + "| total_timesteps | 109686 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.62 |\n", + "| n_updates | 2487 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9948 |\n", + "| fps | 181 |\n", + "| time_elapsed | 603 |\n", + "| total_timesteps | 109710 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.78 |\n", + "| n_updates | 2488 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9952 |\n", + "| fps | 181 |\n", + "| time_elapsed | 603 |\n", + "| total_timesteps | 109734 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 2489 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9956 |\n", + "| fps | 181 |\n", + "| time_elapsed | 603 |\n", + "| total_timesteps | 109758 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.97 |\n", + "| n_updates | 2490 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9960 |\n", + "| fps | 181 |\n", + "| time_elapsed | 604 |\n", + "| total_timesteps | 109794 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 2491 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9964 |\n", + "| fps | 181 |\n", + "| time_elapsed | 604 |\n", + "| total_timesteps | 109824 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 2492 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9968 |\n", + "| fps | 181 |\n", + "| time_elapsed | 604 |\n", + "| total_timesteps | 109866 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.37 |\n", + "| n_updates | 2494 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9972 |\n", + "| fps | 181 |\n", + "| time_elapsed | 605 |\n", + "| total_timesteps | 109902 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.48 |\n", + "| n_updates | 2496 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9976 |\n", + "| fps | 181 |\n", + "| time_elapsed | 605 |\n", + "| total_timesteps | 109944 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.09 |\n", + "| n_updates | 2497 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9980 |\n", + "| fps | 181 |\n", + "| time_elapsed | 605 |\n", + "| total_timesteps | 109968 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.53 |\n", + "| n_updates | 2498 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9984 |\n", + "| fps | 181 |\n", + "| time_elapsed | 606 |\n", + "| total_timesteps | 110022 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 2501 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9988 |\n", + "| fps | 181 |\n", + "| time_elapsed | 606 |\n", + "| total_timesteps | 110052 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.66 |\n", + "| n_updates | 2502 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9992 |\n", + "| fps | 181 |\n", + "| time_elapsed | 606 |\n", + "| total_timesteps | 110094 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.59 |\n", + "| n_updates | 2504 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 9996 |\n", + "| fps | 181 |\n", + "| time_elapsed | 606 |\n", + "| total_timesteps | 110118 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.61 |\n", + "| n_updates | 2505 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10000 |\n", + "| fps | 181 |\n", + "| time_elapsed | 607 |\n", + "| total_timesteps | 110148 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 2506 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10004 |\n", + "| fps | 181 |\n", + "| time_elapsed | 607 |\n", + "| total_timesteps | 110184 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.87 |\n", + "| n_updates | 2507 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10008 |\n", + "| fps | 181 |\n", + "| time_elapsed | 607 |\n", + "| total_timesteps | 110244 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.61 |\n", + "| n_updates | 2510 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10012 |\n", + "| fps | 181 |\n", + "| time_elapsed | 608 |\n", + "| total_timesteps | 110286 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.67 |\n", + "| n_updates | 2512 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10016 |\n", + "| fps | 181 |\n", + "| time_elapsed | 608 |\n", + "| total_timesteps | 110370 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.37 |\n", + "| n_updates | 2515 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10020 |\n", + "| fps | 181 |\n", + "| time_elapsed | 609 |\n", + "| total_timesteps | 110448 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.59 |\n", + "| n_updates | 2518 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10024 |\n", + "| fps | 181 |\n", + "| time_elapsed | 609 |\n", + "| total_timesteps | 110508 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.6 |\n", + "| n_updates | 2521 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10028 |\n", + "| fps | 181 |\n", + "| time_elapsed | 610 |\n", + "| total_timesteps | 110550 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.71 |\n", + "| n_updates | 2523 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10032 |\n", + "| fps | 181 |\n", + "| time_elapsed | 610 |\n", + "| total_timesteps | 110592 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.7 |\n", + "| n_updates | 2524 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10036 |\n", + "| fps | 181 |\n", + "| time_elapsed | 611 |\n", + "| total_timesteps | 110700 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.35 |\n", + "| n_updates | 2529 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10040 |\n", + "| fps | 181 |\n", + "| time_elapsed | 611 |\n", + "| total_timesteps | 110736 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.38 |\n", + "| n_updates | 2530 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10044 |\n", + "| fps | 181 |\n", + "| time_elapsed | 611 |\n", + "| total_timesteps | 110778 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.05 |\n", + "| n_updates | 2532 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10048 |\n", + "| fps | 181 |\n", + "| time_elapsed | 612 |\n", + "| total_timesteps | 110796 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.95 |\n", + "| n_updates | 2533 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10052 |\n", + "| fps | 180 |\n", + "| time_elapsed | 612 |\n", + "| total_timesteps | 110856 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 2535 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10056 |\n", + "| fps | 180 |\n", + "| time_elapsed | 613 |\n", + "| total_timesteps | 110910 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.68 |\n", + "| n_updates | 2538 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10060 |\n", + "| fps | 180 |\n", + "| time_elapsed | 613 |\n", + "| total_timesteps | 110958 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.55 |\n", + "| n_updates | 2540 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10064 |\n", + "| fps | 180 |\n", + "| time_elapsed | 613 |\n", + "| total_timesteps | 111012 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.98 |\n", + "| n_updates | 2542 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10068 |\n", + "| fps | 180 |\n", + "| time_elapsed | 614 |\n", + "| total_timesteps | 111072 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.79 |\n", + "| n_updates | 2544 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10072 |\n", + "| fps | 180 |\n", + "| time_elapsed | 614 |\n", + "| total_timesteps | 111138 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 2547 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10076 |\n", + "| fps | 180 |\n", + "| time_elapsed | 615 |\n", + "| total_timesteps | 111174 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.35 |\n", + "| n_updates | 2549 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10080 |\n", + "| fps | 180 |\n", + "| time_elapsed | 615 |\n", + "| total_timesteps | 111204 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.74 |\n", + "| n_updates | 2550 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10084 |\n", + "| fps | 180 |\n", + "| time_elapsed | 615 |\n", + "| total_timesteps | 111240 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.75 |\n", + "| n_updates | 2551 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10088 |\n", + "| fps | 180 |\n", + "| time_elapsed | 616 |\n", + "| total_timesteps | 111312 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.61 |\n", + "| n_updates | 2554 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10092 |\n", + "| fps | 180 |\n", + "| time_elapsed | 616 |\n", + "| total_timesteps | 111354 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.65 |\n", + "| n_updates | 2556 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10096 |\n", + "| fps | 180 |\n", + "| time_elapsed | 616 |\n", + "| total_timesteps | 111390 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.67 |\n", + "| n_updates | 2558 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10100 |\n", + "| fps | 180 |\n", + "| time_elapsed | 617 |\n", + "| total_timesteps | 111426 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.72 |\n", + "| n_updates | 2559 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10104 |\n", + "| fps | 180 |\n", + "| time_elapsed | 617 |\n", + "| total_timesteps | 111462 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.69 |\n", + "| n_updates | 2561 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10108 |\n", + "| fps | 180 |\n", + "| time_elapsed | 617 |\n", + "| total_timesteps | 111492 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.77 |\n", + "| n_updates | 2562 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10112 |\n", + "| fps | 180 |\n", + "| time_elapsed | 618 |\n", + "| total_timesteps | 111588 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 2566 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10116 |\n", + "| fps | 180 |\n", + "| time_elapsed | 618 |\n", + "| total_timesteps | 111654 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.69 |\n", + "| n_updates | 2569 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10120 |\n", + "| fps | 180 |\n", + "| time_elapsed | 619 |\n", + "| total_timesteps | 111708 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.51 |\n", + "| n_updates | 2571 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10124 |\n", + "| fps | 180 |\n", + "| time_elapsed | 619 |\n", + "| total_timesteps | 111780 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.51 |\n", + "| n_updates | 2574 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10128 |\n", + "| fps | 180 |\n", + "| time_elapsed | 620 |\n", + "| total_timesteps | 111816 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.83 |\n", + "| n_updates | 2575 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10132 |\n", + "| fps | 180 |\n", + "| time_elapsed | 620 |\n", + "| total_timesteps | 111846 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 2577 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10136 |\n", + "| fps | 180 |\n", + "| time_elapsed | 620 |\n", + "| total_timesteps | 111876 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.52 |\n", + "| n_updates | 2578 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10140 |\n", + "| fps | 180 |\n", + "| time_elapsed | 620 |\n", + "| total_timesteps | 111918 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.75 |\n", + "| n_updates | 2580 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10144 |\n", + "| fps | 180 |\n", + "| time_elapsed | 621 |\n", + "| total_timesteps | 112002 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 2583 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10148 |\n", + "| fps | 180 |\n", + "| time_elapsed | 621 |\n", + "| total_timesteps | 112026 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.91 |\n", + "| n_updates | 2584 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10152 |\n", + "| fps | 180 |\n", + "| time_elapsed | 622 |\n", + "| total_timesteps | 112062 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.1 |\n", + "| n_updates | 2586 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10156 |\n", + "| fps | 180 |\n", + "| time_elapsed | 622 |\n", + "| total_timesteps | 112098 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 2587 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10160 |\n", + "| fps | 180 |\n", + "| time_elapsed | 623 |\n", + "| total_timesteps | 112194 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.74 |\n", + "| n_updates | 2591 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10164 |\n", + "| fps | 180 |\n", + "| time_elapsed | 623 |\n", + "| total_timesteps | 112248 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.68 |\n", + "| n_updates | 2593 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10168 |\n", + "| fps | 180 |\n", + "| time_elapsed | 623 |\n", + "| total_timesteps | 112284 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.73 |\n", + "| n_updates | 2595 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10172 |\n", + "| fps | 179 |\n", + "| time_elapsed | 624 |\n", + "| total_timesteps | 112332 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.57 |\n", + "| n_updates | 2597 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10176 |\n", + "| fps | 179 |\n", + "| time_elapsed | 624 |\n", + "| total_timesteps | 112368 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.7 |\n", + "| n_updates | 2598 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10180 |\n", + "| fps | 179 |\n", + "| time_elapsed | 624 |\n", + "| total_timesteps | 112386 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.25 |\n", + "| n_updates | 2599 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10184 |\n", + "| fps | 179 |\n", + "| time_elapsed | 625 |\n", + "| total_timesteps | 112422 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.19 |\n", + "| n_updates | 2601 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10188 |\n", + "| fps | 179 |\n", + "| time_elapsed | 625 |\n", + "| total_timesteps | 112446 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.66 |\n", + "| n_updates | 2602 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10192 |\n", + "| fps | 179 |\n", + "| time_elapsed | 625 |\n", + "| total_timesteps | 112464 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10196 |\n", + "| fps | 179 |\n", + "| time_elapsed | 625 |\n", + "| total_timesteps | 112518 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 2605 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10200 |\n", + "| fps | 179 |\n", + "| time_elapsed | 626 |\n", + "| total_timesteps | 112596 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 2608 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10204 |\n", + "| fps | 179 |\n", + "| time_elapsed | 626 |\n", + "| total_timesteps | 112650 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.36 |\n", + "| n_updates | 2610 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10208 |\n", + "| fps | 179 |\n", + "| time_elapsed | 627 |\n", + "| total_timesteps | 112674 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.76 |\n", + "| n_updates | 2611 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10212 |\n", + "| fps | 179 |\n", + "| time_elapsed | 627 |\n", + "| total_timesteps | 112704 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.43 |\n", + "| n_updates | 2612 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10216 |\n", + "| fps | 179 |\n", + "| time_elapsed | 627 |\n", + "| total_timesteps | 112740 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.4 |\n", + "| n_updates | 2614 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10220 |\n", + "| fps | 179 |\n", + "| time_elapsed | 628 |\n", + "| total_timesteps | 112806 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.44 |\n", + "| n_updates | 2617 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10224 |\n", + "| fps | 179 |\n", + "| time_elapsed | 628 |\n", + "| total_timesteps | 112848 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.77 |\n", + "| n_updates | 2618 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10228 |\n", + "| fps | 179 |\n", + "| time_elapsed | 628 |\n", + "| total_timesteps | 112872 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.62 |\n", + "| n_updates | 2619 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10232 |\n", + "| fps | 179 |\n", + "| time_elapsed | 628 |\n", + "| total_timesteps | 112884 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.86 |\n", + "| n_updates | 2620 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10236 |\n", + "| fps | 179 |\n", + "| time_elapsed | 628 |\n", + "| total_timesteps | 112908 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 2621 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10240 |\n", + "| fps | 179 |\n", + "| time_elapsed | 629 |\n", + "| total_timesteps | 112938 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.52 |\n", + "| n_updates | 2622 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10244 |\n", + "| fps | 179 |\n", + "| time_elapsed | 629 |\n", + "| total_timesteps | 112980 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.59 |\n", + "| n_updates | 2624 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10248 |\n", + "| fps | 179 |\n", + "| time_elapsed | 629 |\n", + "| total_timesteps | 113010 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.41 |\n", + "| n_updates | 2625 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10252 |\n", + "| fps | 179 |\n", + "| time_elapsed | 630 |\n", + "| total_timesteps | 113046 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6 |\n", + "| n_updates | 2627 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10256 |\n", + "| fps | 179 |\n", + "| time_elapsed | 630 |\n", + "| total_timesteps | 113088 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.51 |\n", + "| n_updates | 2628 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10260 |\n", + "| fps | 179 |\n", + "| time_elapsed | 630 |\n", + "| total_timesteps | 113124 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.03 |\n", + "| n_updates | 2630 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10264 |\n", + "| fps | 179 |\n", + "| time_elapsed | 631 |\n", + "| total_timesteps | 113166 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.34 |\n", + "| n_updates | 2632 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10268 |\n", + "| fps | 179 |\n", + "| time_elapsed | 631 |\n", + "| total_timesteps | 113190 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 2633 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10272 |\n", + "| fps | 179 |\n", + "| time_elapsed | 631 |\n", + "| total_timesteps | 113232 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.56 |\n", + "| n_updates | 2634 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10276 |\n", + "| fps | 179 |\n", + "| time_elapsed | 632 |\n", + "| total_timesteps | 113262 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.87 |\n", + "| n_updates | 2636 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10280 |\n", + "| fps | 179 |\n", + "| time_elapsed | 632 |\n", + "| total_timesteps | 113292 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.42 |\n", + "| n_updates | 2637 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10284 |\n", + "| fps | 179 |\n", + "| time_elapsed | 632 |\n", + "| total_timesteps | 113346 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 2639 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10288 |\n", + "| fps | 179 |\n", + "| time_elapsed | 633 |\n", + "| total_timesteps | 113430 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.38 |\n", + "| n_updates | 2643 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10292 |\n", + "| fps | 179 |\n", + "| time_elapsed | 633 |\n", + "| total_timesteps | 113478 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 2645 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10296 |\n", + "| fps | 179 |\n", + "| time_elapsed | 634 |\n", + "| total_timesteps | 113514 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.75 |\n", + "| n_updates | 2646 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10300 |\n", + "| fps | 178 |\n", + "| time_elapsed | 634 |\n", + "| total_timesteps | 113592 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.6 |\n", + "| n_updates | 2649 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10304 |\n", + "| fps | 178 |\n", + "| time_elapsed | 635 |\n", + "| total_timesteps | 113634 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.5 |\n", + "| n_updates | 2651 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10308 |\n", + "| fps | 178 |\n", + "| time_elapsed | 635 |\n", + "| total_timesteps | 113652 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.8 |\n", + "| n_updates | 2652 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10312 |\n", + "| fps | 178 |\n", + "| time_elapsed | 635 |\n", + "| total_timesteps | 113688 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.52 |\n", + "| n_updates | 2653 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10316 |\n", + "| fps | 178 |\n", + "| time_elapsed | 635 |\n", + "| total_timesteps | 113712 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.4 |\n", + "| n_updates | 2654 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10320 |\n", + "| fps | 178 |\n", + "| time_elapsed | 636 |\n", + "| total_timesteps | 113742 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.62 |\n", + "| n_updates | 2656 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10324 |\n", + "| fps | 178 |\n", + "| time_elapsed | 636 |\n", + "| total_timesteps | 113784 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 2657 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10328 |\n", + "| fps | 178 |\n", + "| time_elapsed | 637 |\n", + "| total_timesteps | 113874 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.71 |\n", + "| n_updates | 2661 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10332 |\n", + "| fps | 178 |\n", + "| time_elapsed | 637 |\n", + "| total_timesteps | 113946 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 2664 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10336 |\n", + "| fps | 178 |\n", + "| time_elapsed | 637 |\n", + "| total_timesteps | 113982 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.01 |\n", + "| n_updates | 2666 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10340 |\n", + "| fps | 178 |\n", + "| time_elapsed | 638 |\n", + "| total_timesteps | 114018 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.25 |\n", + "| n_updates | 2667 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10344 |\n", + "| fps | 178 |\n", + "| time_elapsed | 638 |\n", + "| total_timesteps | 114078 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.48 |\n", + "| n_updates | 2670 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10348 |\n", + "| fps | 178 |\n", + "| time_elapsed | 638 |\n", + "| total_timesteps | 114120 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.52 |\n", + "| n_updates | 2671 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10352 |\n", + "| fps | 178 |\n", + "| time_elapsed | 639 |\n", + "| total_timesteps | 114186 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.43 |\n", + "| n_updates | 2674 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10356 |\n", + "| fps | 178 |\n", + "| time_elapsed | 639 |\n", + "| total_timesteps | 114228 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 2676 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10360 |\n", + "| fps | 178 |\n", + "| time_elapsed | 640 |\n", + "| total_timesteps | 114282 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.93 |\n", + "| n_updates | 2678 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10364 |\n", + "| fps | 178 |\n", + "| time_elapsed | 640 |\n", + "| total_timesteps | 114342 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.8 |\n", + "| n_updates | 2681 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10368 |\n", + "| fps | 178 |\n", + "| time_elapsed | 641 |\n", + "| total_timesteps | 114414 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.24 |\n", + "| n_updates | 2684 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10372 |\n", + "| fps | 178 |\n", + "| time_elapsed | 641 |\n", + "| total_timesteps | 114480 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.47 |\n", + "| n_updates | 2686 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10376 |\n", + "| fps | 178 |\n", + "| time_elapsed | 642 |\n", + "| total_timesteps | 114528 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.62 |\n", + "| n_updates | 2688 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10380 |\n", + "| fps | 178 |\n", + "| time_elapsed | 642 |\n", + "| total_timesteps | 114594 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.54 |\n", + "| n_updates | 2691 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10384 |\n", + "| fps | 178 |\n", + "| time_elapsed | 643 |\n", + "| total_timesteps | 114654 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.71 |\n", + "| n_updates | 2694 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10388 |\n", + "| fps | 178 |\n", + "| time_elapsed | 643 |\n", + "| total_timesteps | 114690 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.25 |\n", + "| n_updates | 2695 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10392 |\n", + "| fps | 178 |\n", + "| time_elapsed | 643 |\n", + "| total_timesteps | 114726 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 2697 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10396 |\n", + "| fps | 178 |\n", + "| time_elapsed | 644 |\n", + "| total_timesteps | 114762 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 2698 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10400 |\n", + "| fps | 178 |\n", + "| time_elapsed | 644 |\n", + "| total_timesteps | 114834 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.96 |\n", + "| n_updates | 2701 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10404 |\n", + "| fps | 178 |\n", + "| time_elapsed | 645 |\n", + "| total_timesteps | 114900 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.45 |\n", + "| n_updates | 2704 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10408 |\n", + "| fps | 178 |\n", + "| time_elapsed | 645 |\n", + "| total_timesteps | 114960 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 2706 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10412 |\n", + "| fps | 178 |\n", + "| time_elapsed | 646 |\n", + "| total_timesteps | 115026 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.63 |\n", + "| n_updates | 2709 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10416 |\n", + "| fps | 177 |\n", + "| time_elapsed | 646 |\n", + "| total_timesteps | 115104 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.77 |\n", + "| n_updates | 2712 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10420 |\n", + "| fps | 177 |\n", + "| time_elapsed | 647 |\n", + "| total_timesteps | 115164 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.66 |\n", + "| n_updates | 2715 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10424 |\n", + "| fps | 177 |\n", + "| time_elapsed | 647 |\n", + "| total_timesteps | 115194 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.08 |\n", + "| n_updates | 2716 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10428 |\n", + "| fps | 177 |\n", + "| time_elapsed | 647 |\n", + "| total_timesteps | 115236 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.52 |\n", + "| n_updates | 2718 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10432 |\n", + "| fps | 177 |\n", + "| time_elapsed | 648 |\n", + "| total_timesteps | 115272 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 2719 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10436 |\n", + "| fps | 177 |\n", + "| time_elapsed | 648 |\n", + "| total_timesteps | 115350 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.39 |\n", + "| n_updates | 2723 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10440 |\n", + "| fps | 177 |\n", + "| time_elapsed | 649 |\n", + "| total_timesteps | 115404 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.52 |\n", + "| n_updates | 2725 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10444 |\n", + "| fps | 177 |\n", + "| time_elapsed | 649 |\n", + "| total_timesteps | 115446 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.46 |\n", + "| n_updates | 2727 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10448 |\n", + "| fps | 177 |\n", + "| time_elapsed | 649 |\n", + "| total_timesteps | 115488 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.8 |\n", + "| n_updates | 2728 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10452 |\n", + "| fps | 177 |\n", + "| time_elapsed | 650 |\n", + "| total_timesteps | 115530 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 2730 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10456 |\n", + "| fps | 177 |\n", + "| time_elapsed | 650 |\n", + "| total_timesteps | 115566 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.42 |\n", + "| n_updates | 2732 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10460 |\n", + "| fps | 177 |\n", + "| time_elapsed | 650 |\n", + "| total_timesteps | 115602 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.45 |\n", + "| n_updates | 2733 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10464 |\n", + "| fps | 177 |\n", + "| time_elapsed | 651 |\n", + "| total_timesteps | 115638 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.75 |\n", + "| n_updates | 2735 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10468 |\n", + "| fps | 177 |\n", + "| time_elapsed | 651 |\n", + "| total_timesteps | 115674 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.37 |\n", + "| n_updates | 2736 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10472 |\n", + "| fps | 177 |\n", + "| time_elapsed | 652 |\n", + "| total_timesteps | 115734 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 2739 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10476 |\n", + "| fps | 177 |\n", + "| time_elapsed | 652 |\n", + "| total_timesteps | 115812 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 2742 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10480 |\n", + "| fps | 177 |\n", + "| time_elapsed | 652 |\n", + "| total_timesteps | 115854 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.24 |\n", + "| n_updates | 2744 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10484 |\n", + "| fps | 177 |\n", + "| time_elapsed | 653 |\n", + "| total_timesteps | 115878 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.58 |\n", + "| n_updates | 2745 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10488 |\n", + "| fps | 177 |\n", + "| time_elapsed | 653 |\n", + "| total_timesteps | 115914 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.5 |\n", + "| n_updates | 2746 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.18 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10492 |\n", + "| fps | 177 |\n", + "| time_elapsed | 653 |\n", + "| total_timesteps | 115944 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.9 |\n", + "| n_updates | 2747 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10496 |\n", + "| fps | 177 |\n", + "| time_elapsed | 653 |\n", + "| total_timesteps | 115980 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.5 |\n", + "| n_updates | 2749 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10500 |\n", + "| fps | 177 |\n", + "| time_elapsed | 654 |\n", + "| total_timesteps | 116076 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.92 |\n", + "| n_updates | 2753 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.19 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10504 |\n", + "| fps | 177 |\n", + "| time_elapsed | 654 |\n", + "| total_timesteps | 116112 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.68 |\n", + "| n_updates | 2754 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10508 |\n", + "| fps | 177 |\n", + "| time_elapsed | 655 |\n", + "| total_timesteps | 116154 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.8 |\n", + "| n_updates | 2756 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10512 |\n", + "| fps | 177 |\n", + "| time_elapsed | 655 |\n", + "| total_timesteps | 116190 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.5 |\n", + "| n_updates | 2758 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10516 |\n", + "| fps | 177 |\n", + "| time_elapsed | 655 |\n", + "| total_timesteps | 116226 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.12 |\n", + "| n_updates | 2759 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.22 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10520 |\n", + "| fps | 177 |\n", + "| time_elapsed | 656 |\n", + "| total_timesteps | 116244 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.04 |\n", + "| n_updates | 2760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10524 |\n", + "| fps | 177 |\n", + "| time_elapsed | 656 |\n", + "| total_timesteps | 116316 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 2763 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10528 |\n", + "| fps | 177 |\n", + "| time_elapsed | 657 |\n", + "| total_timesteps | 116364 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.96 |\n", + "| n_updates | 2765 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10532 |\n", + "| fps | 177 |\n", + "| time_elapsed | 657 |\n", + "| total_timesteps | 116412 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.76 |\n", + "| n_updates | 2767 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10536 |\n", + "| fps | 177 |\n", + "| time_elapsed | 657 |\n", + "| total_timesteps | 116448 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 0.928 |\n", + "| n_updates | 2768 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10540 |\n", + "| fps | 177 |\n", + "| time_elapsed | 658 |\n", + "| total_timesteps | 116502 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.66 |\n", + "| n_updates | 2771 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10544 |\n", + "| fps | 176 |\n", + "| time_elapsed | 658 |\n", + "| total_timesteps | 116574 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.55 |\n", + "| n_updates | 2774 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10548 |\n", + "| fps | 176 |\n", + "| time_elapsed | 659 |\n", + "| total_timesteps | 116652 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.26 |\n", + "| n_updates | 2777 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10552 |\n", + "| fps | 176 |\n", + "| time_elapsed | 659 |\n", + "| total_timesteps | 116724 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.69 |\n", + "| n_updates | 2780 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10556 |\n", + "| fps | 176 |\n", + "| time_elapsed | 660 |\n", + "| total_timesteps | 116760 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.3 |\n", + "| n_updates | 2781 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10560 |\n", + "| fps | 176 |\n", + "| time_elapsed | 660 |\n", + "| total_timesteps | 116796 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.51 |\n", + "| n_updates | 2783 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10564 |\n", + "| fps | 176 |\n", + "| time_elapsed | 660 |\n", + "| total_timesteps | 116832 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.68 |\n", + "| n_updates | 2784 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10568 |\n", + "| fps | 176 |\n", + "| time_elapsed | 661 |\n", + "| total_timesteps | 116874 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.17 |\n", + "| n_updates | 2786 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10572 |\n", + "| fps | 176 |\n", + "| time_elapsed | 661 |\n", + "| total_timesteps | 116892 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.89 |\n", + "| n_updates | 2787 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10576 |\n", + "| fps | 176 |\n", + "| time_elapsed | 661 |\n", + "| total_timesteps | 116922 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 2788 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10580 |\n", + "| fps | 176 |\n", + "| time_elapsed | 662 |\n", + "| total_timesteps | 117006 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.27 |\n", + "| n_updates | 2792 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10584 |\n", + "| fps | 176 |\n", + "| time_elapsed | 662 |\n", + "| total_timesteps | 117090 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 2795 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10588 |\n", + "| fps | 176 |\n", + "| time_elapsed | 663 |\n", + "| total_timesteps | 117126 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.89 |\n", + "| n_updates | 2797 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10592 |\n", + "| fps | 176 |\n", + "| time_elapsed | 663 |\n", + "| total_timesteps | 117168 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.76 |\n", + "| n_updates | 2798 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10596 |\n", + "| fps | 176 |\n", + "| time_elapsed | 663 |\n", + "| total_timesteps | 117216 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 2800 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10600 |\n", + "| fps | 176 |\n", + "| time_elapsed | 664 |\n", + "| total_timesteps | 117252 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.63 |\n", + "| n_updates | 2802 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10604 |\n", + "| fps | 176 |\n", + "| time_elapsed | 664 |\n", + "| total_timesteps | 117270 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.66 |\n", + "| n_updates | 2803 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10608 |\n", + "| fps | 176 |\n", + "| time_elapsed | 664 |\n", + "| total_timesteps | 117336 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.55 |\n", + "| n_updates | 2805 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10612 |\n", + "| fps | 176 |\n", + "| time_elapsed | 665 |\n", + "| total_timesteps | 117372 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 2807 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10616 |\n", + "| fps | 176 |\n", + "| time_elapsed | 665 |\n", + "| total_timesteps | 117450 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.88 |\n", + "| n_updates | 2810 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10620 |\n", + "| fps | 176 |\n", + "| time_elapsed | 666 |\n", + "| total_timesteps | 117504 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.07 |\n", + "| n_updates | 2812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10624 |\n", + "| fps | 176 |\n", + "| time_elapsed | 666 |\n", + "| total_timesteps | 117540 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 2814 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10628 |\n", + "| fps | 176 |\n", + "| time_elapsed | 666 |\n", + "| total_timesteps | 117564 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.72 |\n", + "| n_updates | 2815 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10632 |\n", + "| fps | 176 |\n", + "| time_elapsed | 666 |\n", + "| total_timesteps | 117600 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.79 |\n", + "| n_updates | 2816 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10636 |\n", + "| fps | 176 |\n", + "| time_elapsed | 667 |\n", + "| total_timesteps | 117744 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.73 |\n", + "| n_updates | 2822 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10640 |\n", + "| fps | 176 |\n", + "| time_elapsed | 668 |\n", + "| total_timesteps | 117786 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.46 |\n", + "| n_updates | 2824 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10644 |\n", + "| fps | 176 |\n", + "| time_elapsed | 668 |\n", + "| total_timesteps | 117828 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 2826 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10648 |\n", + "| fps | 176 |\n", + "| time_elapsed | 668 |\n", + "| total_timesteps | 117864 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.7 |\n", + "| n_updates | 2827 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10652 |\n", + "| fps | 176 |\n", + "| time_elapsed | 669 |\n", + "| total_timesteps | 117900 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.71 |\n", + "| n_updates | 2829 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10656 |\n", + "| fps | 176 |\n", + "| time_elapsed | 669 |\n", + "| total_timesteps | 117942 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.59 |\n", + "| n_updates | 2831 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10660 |\n", + "| fps | 176 |\n", + "| time_elapsed | 670 |\n", + "| total_timesteps | 118008 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 2833 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10664 |\n", + "| fps | 176 |\n", + "| time_elapsed | 670 |\n", + "| total_timesteps | 118068 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.07 |\n", + "| n_updates | 2836 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10668 |\n", + "| fps | 176 |\n", + "| time_elapsed | 670 |\n", + "| total_timesteps | 118104 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.59 |\n", + "| n_updates | 2837 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10672 |\n", + "| fps | 175 |\n", + "| time_elapsed | 671 |\n", + "| total_timesteps | 118140 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.74 |\n", + "| n_updates | 2839 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10676 |\n", + "| fps | 175 |\n", + "| time_elapsed | 671 |\n", + "| total_timesteps | 118188 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.81 |\n", + "| n_updates | 2841 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10680 |\n", + "| fps | 175 |\n", + "| time_elapsed | 672 |\n", + "| total_timesteps | 118254 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.85 |\n", + "| n_updates | 2844 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10684 |\n", + "| fps | 175 |\n", + "| time_elapsed | 672 |\n", + "| total_timesteps | 118320 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 2846 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10688 |\n", + "| fps | 175 |\n", + "| time_elapsed | 673 |\n", + "| total_timesteps | 118374 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.09 |\n", + "| n_updates | 2849 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10692 |\n", + "| fps | 175 |\n", + "| time_elapsed | 673 |\n", + "| total_timesteps | 118410 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.55 |\n", + "| n_updates | 2850 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10696 |\n", + "| fps | 175 |\n", + "| time_elapsed | 673 |\n", + "| total_timesteps | 118440 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.61 |\n", + "| n_updates | 2851 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10700 |\n", + "| fps | 175 |\n", + "| time_elapsed | 674 |\n", + "| total_timesteps | 118488 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.84 |\n", + "| n_updates | 2853 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10704 |\n", + "| fps | 175 |\n", + "| time_elapsed | 674 |\n", + "| total_timesteps | 118548 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.14 |\n", + "| n_updates | 2856 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10708 |\n", + "| fps | 175 |\n", + "| time_elapsed | 675 |\n", + "| total_timesteps | 118620 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.55 |\n", + "| n_updates | 2859 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10712 |\n", + "| fps | 175 |\n", + "| time_elapsed | 675 |\n", + "| total_timesteps | 118674 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.33 |\n", + "| n_updates | 2861 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10716 |\n", + "| fps | 175 |\n", + "| time_elapsed | 675 |\n", + "| total_timesteps | 118728 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 2863 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10720 |\n", + "| fps | 175 |\n", + "| time_elapsed | 676 |\n", + "| total_timesteps | 118770 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.6 |\n", + "| n_updates | 2865 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10724 |\n", + "| fps | 175 |\n", + "| time_elapsed | 676 |\n", + "| total_timesteps | 118806 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 2867 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10728 |\n", + "| fps | 175 |\n", + "| time_elapsed | 676 |\n", + "| total_timesteps | 118824 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10732 |\n", + "| fps | 175 |\n", + "| time_elapsed | 676 |\n", + "| total_timesteps | 118848 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.44 |\n", + "| n_updates | 2868 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10736 |\n", + "| fps | 175 |\n", + "| time_elapsed | 677 |\n", + "| total_timesteps | 118884 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3 |\n", + "| n_updates | 2870 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10740 |\n", + "| fps | 175 |\n", + "| time_elapsed | 677 |\n", + "| total_timesteps | 118908 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.8 |\n", + "| n_updates | 2871 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10744 |\n", + "| fps | 175 |\n", + "| time_elapsed | 677 |\n", + "| total_timesteps | 118962 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.44 |\n", + "| n_updates | 2873 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10748 |\n", + "| fps | 175 |\n", + "| time_elapsed | 678 |\n", + "| total_timesteps | 118992 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.84 |\n", + "| n_updates | 2874 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10752 |\n", + "| fps | 175 |\n", + "| time_elapsed | 678 |\n", + "| total_timesteps | 119028 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.69 |\n", + "| n_updates | 2876 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10756 |\n", + "| fps | 175 |\n", + "| time_elapsed | 678 |\n", + "| total_timesteps | 119070 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.93 |\n", + "| n_updates | 2878 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10760 |\n", + "| fps | 175 |\n", + "| time_elapsed | 679 |\n", + "| total_timesteps | 119106 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.2 |\n", + "| n_updates | 2879 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10764 |\n", + "| fps | 175 |\n", + "| time_elapsed | 679 |\n", + "| total_timesteps | 119142 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.8 |\n", + "| n_updates | 2881 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10768 |\n", + "| fps | 175 |\n", + "| time_elapsed | 679 |\n", + "| total_timesteps | 119190 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.28 |\n", + "| n_updates | 2883 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10772 |\n", + "| fps | 175 |\n", + "| time_elapsed | 680 |\n", + "| total_timesteps | 119232 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.99 |\n", + "| n_updates | 2884 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10776 |\n", + "| fps | 175 |\n", + "| time_elapsed | 680 |\n", + "| total_timesteps | 119274 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.07 |\n", + "| n_updates | 2886 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10780 |\n", + "| fps | 175 |\n", + "| time_elapsed | 680 |\n", + "| total_timesteps | 119316 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 2888 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 311 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10784 |\n", + "| fps | 175 |\n", + "| time_elapsed | 681 |\n", + "| total_timesteps | 119376 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.6 |\n", + "| n_updates | 2890 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 311 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10788 |\n", + "| fps | 175 |\n", + "| time_elapsed | 681 |\n", + "| total_timesteps | 119412 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.75 |\n", + "| n_updates | 2892 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10792 |\n", + "| fps | 175 |\n", + "| time_elapsed | 681 |\n", + "| total_timesteps | 119424 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10796 |\n", + "| fps | 175 |\n", + "| time_elapsed | 682 |\n", + "| total_timesteps | 119466 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.32 |\n", + "| n_updates | 2894 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10800 |\n", + "| fps | 175 |\n", + "| time_elapsed | 682 |\n", + "| total_timesteps | 119508 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.26 |\n", + "| n_updates | 2896 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10804 |\n", + "| fps | 175 |\n", + "| time_elapsed | 682 |\n", + "| total_timesteps | 119544 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 2897 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10808 |\n", + "| fps | 175 |\n", + "| time_elapsed | 683 |\n", + "| total_timesteps | 119592 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.73 |\n", + "| n_updates | 2899 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 310 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10812 |\n", + "| fps | 175 |\n", + "| time_elapsed | 683 |\n", + "| total_timesteps | 119622 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.5 |\n", + "| n_updates | 2901 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10816 |\n", + "| fps | 174 |\n", + "| time_elapsed | 683 |\n", + "| total_timesteps | 119646 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.89 |\n", + "| n_updates | 2902 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10820 |\n", + "| fps | 174 |\n", + "| time_elapsed | 683 |\n", + "| total_timesteps | 119676 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.76 |\n", + "| n_updates | 2903 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10824 |\n", + "| fps | 174 |\n", + "| time_elapsed | 684 |\n", + "| total_timesteps | 119694 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.55 |\n", + "| n_updates | 2904 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 309 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10828 |\n", + "| fps | 174 |\n", + "| time_elapsed | 684 |\n", + "| total_timesteps | 119736 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.38 |\n", + "| n_updates | 2905 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10832 |\n", + "| fps | 174 |\n", + "| time_elapsed | 684 |\n", + "| total_timesteps | 119808 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 2908 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10836 |\n", + "| fps | 174 |\n", + "| time_elapsed | 685 |\n", + "| total_timesteps | 119886 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.48 |\n", + "| n_updates | 2912 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10840 |\n", + "| fps | 174 |\n", + "| time_elapsed | 686 |\n", + "| total_timesteps | 119946 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.43 |\n", + "| n_updates | 2914 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10844 |\n", + "| fps | 174 |\n", + "| time_elapsed | 686 |\n", + "| total_timesteps | 120036 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.52 |\n", + "| n_updates | 2918 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 308 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10848 |\n", + "| fps | 174 |\n", + "| time_elapsed | 687 |\n", + "| total_timesteps | 120078 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.72 |\n", + "| n_updates | 2920 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10852 |\n", + "| fps | 174 |\n", + "| time_elapsed | 687 |\n", + "| total_timesteps | 120120 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.07 |\n", + "| n_updates | 2921 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10856 |\n", + "| fps | 174 |\n", + "| time_elapsed | 687 |\n", + "| total_timesteps | 120156 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.77 |\n", + "| n_updates | 2923 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10860 |\n", + "| fps | 174 |\n", + "| time_elapsed | 688 |\n", + "| total_timesteps | 120192 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.11 |\n", + "| n_updates | 2924 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 307 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10864 |\n", + "| fps | 174 |\n", + "| time_elapsed | 688 |\n", + "| total_timesteps | 120216 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.4 |\n", + "| n_updates | 2925 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10868 |\n", + "| fps | 174 |\n", + "| time_elapsed | 688 |\n", + "| total_timesteps | 120276 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.71 |\n", + "| n_updates | 2928 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10872 |\n", + "| fps | 174 |\n", + "| time_elapsed | 689 |\n", + "| total_timesteps | 120294 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.75 |\n", + "| n_updates | 2929 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10876 |\n", + "| fps | 174 |\n", + "| time_elapsed | 689 |\n", + "| total_timesteps | 120324 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.79 |\n", + "| n_updates | 2930 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10880 |\n", + "| fps | 174 |\n", + "| time_elapsed | 689 |\n", + "| total_timesteps | 120354 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.75 |\n", + "| n_updates | 2931 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10884 |\n", + "| fps | 174 |\n", + "| time_elapsed | 689 |\n", + "| total_timesteps | 120384 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.15 |\n", + "| n_updates | 2932 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10888 |\n", + "| fps | 174 |\n", + "| time_elapsed | 690 |\n", + "| total_timesteps | 120420 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.11 |\n", + "| n_updates | 2934 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10892 |\n", + "| fps | 174 |\n", + "| time_elapsed | 690 |\n", + "| total_timesteps | 120444 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.32 |\n", + "| n_updates | 2935 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10896 |\n", + "| fps | 174 |\n", + "| time_elapsed | 690 |\n", + "| total_timesteps | 120480 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.24 |\n", + "| n_updates | 2936 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10900 |\n", + "| fps | 174 |\n", + "| time_elapsed | 691 |\n", + "| total_timesteps | 120522 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.33 |\n", + "| n_updates | 2938 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10904 |\n", + "| fps | 174 |\n", + "| time_elapsed | 691 |\n", + "| total_timesteps | 120564 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.02 |\n", + "| n_updates | 2940 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10908 |\n", + "| fps | 174 |\n", + "| time_elapsed | 691 |\n", + "| total_timesteps | 120588 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.86 |\n", + "| n_updates | 2941 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10912 |\n", + "| fps | 174 |\n", + "| time_elapsed | 692 |\n", + "| total_timesteps | 120654 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.58 |\n", + "| n_updates | 2944 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10916 |\n", + "| fps | 174 |\n", + "| time_elapsed | 692 |\n", + "| total_timesteps | 120684 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.86 |\n", + "| n_updates | 2945 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10920 |\n", + "| fps | 174 |\n", + "| time_elapsed | 693 |\n", + "| total_timesteps | 120750 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.9 |\n", + "| n_updates | 2948 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10924 |\n", + "| fps | 174 |\n", + "| time_elapsed | 693 |\n", + "| total_timesteps | 120786 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 2949 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10928 |\n", + "| fps | 174 |\n", + "| time_elapsed | 693 |\n", + "| total_timesteps | 120804 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.75 |\n", + "| n_updates | 2950 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10932 |\n", + "| fps | 174 |\n", + "| time_elapsed | 694 |\n", + "| total_timesteps | 120876 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.06 |\n", + "| n_updates | 2953 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10936 |\n", + "| fps | 174 |\n", + "| time_elapsed | 694 |\n", + "| total_timesteps | 120912 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.91 |\n", + "| n_updates | 2954 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10940 |\n", + "| fps | 174 |\n", + "| time_elapsed | 694 |\n", + "| total_timesteps | 120942 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.79 |\n", + "| n_updates | 2956 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10944 |\n", + "| fps | 174 |\n", + "| time_elapsed | 694 |\n", + "| total_timesteps | 120978 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 2957 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10948 |\n", + "| fps | 174 |\n", + "| time_elapsed | 695 |\n", + "| total_timesteps | 121014 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 2959 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10952 |\n", + "| fps | 174 |\n", + "| time_elapsed | 695 |\n", + "| total_timesteps | 121044 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.84 |\n", + "| n_updates | 2960 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10956 |\n", + "| fps | 174 |\n", + "| time_elapsed | 695 |\n", + "| total_timesteps | 121062 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.9 |\n", + "| n_updates | 2961 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10960 |\n", + "| fps | 173 |\n", + "| time_elapsed | 696 |\n", + "| total_timesteps | 121194 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.89 |\n", + "| n_updates | 2966 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10964 |\n", + "| fps | 173 |\n", + "| time_elapsed | 697 |\n", + "| total_timesteps | 121248 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.69 |\n", + "| n_updates | 2968 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10968 |\n", + "| fps | 173 |\n", + "| time_elapsed | 697 |\n", + "| total_timesteps | 121272 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.49 |\n", + "| n_updates | 2969 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10972 |\n", + "| fps | 173 |\n", + "| time_elapsed | 697 |\n", + "| total_timesteps | 121284 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 2970 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10976 |\n", + "| fps | 173 |\n", + "| time_elapsed | 697 |\n", + "| total_timesteps | 121308 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 2971 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10980 |\n", + "| fps | 173 |\n", + "| time_elapsed | 698 |\n", + "| total_timesteps | 121380 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.02 |\n", + "| n_updates | 2974 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10984 |\n", + "| fps | 173 |\n", + "| time_elapsed | 698 |\n", + "| total_timesteps | 121428 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.86 |\n", + "| n_updates | 2976 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10988 |\n", + "| fps | 173 |\n", + "| time_elapsed | 699 |\n", + "| total_timesteps | 121470 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.31 |\n", + "| n_updates | 2978 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10992 |\n", + "| fps | 173 |\n", + "| time_elapsed | 699 |\n", + "| total_timesteps | 121506 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 2979 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 10996 |\n", + "| fps | 173 |\n", + "| time_elapsed | 699 |\n", + "| total_timesteps | 121536 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.77 |\n", + "| n_updates | 2980 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11000 |\n", + "| fps | 173 |\n", + "| time_elapsed | 699 |\n", + "| total_timesteps | 121572 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.52 |\n", + "| n_updates | 2982 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11004 |\n", + "| fps | 173 |\n", + "| time_elapsed | 700 |\n", + "| total_timesteps | 121596 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.91 |\n", + "| n_updates | 2983 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11008 |\n", + "| fps | 173 |\n", + "| time_elapsed | 700 |\n", + "| total_timesteps | 121650 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.05 |\n", + "| n_updates | 2985 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11012 |\n", + "| fps | 173 |\n", + "| time_elapsed | 700 |\n", + "| total_timesteps | 121692 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.18 |\n", + "| n_updates | 2987 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11016 |\n", + "| fps | 173 |\n", + "| time_elapsed | 701 |\n", + "| total_timesteps | 121734 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.9 |\n", + "| n_updates | 2989 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11020 |\n", + "| fps | 173 |\n", + "| time_elapsed | 701 |\n", + "| total_timesteps | 121776 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.87 |\n", + "| n_updates | 2990 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11024 |\n", + "| fps | 173 |\n", + "| time_elapsed | 701 |\n", + "| total_timesteps | 121818 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.09 |\n", + "| n_updates | 2992 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11028 |\n", + "| fps | 173 |\n", + "| time_elapsed | 702 |\n", + "| total_timesteps | 121860 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.88 |\n", + "| n_updates | 2994 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11032 |\n", + "| fps | 173 |\n", + "| time_elapsed | 702 |\n", + "| total_timesteps | 121932 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.69 |\n", + "| n_updates | 2997 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11036 |\n", + "| fps | 173 |\n", + "| time_elapsed | 703 |\n", + "| total_timesteps | 121992 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.16 |\n", + "| n_updates | 2999 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11040 |\n", + "| fps | 173 |\n", + "| time_elapsed | 703 |\n", + "| total_timesteps | 122028 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.19 |\n", + "| n_updates | 3001 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11044 |\n", + "| fps | 173 |\n", + "| time_elapsed | 703 |\n", + "| total_timesteps | 122046 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 3002 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11048 |\n", + "| fps | 173 |\n", + "| time_elapsed | 704 |\n", + "| total_timesteps | 122112 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.83 |\n", + "| n_updates | 3004 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11052 |\n", + "| fps | 173 |\n", + "| time_elapsed | 704 |\n", + "| total_timesteps | 122154 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.11 |\n", + "| n_updates | 3006 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11056 |\n", + "| fps | 173 |\n", + "| time_elapsed | 705 |\n", + "| total_timesteps | 122202 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.99 |\n", + "| n_updates | 3008 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11060 |\n", + "| fps | 173 |\n", + "| time_elapsed | 705 |\n", + "| total_timesteps | 122238 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.86 |\n", + "| n_updates | 3010 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11064 |\n", + "| fps | 173 |\n", + "| time_elapsed | 705 |\n", + "| total_timesteps | 122292 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.06 |\n", + "| n_updates | 3012 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11068 |\n", + "| fps | 173 |\n", + "| time_elapsed | 706 |\n", + "| total_timesteps | 122340 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.02 |\n", + "| n_updates | 3014 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11072 |\n", + "| fps | 173 |\n", + "| time_elapsed | 706 |\n", + "| total_timesteps | 122394 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.89 |\n", + "| n_updates | 3016 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11076 |\n", + "| fps | 173 |\n", + "| time_elapsed | 707 |\n", + "| total_timesteps | 122454 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.94 |\n", + "| n_updates | 3019 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11080 |\n", + "| fps | 173 |\n", + "| time_elapsed | 707 |\n", + "| total_timesteps | 122508 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.94 |\n", + "| n_updates | 3021 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11084 |\n", + "| fps | 173 |\n", + "| time_elapsed | 707 |\n", + "| total_timesteps | 122568 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.73 |\n", + "| n_updates | 3023 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11088 |\n", + "| fps | 173 |\n", + "| time_elapsed | 708 |\n", + "| total_timesteps | 122628 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.76 |\n", + "| n_updates | 3026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11092 |\n", + "| fps | 173 |\n", + "| time_elapsed | 708 |\n", + "| total_timesteps | 122682 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.46 |\n", + "| n_updates | 3028 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11096 |\n", + "| fps | 173 |\n", + "| time_elapsed | 709 |\n", + "| total_timesteps | 122718 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.27 |\n", + "| n_updates | 3030 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11100 |\n", + "| fps | 173 |\n", + "| time_elapsed | 709 |\n", + "| total_timesteps | 122766 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.3 |\n", + "| n_updates | 3032 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11104 |\n", + "| fps | 173 |\n", + "| time_elapsed | 709 |\n", + "| total_timesteps | 122832 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.96 |\n", + "| n_updates | 3034 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11108 |\n", + "| fps | 172 |\n", + "| time_elapsed | 710 |\n", + "| total_timesteps | 122874 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.2 |\n", + "| n_updates | 3036 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11112 |\n", + "| fps | 172 |\n", + "| time_elapsed | 710 |\n", + "| total_timesteps | 122916 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.11 |\n", + "| n_updates | 3038 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11116 |\n", + "| fps | 172 |\n", + "| time_elapsed | 711 |\n", + "| total_timesteps | 122994 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.87 |\n", + "| n_updates | 3041 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11120 |\n", + "| fps | 172 |\n", + "| time_elapsed | 711 |\n", + "| total_timesteps | 123048 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.72 |\n", + "| n_updates | 3043 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11124 |\n", + "| fps | 172 |\n", + "| time_elapsed | 712 |\n", + "| total_timesteps | 123096 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 3045 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11128 |\n", + "| fps | 172 |\n", + "| time_elapsed | 712 |\n", + "| total_timesteps | 123186 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.08 |\n", + "| n_updates | 3049 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11132 |\n", + "| fps | 172 |\n", + "| time_elapsed | 713 |\n", + "| total_timesteps | 123228 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.33 |\n", + "| n_updates | 3051 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11136 |\n", + "| fps | 172 |\n", + "| time_elapsed | 713 |\n", + "| total_timesteps | 123258 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.29 |\n", + "| n_updates | 3052 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11140 |\n", + "| fps | 172 |\n", + "| time_elapsed | 713 |\n", + "| total_timesteps | 123282 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.15 |\n", + "| n_updates | 3053 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11144 |\n", + "| fps | 172 |\n", + "| time_elapsed | 713 |\n", + "| total_timesteps | 123306 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 3054 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11148 |\n", + "| fps | 172 |\n", + "| time_elapsed | 714 |\n", + "| total_timesteps | 123348 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.83 |\n", + "| n_updates | 3056 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11152 |\n", + "| fps | 172 |\n", + "| time_elapsed | 714 |\n", + "| total_timesteps | 123372 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.67 |\n", + "| n_updates | 3057 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11156 |\n", + "| fps | 172 |\n", + "| time_elapsed | 715 |\n", + "| total_timesteps | 123438 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.11 |\n", + "| n_updates | 3060 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11160 |\n", + "| fps | 172 |\n", + "| time_elapsed | 715 |\n", + "| total_timesteps | 123486 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.77 |\n", + "| n_updates | 3062 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11164 |\n", + "| fps | 172 |\n", + "| time_elapsed | 715 |\n", + "| total_timesteps | 123528 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.87 |\n", + "| n_updates | 3063 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11168 |\n", + "| fps | 172 |\n", + "| time_elapsed | 716 |\n", + "| total_timesteps | 123564 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.57 |\n", + "| n_updates | 3065 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11172 |\n", + "| fps | 172 |\n", + "| time_elapsed | 716 |\n", + "| total_timesteps | 123624 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.08 |\n", + "| n_updates | 3067 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11176 |\n", + "| fps | 172 |\n", + "| time_elapsed | 717 |\n", + "| total_timesteps | 123684 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.88 |\n", + "| n_updates | 3070 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11180 |\n", + "| fps | 172 |\n", + "| time_elapsed | 717 |\n", + "| total_timesteps | 123732 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.08 |\n", + "| n_updates | 3072 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11184 |\n", + "| fps | 172 |\n", + "| time_elapsed | 717 |\n", + "| total_timesteps | 123762 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.76 |\n", + "| n_updates | 3073 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11188 |\n", + "| fps | 172 |\n", + "| time_elapsed | 718 |\n", + "| total_timesteps | 123804 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 3075 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11192 |\n", + "| fps | 172 |\n", + "| time_elapsed | 718 |\n", + "| total_timesteps | 123864 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.78 |\n", + "| n_updates | 3077 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11196 |\n", + "| fps | 172 |\n", + "| time_elapsed | 718 |\n", + "| total_timesteps | 123912 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.26 |\n", + "| n_updates | 3079 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11200 |\n", + "| fps | 172 |\n", + "| time_elapsed | 719 |\n", + "| total_timesteps | 123990 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.94 |\n", + "| n_updates | 3083 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11204 |\n", + "| fps | 172 |\n", + "| time_elapsed | 719 |\n", + "| total_timesteps | 124050 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.81 |\n", + "| n_updates | 3085 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11208 |\n", + "| fps | 172 |\n", + "| time_elapsed | 720 |\n", + "| total_timesteps | 124092 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.19 |\n", + "| n_updates | 3087 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11212 |\n", + "| fps | 172 |\n", + "| time_elapsed | 720 |\n", + "| total_timesteps | 124128 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.88 |\n", + "| n_updates | 3088 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11216 |\n", + "| fps | 172 |\n", + "| time_elapsed | 720 |\n", + "| total_timesteps | 124170 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.25 |\n", + "| n_updates | 3090 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11220 |\n", + "| fps | 172 |\n", + "| time_elapsed | 721 |\n", + "| total_timesteps | 124194 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.04 |\n", + "| n_updates | 3091 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11224 |\n", + "| fps | 172 |\n", + "| time_elapsed | 721 |\n", + "| total_timesteps | 124230 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.79 |\n", + "| n_updates | 3093 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11228 |\n", + "| fps | 172 |\n", + "| time_elapsed | 721 |\n", + "| total_timesteps | 124260 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.99 |\n", + "| n_updates | 3094 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11232 |\n", + "| fps | 172 |\n", + "| time_elapsed | 722 |\n", + "| total_timesteps | 124302 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 3096 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11236 |\n", + "| fps | 172 |\n", + "| time_elapsed | 722 |\n", + "| total_timesteps | 124344 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.32 |\n", + "| n_updates | 3097 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11240 |\n", + "| fps | 172 |\n", + "| time_elapsed | 722 |\n", + "| total_timesteps | 124380 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.1 |\n", + "| n_updates | 3099 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11244 |\n", + "| fps | 172 |\n", + "| time_elapsed | 723 |\n", + "| total_timesteps | 124458 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.47 |\n", + "| n_updates | 3102 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11248 |\n", + "| fps | 172 |\n", + "| time_elapsed | 723 |\n", + "| total_timesteps | 124536 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.68 |\n", + "| n_updates | 3105 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11252 |\n", + "| fps | 172 |\n", + "| time_elapsed | 724 |\n", + "| total_timesteps | 124572 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.55 |\n", + "| n_updates | 3107 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11256 |\n", + "| fps | 172 |\n", + "| time_elapsed | 724 |\n", + "| total_timesteps | 124584 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11260 |\n", + "| fps | 171 |\n", + "| time_elapsed | 724 |\n", + "| total_timesteps | 124620 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.91 |\n", + "| n_updates | 3109 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11264 |\n", + "| fps | 171 |\n", + "| time_elapsed | 725 |\n", + "| total_timesteps | 124662 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.92 |\n", + "| n_updates | 3111 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11268 |\n", + "| fps | 171 |\n", + "| time_elapsed | 725 |\n", + "| total_timesteps | 124710 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.83 |\n", + "| n_updates | 3113 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11272 |\n", + "| fps | 171 |\n", + "| time_elapsed | 725 |\n", + "| total_timesteps | 124752 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.46 |\n", + "| n_updates | 3114 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11276 |\n", + "| fps | 171 |\n", + "| time_elapsed | 726 |\n", + "| total_timesteps | 124830 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.12 |\n", + "| n_updates | 3118 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11280 |\n", + "| fps | 171 |\n", + "| time_elapsed | 726 |\n", + "| total_timesteps | 124890 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.9 |\n", + "| n_updates | 3120 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11284 |\n", + "| fps | 171 |\n", + "| time_elapsed | 727 |\n", + "| total_timesteps | 124950 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.74 |\n", + "| n_updates | 3123 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11288 |\n", + "| fps | 171 |\n", + "| time_elapsed | 727 |\n", + "| total_timesteps | 124980 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.44 |\n", + "| n_updates | 3124 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11292 |\n", + "| fps | 171 |\n", + "| time_elapsed | 728 |\n", + "| total_timesteps | 125070 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.75 |\n", + "| n_updates | 3128 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11296 |\n", + "| fps | 171 |\n", + "| time_elapsed | 728 |\n", + "| total_timesteps | 125112 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 3129 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11300 |\n", + "| fps | 171 |\n", + "| time_elapsed | 728 |\n", + "| total_timesteps | 125160 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.08 |\n", + "| n_updates | 3131 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11304 |\n", + "| fps | 171 |\n", + "| time_elapsed | 729 |\n", + "| total_timesteps | 125196 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.36 |\n", + "| n_updates | 3133 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11308 |\n", + "| fps | 171 |\n", + "| time_elapsed | 729 |\n", + "| total_timesteps | 125226 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.58 |\n", + "| n_updates | 3134 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11312 |\n", + "| fps | 171 |\n", + "| time_elapsed | 729 |\n", + "| total_timesteps | 125262 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.87 |\n", + "| n_updates | 3136 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11316 |\n", + "| fps | 171 |\n", + "| time_elapsed | 730 |\n", + "| total_timesteps | 125292 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.84 |\n", + "| n_updates | 3137 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11320 |\n", + "| fps | 171 |\n", + "| time_elapsed | 730 |\n", + "| total_timesteps | 125328 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2 |\n", + "| n_updates | 3138 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11324 |\n", + "| fps | 171 |\n", + "| time_elapsed | 730 |\n", + "| total_timesteps | 125370 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 3140 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11328 |\n", + "| fps | 171 |\n", + "| time_elapsed | 731 |\n", + "| total_timesteps | 125412 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.69 |\n", + "| n_updates | 3142 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11332 |\n", + "| fps | 171 |\n", + "| time_elapsed | 731 |\n", + "| total_timesteps | 125466 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.88 |\n", + "| n_updates | 3144 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11336 |\n", + "| fps | 171 |\n", + "| time_elapsed | 731 |\n", + "| total_timesteps | 125508 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.62 |\n", + "| n_updates | 3146 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11340 |\n", + "| fps | 171 |\n", + "| time_elapsed | 732 |\n", + "| total_timesteps | 125562 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.97 |\n", + "| n_updates | 3148 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11344 |\n", + "| fps | 171 |\n", + "| time_elapsed | 732 |\n", + "| total_timesteps | 125622 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.99 |\n", + "| n_updates | 3151 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11348 |\n", + "| fps | 171 |\n", + "| time_elapsed | 733 |\n", + "| total_timesteps | 125658 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.79 |\n", + "| n_updates | 3152 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11352 |\n", + "| fps | 171 |\n", + "| time_elapsed | 733 |\n", + "| total_timesteps | 125700 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.01 |\n", + "| n_updates | 3154 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11356 |\n", + "| fps | 171 |\n", + "| time_elapsed | 733 |\n", + "| total_timesteps | 125730 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.19 |\n", + "| n_updates | 3155 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11360 |\n", + "| fps | 171 |\n", + "| time_elapsed | 733 |\n", + "| total_timesteps | 125760 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.81 |\n", + "| n_updates | 3156 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11364 |\n", + "| fps | 171 |\n", + "| time_elapsed | 734 |\n", + "| total_timesteps | 125796 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.92 |\n", + "| n_updates | 3158 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11368 |\n", + "| fps | 171 |\n", + "| time_elapsed | 735 |\n", + "| total_timesteps | 125910 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.59 |\n", + "| n_updates | 3163 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11372 |\n", + "| fps | 171 |\n", + "| time_elapsed | 735 |\n", + "| total_timesteps | 125964 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.97 |\n", + "| n_updates | 3165 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11376 |\n", + "| fps | 171 |\n", + "| time_elapsed | 736 |\n", + "| total_timesteps | 126042 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.29 |\n", + "| n_updates | 3168 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11380 |\n", + "| fps | 171 |\n", + "| time_elapsed | 736 |\n", + "| total_timesteps | 126072 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.99 |\n", + "| n_updates | 3169 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11384 |\n", + "| fps | 171 |\n", + "| time_elapsed | 736 |\n", + "| total_timesteps | 126096 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.24 |\n", + "| n_updates | 3170 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11388 |\n", + "| fps | 171 |\n", + "| time_elapsed | 736 |\n", + "| total_timesteps | 126132 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.01 |\n", + "| n_updates | 3172 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11392 |\n", + "| fps | 171 |\n", + "| time_elapsed | 737 |\n", + "| total_timesteps | 126180 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.64 |\n", + "| n_updates | 3174 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11396 |\n", + "| fps | 171 |\n", + "| time_elapsed | 738 |\n", + "| total_timesteps | 126288 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.39 |\n", + "| n_updates | 3178 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11400 |\n", + "| fps | 171 |\n", + "| time_elapsed | 738 |\n", + "| total_timesteps | 126324 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 3180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11404 |\n", + "| fps | 171 |\n", + "| time_elapsed | 738 |\n", + "| total_timesteps | 126342 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.63 |\n", + "| n_updates | 3181 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11408 |\n", + "| fps | 171 |\n", + "| time_elapsed | 738 |\n", + "| total_timesteps | 126360 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11412 |\n", + "| fps | 170 |\n", + "| time_elapsed | 739 |\n", + "| total_timesteps | 126396 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.88 |\n", + "| n_updates | 3183 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11416 |\n", + "| fps | 170 |\n", + "| time_elapsed | 739 |\n", + "| total_timesteps | 126480 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.74 |\n", + "| n_updates | 3186 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11420 |\n", + "| fps | 170 |\n", + "| time_elapsed | 740 |\n", + "| total_timesteps | 126522 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.72 |\n", + "| n_updates | 3188 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11424 |\n", + "| fps | 170 |\n", + "| time_elapsed | 740 |\n", + "| total_timesteps | 126564 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.15 |\n", + "| n_updates | 3190 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11428 |\n", + "| fps | 170 |\n", + "| time_elapsed | 740 |\n", + "| total_timesteps | 126606 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.96 |\n", + "| n_updates | 3192 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11432 |\n", + "| fps | 170 |\n", + "| time_elapsed | 741 |\n", + "| total_timesteps | 126648 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.17 |\n", + "| n_updates | 3193 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11436 |\n", + "| fps | 170 |\n", + "| time_elapsed | 741 |\n", + "| total_timesteps | 126690 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.14 |\n", + "| n_updates | 3195 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11440 |\n", + "| fps | 170 |\n", + "| time_elapsed | 741 |\n", + "| total_timesteps | 126720 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.41 |\n", + "| n_updates | 3196 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11444 |\n", + "| fps | 170 |\n", + "| time_elapsed | 741 |\n", + "| total_timesteps | 126738 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.61 |\n", + "| n_updates | 3197 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11448 |\n", + "| fps | 170 |\n", + "| time_elapsed | 742 |\n", + "| total_timesteps | 126882 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.78 |\n", + "| n_updates | 3203 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11452 |\n", + "| fps | 170 |\n", + "| time_elapsed | 743 |\n", + "| total_timesteps | 126912 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.21 |\n", + "| n_updates | 3204 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11456 |\n", + "| fps | 170 |\n", + "| time_elapsed | 743 |\n", + "| total_timesteps | 126936 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.14 |\n", + "| n_updates | 3205 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11460 |\n", + "| fps | 170 |\n", + "| time_elapsed | 743 |\n", + "| total_timesteps | 126954 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.04 |\n", + "| n_updates | 3206 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11464 |\n", + "| fps | 170 |\n", + "| time_elapsed | 743 |\n", + "| total_timesteps | 126978 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.06 |\n", + "| n_updates | 3207 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11468 |\n", + "| fps | 170 |\n", + "| time_elapsed | 744 |\n", + "| total_timesteps | 127050 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.41 |\n", + "| n_updates | 3210 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11472 |\n", + "| fps | 170 |\n", + "| time_elapsed | 745 |\n", + "| total_timesteps | 127140 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 3214 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11476 |\n", + "| fps | 170 |\n", + "| time_elapsed | 745 |\n", + "| total_timesteps | 127182 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.69 |\n", + "| n_updates | 3216 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11480 |\n", + "| fps | 170 |\n", + "| time_elapsed | 745 |\n", + "| total_timesteps | 127248 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.18 |\n", + "| n_updates | 3218 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11484 |\n", + "| fps | 170 |\n", + "| time_elapsed | 746 |\n", + "| total_timesteps | 127296 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.27 |\n", + "| n_updates | 3220 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11488 |\n", + "| fps | 170 |\n", + "| time_elapsed | 746 |\n", + "| total_timesteps | 127332 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.14 |\n", + "| n_updates | 3222 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11492 |\n", + "| fps | 170 |\n", + "| time_elapsed | 746 |\n", + "| total_timesteps | 127368 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.54 |\n", + "| n_updates | 3223 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11496 |\n", + "| fps | 170 |\n", + "| time_elapsed | 747 |\n", + "| total_timesteps | 127410 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.56 |\n", + "| n_updates | 3225 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11500 |\n", + "| fps | 170 |\n", + "| time_elapsed | 747 |\n", + "| total_timesteps | 127452 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.89 |\n", + "| n_updates | 3227 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11504 |\n", + "| fps | 170 |\n", + "| time_elapsed | 747 |\n", + "| total_timesteps | 127482 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.87 |\n", + "| n_updates | 3228 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11508 |\n", + "| fps | 170 |\n", + "| time_elapsed | 748 |\n", + "| total_timesteps | 127518 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.29 |\n", + "| n_updates | 3230 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 306 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11512 |\n", + "| fps | 170 |\n", + "| time_elapsed | 748 |\n", + "| total_timesteps | 127554 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.95 |\n", + "| n_updates | 3231 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11516 |\n", + "| fps | 170 |\n", + "| time_elapsed | 748 |\n", + "| total_timesteps | 127590 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 3233 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11520 |\n", + "| fps | 170 |\n", + "| time_elapsed | 749 |\n", + "| total_timesteps | 127632 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.77 |\n", + "| n_updates | 3234 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11524 |\n", + "| fps | 170 |\n", + "| time_elapsed | 749 |\n", + "| total_timesteps | 127674 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 3236 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11528 |\n", + "| fps | 170 |\n", + "| time_elapsed | 749 |\n", + "| total_timesteps | 127692 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.84 |\n", + "| n_updates | 3237 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11532 |\n", + "| fps | 170 |\n", + "| time_elapsed | 749 |\n", + "| total_timesteps | 127728 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.23 |\n", + "| n_updates | 3238 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11536 |\n", + "| fps | 170 |\n", + "| time_elapsed | 750 |\n", + "| total_timesteps | 127758 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 3240 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11540 |\n", + "| fps | 170 |\n", + "| time_elapsed | 750 |\n", + "| total_timesteps | 127824 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.11 |\n", + "| n_updates | 3242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11544 |\n", + "| fps | 170 |\n", + "| time_elapsed | 751 |\n", + "| total_timesteps | 127854 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 3244 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11548 |\n", + "| fps | 170 |\n", + "| time_elapsed | 751 |\n", + "| total_timesteps | 127878 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.02 |\n", + "| n_updates | 3245 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11552 |\n", + "| fps | 170 |\n", + "| time_elapsed | 751 |\n", + "| total_timesteps | 127920 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.87 |\n", + "| n_updates | 3246 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11556 |\n", + "| fps | 170 |\n", + "| time_elapsed | 751 |\n", + "| total_timesteps | 127950 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.08 |\n", + "| n_updates | 3248 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11560 |\n", + "| fps | 170 |\n", + "| time_elapsed | 752 |\n", + "| total_timesteps | 127986 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.25 |\n", + "| n_updates | 3249 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11564 |\n", + "| fps | 170 |\n", + "| time_elapsed | 752 |\n", + "| total_timesteps | 128076 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 3253 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11568 |\n", + "| fps | 170 |\n", + "| time_elapsed | 753 |\n", + "| total_timesteps | 128148 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.52 |\n", + "| n_updates | 3256 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11572 |\n", + "| fps | 170 |\n", + "| time_elapsed | 753 |\n", + "| total_timesteps | 128202 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.37 |\n", + "| n_updates | 3258 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11576 |\n", + "| fps | 170 |\n", + "| time_elapsed | 754 |\n", + "| total_timesteps | 128226 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.47 |\n", + "| n_updates | 3259 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11580 |\n", + "| fps | 170 |\n", + "| time_elapsed | 754 |\n", + "| total_timesteps | 128244 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.71 |\n", + "| n_updates | 3260 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11584 |\n", + "| fps | 170 |\n", + "| time_elapsed | 754 |\n", + "| total_timesteps | 128274 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 3261 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11588 |\n", + "| fps | 170 |\n", + "| time_elapsed | 754 |\n", + "| total_timesteps | 128304 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.78 |\n", + "| n_updates | 3262 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11592 |\n", + "| fps | 169 |\n", + "| time_elapsed | 755 |\n", + "| total_timesteps | 128352 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.88 |\n", + "| n_updates | 3264 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11596 |\n", + "| fps | 169 |\n", + "| time_elapsed | 755 |\n", + "| total_timesteps | 128400 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.7 |\n", + "| n_updates | 3266 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11600 |\n", + "| fps | 169 |\n", + "| time_elapsed | 755 |\n", + "| total_timesteps | 128418 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.39 |\n", + "| n_updates | 3267 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11604 |\n", + "| fps | 169 |\n", + "| time_elapsed | 755 |\n", + "| total_timesteps | 128448 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.89 |\n", + "| n_updates | 3268 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11608 |\n", + "| fps | 169 |\n", + "| time_elapsed | 756 |\n", + "| total_timesteps | 128472 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.27 |\n", + "| n_updates | 3269 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11612 |\n", + "| fps | 169 |\n", + "| time_elapsed | 756 |\n", + "| total_timesteps | 128514 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.29 |\n", + "| n_updates | 3271 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11616 |\n", + "| fps | 169 |\n", + "| time_elapsed | 756 |\n", + "| total_timesteps | 128538 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.59 |\n", + "| n_updates | 3272 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11620 |\n", + "| fps | 169 |\n", + "| time_elapsed | 756 |\n", + "| total_timesteps | 128550 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.94 |\n", + "| n_updates | 3273 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11624 |\n", + "| fps | 169 |\n", + "| time_elapsed | 757 |\n", + "| total_timesteps | 128580 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.61 |\n", + "| n_updates | 3274 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11628 |\n", + "| fps | 169 |\n", + "| time_elapsed | 757 |\n", + "| total_timesteps | 128652 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 3277 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11632 |\n", + "| fps | 169 |\n", + "| time_elapsed | 758 |\n", + "| total_timesteps | 128682 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.9 |\n", + "| n_updates | 3278 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11636 |\n", + "| fps | 169 |\n", + "| time_elapsed | 758 |\n", + "| total_timesteps | 128712 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.09 |\n", + "| n_updates | 3279 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11640 |\n", + "| fps | 169 |\n", + "| time_elapsed | 758 |\n", + "| total_timesteps | 128736 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 3280 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11644 |\n", + "| fps | 169 |\n", + "| time_elapsed | 758 |\n", + "| total_timesteps | 128766 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.78 |\n", + "| n_updates | 3282 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11648 |\n", + "| fps | 169 |\n", + "| time_elapsed | 759 |\n", + "| total_timesteps | 128796 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.9 |\n", + "| n_updates | 3283 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11652 |\n", + "| fps | 169 |\n", + "| time_elapsed | 759 |\n", + "| total_timesteps | 128820 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.97 |\n", + "| n_updates | 3284 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11656 |\n", + "| fps | 169 |\n", + "| time_elapsed | 759 |\n", + "| total_timesteps | 128856 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.52 |\n", + "| n_updates | 3285 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11660 |\n", + "| fps | 169 |\n", + "| time_elapsed | 759 |\n", + "| total_timesteps | 128874 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.45 |\n", + "| n_updates | 3286 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11664 |\n", + "| fps | 169 |\n", + "| time_elapsed | 760 |\n", + "| total_timesteps | 128934 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.69 |\n", + "| n_updates | 3289 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11668 |\n", + "| fps | 169 |\n", + "| time_elapsed | 760 |\n", + "| total_timesteps | 128964 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.02 |\n", + "| n_updates | 3290 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11672 |\n", + "| fps | 169 |\n", + "| time_elapsed | 760 |\n", + "| total_timesteps | 128982 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.65 |\n", + "| n_updates | 3291 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11676 |\n", + "| fps | 169 |\n", + "| time_elapsed | 760 |\n", + "| total_timesteps | 129006 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.9 |\n", + "| n_updates | 3292 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11680 |\n", + "| fps | 169 |\n", + "| time_elapsed | 761 |\n", + "| total_timesteps | 129036 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.74 |\n", + "| n_updates | 3293 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11684 |\n", + "| fps | 169 |\n", + "| time_elapsed | 761 |\n", + "| total_timesteps | 129060 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.26 |\n", + "| n_updates | 3294 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11688 |\n", + "| fps | 169 |\n", + "| time_elapsed | 761 |\n", + "| total_timesteps | 129078 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.57 |\n", + "| n_updates | 3295 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11692 |\n", + "| fps | 169 |\n", + "| time_elapsed | 761 |\n", + "| total_timesteps | 129102 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.28 |\n", + "| n_updates | 3296 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11696 |\n", + "| fps | 169 |\n", + "| time_elapsed | 762 |\n", + "| total_timesteps | 129156 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.84 |\n", + "| n_updates | 3298 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11700 |\n", + "| fps | 169 |\n", + "| time_elapsed | 762 |\n", + "| total_timesteps | 129204 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.45 |\n", + "| n_updates | 3300 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11704 |\n", + "| fps | 169 |\n", + "| time_elapsed | 763 |\n", + "| total_timesteps | 129294 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.95 |\n", + "| n_updates | 3304 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11708 |\n", + "| fps | 169 |\n", + "| time_elapsed | 763 |\n", + "| total_timesteps | 129330 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.03 |\n", + "| n_updates | 3305 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11712 |\n", + "| fps | 169 |\n", + "| time_elapsed | 764 |\n", + "| total_timesteps | 129366 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.83 |\n", + "| n_updates | 3307 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11716 |\n", + "| fps | 169 |\n", + "| time_elapsed | 764 |\n", + "| total_timesteps | 129396 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 3308 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11720 |\n", + "| fps | 169 |\n", + "| time_elapsed | 764 |\n", + "| total_timesteps | 129432 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.99 |\n", + "| n_updates | 3309 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11724 |\n", + "| fps | 169 |\n", + "| time_elapsed | 764 |\n", + "| total_timesteps | 129474 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.76 |\n", + "| n_updates | 3311 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11728 |\n", + "| fps | 169 |\n", + "| time_elapsed | 765 |\n", + "| total_timesteps | 129510 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.69 |\n", + "| n_updates | 3313 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11732 |\n", + "| fps | 169 |\n", + "| time_elapsed | 765 |\n", + "| total_timesteps | 129576 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.74 |\n", + "| n_updates | 3315 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11736 |\n", + "| fps | 169 |\n", + "| time_elapsed | 766 |\n", + "| total_timesteps | 129618 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 3317 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11740 |\n", + "| fps | 169 |\n", + "| time_elapsed | 766 |\n", + "| total_timesteps | 129648 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.09 |\n", + "| n_updates | 3318 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11744 |\n", + "| fps | 169 |\n", + "| time_elapsed | 766 |\n", + "| total_timesteps | 129702 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.2 |\n", + "| n_updates | 3321 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11748 |\n", + "| fps | 169 |\n", + "| time_elapsed | 767 |\n", + "| total_timesteps | 129726 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.28 |\n", + "| n_updates | 3322 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11752 |\n", + "| fps | 169 |\n", + "| time_elapsed | 767 |\n", + "| total_timesteps | 129756 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.73 |\n", + "| n_updates | 3323 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11756 |\n", + "| fps | 169 |\n", + "| time_elapsed | 767 |\n", + "| total_timesteps | 129822 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.37 |\n", + "| n_updates | 3326 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11760 |\n", + "| fps | 169 |\n", + "| time_elapsed | 768 |\n", + "| total_timesteps | 129888 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.7 |\n", + "| n_updates | 3328 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11764 |\n", + "| fps | 169 |\n", + "| time_elapsed | 768 |\n", + "| total_timesteps | 129954 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.22 |\n", + "| n_updates | 3331 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11768 |\n", + "| fps | 168 |\n", + "| time_elapsed | 769 |\n", + "| total_timesteps | 129966 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.42 |\n", + "| n_updates | 3332 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11772 |\n", + "| fps | 168 |\n", + "| time_elapsed | 769 |\n", + "| total_timesteps | 130008 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.83 |\n", + "| n_updates | 3333 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11776 |\n", + "| fps | 168 |\n", + "| time_elapsed | 769 |\n", + "| total_timesteps | 130038 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.07 |\n", + "| n_updates | 3335 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11780 |\n", + "| fps | 168 |\n", + "| time_elapsed | 770 |\n", + "| total_timesteps | 130098 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 3337 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11784 |\n", + "| fps | 168 |\n", + "| time_elapsed | 770 |\n", + "| total_timesteps | 130176 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.86 |\n", + "| n_updates | 3340 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11788 |\n", + "| fps | 168 |\n", + "| time_elapsed | 771 |\n", + "| total_timesteps | 130224 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.21 |\n", + "| n_updates | 3342 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11792 |\n", + "| fps | 168 |\n", + "| time_elapsed | 771 |\n", + "| total_timesteps | 130254 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.25 |\n", + "| n_updates | 3344 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11796 |\n", + "| fps | 168 |\n", + "| time_elapsed | 771 |\n", + "| total_timesteps | 130320 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.44 |\n", + "| n_updates | 3346 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11800 |\n", + "| fps | 168 |\n", + "| time_elapsed | 772 |\n", + "| total_timesteps | 130332 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.89 |\n", + "| n_updates | 3347 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11804 |\n", + "| fps | 168 |\n", + "| time_elapsed | 772 |\n", + "| total_timesteps | 130356 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.73 |\n", + "| n_updates | 3348 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11808 |\n", + "| fps | 168 |\n", + "| time_elapsed | 772 |\n", + "| total_timesteps | 130392 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.88 |\n", + "| n_updates | 3349 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11812 |\n", + "| fps | 168 |\n", + "| time_elapsed | 772 |\n", + "| total_timesteps | 130428 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.77 |\n", + "| n_updates | 3351 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11816 |\n", + "| fps | 168 |\n", + "| time_elapsed | 773 |\n", + "| total_timesteps | 130458 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.9 |\n", + "| n_updates | 3352 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11820 |\n", + "| fps | 168 |\n", + "| time_elapsed | 773 |\n", + "| total_timesteps | 130518 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.24 |\n", + "| n_updates | 3355 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11824 |\n", + "| fps | 168 |\n", + "| time_elapsed | 773 |\n", + "| total_timesteps | 130554 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.11 |\n", + "| n_updates | 3356 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11828 |\n", + "| fps | 168 |\n", + "| time_elapsed | 774 |\n", + "| total_timesteps | 130602 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.11 |\n", + "| n_updates | 3358 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11832 |\n", + "| fps | 168 |\n", + "| time_elapsed | 774 |\n", + "| total_timesteps | 130632 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.42 |\n", + "| n_updates | 3359 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11836 |\n", + "| fps | 168 |\n", + "| time_elapsed | 774 |\n", + "| total_timesteps | 130662 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.99 |\n", + "| n_updates | 3361 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11840 |\n", + "| fps | 168 |\n", + "| time_elapsed | 775 |\n", + "| total_timesteps | 130704 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.7 |\n", + "| n_updates | 3362 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11844 |\n", + "| fps | 168 |\n", + "| time_elapsed | 775 |\n", + "| total_timesteps | 130752 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.03 |\n", + "| n_updates | 3364 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11848 |\n", + "| fps | 168 |\n", + "| time_elapsed | 776 |\n", + "| total_timesteps | 130806 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.07 |\n", + "| n_updates | 3367 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11852 |\n", + "| fps | 168 |\n", + "| time_elapsed | 776 |\n", + "| total_timesteps | 130842 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.29 |\n", + "| n_updates | 3368 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11856 |\n", + "| fps | 168 |\n", + "| time_elapsed | 776 |\n", + "| total_timesteps | 130878 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.87 |\n", + "| n_updates | 3370 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11860 |\n", + "| fps | 168 |\n", + "| time_elapsed | 776 |\n", + "| total_timesteps | 130920 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.64 |\n", + "| n_updates | 3371 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11864 |\n", + "| fps | 168 |\n", + "| time_elapsed | 777 |\n", + "| total_timesteps | 130956 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.91 |\n", + "| n_updates | 3373 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11868 |\n", + "| fps | 168 |\n", + "| time_elapsed | 777 |\n", + "| total_timesteps | 130986 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.8 |\n", + "| n_updates | 3374 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11872 |\n", + "| fps | 168 |\n", + "| time_elapsed | 777 |\n", + "| total_timesteps | 131010 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.12 |\n", + "| n_updates | 3375 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11876 |\n", + "| fps | 168 |\n", + "| time_elapsed | 777 |\n", + "| total_timesteps | 131040 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.85 |\n", + "| n_updates | 3376 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11880 |\n", + "| fps | 168 |\n", + "| time_elapsed | 778 |\n", + "| total_timesteps | 131112 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.92 |\n", + "| n_updates | 3379 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11884 |\n", + "| fps | 168 |\n", + "| time_elapsed | 779 |\n", + "| total_timesteps | 131184 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 3382 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11888 |\n", + "| fps | 168 |\n", + "| time_elapsed | 779 |\n", + "| total_timesteps | 131226 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.65 |\n", + "| n_updates | 3384 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11892 |\n", + "| fps | 168 |\n", + "| time_elapsed | 779 |\n", + "| total_timesteps | 131268 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.8 |\n", + "| n_updates | 3386 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11896 |\n", + "| fps | 168 |\n", + "| time_elapsed | 780 |\n", + "| total_timesteps | 131340 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5 |\n", + "| n_updates | 3389 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11900 |\n", + "| fps | 168 |\n", + "| time_elapsed | 780 |\n", + "| total_timesteps | 131376 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.95 |\n", + "| n_updates | 3390 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11904 |\n", + "| fps | 168 |\n", + "| time_elapsed | 781 |\n", + "| total_timesteps | 131430 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.14 |\n", + "| n_updates | 3393 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11908 |\n", + "| fps | 168 |\n", + "| time_elapsed | 781 |\n", + "| total_timesteps | 131502 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.58 |\n", + "| n_updates | 3396 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11912 |\n", + "| fps | 168 |\n", + "| time_elapsed | 782 |\n", + "| total_timesteps | 131550 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.61 |\n", + "| n_updates | 3398 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11916 |\n", + "| fps | 168 |\n", + "| time_elapsed | 782 |\n", + "| total_timesteps | 131592 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.12 |\n", + "| n_updates | 3399 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11920 |\n", + "| fps | 168 |\n", + "| time_elapsed | 782 |\n", + "| total_timesteps | 131652 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.39 |\n", + "| n_updates | 3402 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11924 |\n", + "| fps | 168 |\n", + "| time_elapsed | 783 |\n", + "| total_timesteps | 131682 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.07 |\n", + "| n_updates | 3403 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11928 |\n", + "| fps | 168 |\n", + "| time_elapsed | 783 |\n", + "| total_timesteps | 131718 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.02 |\n", + "| n_updates | 3405 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11932 |\n", + "| fps | 168 |\n", + "| time_elapsed | 783 |\n", + "| total_timesteps | 131784 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.73 |\n", + "| n_updates | 3407 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11936 |\n", + "| fps | 168 |\n", + "| time_elapsed | 784 |\n", + "| total_timesteps | 131814 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.81 |\n", + "| n_updates | 3409 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11940 |\n", + "| fps | 168 |\n", + "| time_elapsed | 784 |\n", + "| total_timesteps | 131862 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.05 |\n", + "| n_updates | 3411 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11944 |\n", + "| fps | 168 |\n", + "| time_elapsed | 784 |\n", + "| total_timesteps | 131880 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11948 |\n", + "| fps | 168 |\n", + "| time_elapsed | 785 |\n", + "| total_timesteps | 131928 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.69 |\n", + "| n_updates | 3413 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11952 |\n", + "| fps | 167 |\n", + "| time_elapsed | 785 |\n", + "| total_timesteps | 132036 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.23 |\n", + "| n_updates | 3418 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11956 |\n", + "| fps | 167 |\n", + "| time_elapsed | 786 |\n", + "| total_timesteps | 132096 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2 |\n", + "| n_updates | 3420 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11960 |\n", + "| fps | 167 |\n", + "| time_elapsed | 787 |\n", + "| total_timesteps | 132180 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.97 |\n", + "| n_updates | 3424 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11964 |\n", + "| fps | 167 |\n", + "| time_elapsed | 787 |\n", + "| total_timesteps | 132228 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.47 |\n", + "| n_updates | 3426 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11968 |\n", + "| fps | 167 |\n", + "| time_elapsed | 787 |\n", + "| total_timesteps | 132270 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 3428 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11972 |\n", + "| fps | 167 |\n", + "| time_elapsed | 788 |\n", + "| total_timesteps | 132312 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.63 |\n", + "| n_updates | 3429 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11976 |\n", + "| fps | 167 |\n", + "| time_elapsed | 788 |\n", + "| total_timesteps | 132342 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.78 |\n", + "| n_updates | 3431 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11980 |\n", + "| fps | 167 |\n", + "| time_elapsed | 788 |\n", + "| total_timesteps | 132384 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.09 |\n", + "| n_updates | 3432 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11984 |\n", + "| fps | 167 |\n", + "| time_elapsed | 788 |\n", + "| total_timesteps | 132408 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.74 |\n", + "| n_updates | 3433 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11988 |\n", + "| fps | 167 |\n", + "| time_elapsed | 789 |\n", + "| total_timesteps | 132462 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.98 |\n", + "| n_updates | 3436 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11992 |\n", + "| fps | 167 |\n", + "| time_elapsed | 789 |\n", + "| total_timesteps | 132504 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.29 |\n", + "| n_updates | 3437 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 11996 |\n", + "| fps | 167 |\n", + "| time_elapsed | 790 |\n", + "| total_timesteps | 132570 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.68 |\n", + "| n_updates | 3440 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12000 |\n", + "| fps | 167 |\n", + "| time_elapsed | 790 |\n", + "| total_timesteps | 132618 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.79 |\n", + "| n_updates | 3442 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12004 |\n", + "| fps | 167 |\n", + "| time_elapsed | 791 |\n", + "| total_timesteps | 132678 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 3445 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12008 |\n", + "| fps | 167 |\n", + "| time_elapsed | 791 |\n", + "| total_timesteps | 132732 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 3447 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12012 |\n", + "| fps | 167 |\n", + "| time_elapsed | 791 |\n", + "| total_timesteps | 132768 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.84 |\n", + "| n_updates | 3448 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12016 |\n", + "| fps | 167 |\n", + "| time_elapsed | 792 |\n", + "| total_timesteps | 132786 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.79 |\n", + "| n_updates | 3449 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12020 |\n", + "| fps | 167 |\n", + "| time_elapsed | 792 |\n", + "| total_timesteps | 132822 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.93 |\n", + "| n_updates | 3451 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12024 |\n", + "| fps | 167 |\n", + "| time_elapsed | 792 |\n", + "| total_timesteps | 132888 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 3453 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12028 |\n", + "| fps | 167 |\n", + "| time_elapsed | 793 |\n", + "| total_timesteps | 133002 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 3458 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12032 |\n", + "| fps | 167 |\n", + "| time_elapsed | 794 |\n", + "| total_timesteps | 133044 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3 |\n", + "| n_updates | 3460 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12036 |\n", + "| fps | 167 |\n", + "| time_elapsed | 794 |\n", + "| total_timesteps | 133122 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.43 |\n", + "| n_updates | 3463 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12040 |\n", + "| fps | 167 |\n", + "| time_elapsed | 795 |\n", + "| total_timesteps | 133164 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.7 |\n", + "| n_updates | 3465 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12044 |\n", + "| fps | 167 |\n", + "| time_elapsed | 795 |\n", + "| total_timesteps | 133194 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 3466 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12048 |\n", + "| fps | 167 |\n", + "| time_elapsed | 795 |\n", + "| total_timesteps | 133230 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.8 |\n", + "| n_updates | 3468 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12052 |\n", + "| fps | 167 |\n", + "| time_elapsed | 796 |\n", + "| total_timesteps | 133302 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.39 |\n", + "| n_updates | 3471 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12056 |\n", + "| fps | 167 |\n", + "| time_elapsed | 796 |\n", + "| total_timesteps | 133392 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.91 |\n", + "| n_updates | 3474 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12060 |\n", + "| fps | 167 |\n", + "| time_elapsed | 797 |\n", + "| total_timesteps | 133416 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.77 |\n", + "| n_updates | 3475 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12064 |\n", + "| fps | 167 |\n", + "| time_elapsed | 797 |\n", + "| total_timesteps | 133440 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.89 |\n", + "| n_updates | 3476 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12068 |\n", + "| fps | 167 |\n", + "| time_elapsed | 797 |\n", + "| total_timesteps | 133500 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.77 |\n", + "| n_updates | 3479 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12072 |\n", + "| fps | 167 |\n", + "| time_elapsed | 798 |\n", + "| total_timesteps | 133548 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.69 |\n", + "| n_updates | 3481 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12076 |\n", + "| fps | 167 |\n", + "| time_elapsed | 798 |\n", + "| total_timesteps | 133584 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.06 |\n", + "| n_updates | 3482 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12080 |\n", + "| fps | 167 |\n", + "| time_elapsed | 798 |\n", + "| total_timesteps | 133614 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.62 |\n", + "| n_updates | 3484 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12084 |\n", + "| fps | 167 |\n", + "| time_elapsed | 799 |\n", + "| total_timesteps | 133650 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.77 |\n", + "| n_updates | 3485 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12088 |\n", + "| fps | 167 |\n", + "| time_elapsed | 799 |\n", + "| total_timesteps | 133668 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.94 |\n", + "| n_updates | 3486 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12092 |\n", + "| fps | 167 |\n", + "| time_elapsed | 799 |\n", + "| total_timesteps | 133704 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.85 |\n", + "| n_updates | 3487 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12096 |\n", + "| fps | 167 |\n", + "| time_elapsed | 799 |\n", + "| total_timesteps | 133746 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.34 |\n", + "| n_updates | 3489 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12100 |\n", + "| fps | 167 |\n", + "| time_elapsed | 800 |\n", + "| total_timesteps | 133818 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.53 |\n", + "| n_updates | 3492 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12104 |\n", + "| fps | 167 |\n", + "| time_elapsed | 800 |\n", + "| total_timesteps | 133878 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 3495 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12108 |\n", + "| fps | 167 |\n", + "| time_elapsed | 801 |\n", + "| total_timesteps | 133920 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.39 |\n", + "| n_updates | 3496 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12112 |\n", + "| fps | 167 |\n", + "| time_elapsed | 801 |\n", + "| total_timesteps | 133950 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.04 |\n", + "| n_updates | 3498 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12116 |\n", + "| fps | 167 |\n", + "| time_elapsed | 801 |\n", + "| total_timesteps | 133992 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.08 |\n", + "| n_updates | 3499 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12120 |\n", + "| fps | 167 |\n", + "| time_elapsed | 802 |\n", + "| total_timesteps | 134058 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.86 |\n", + "| n_updates | 3502 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12124 |\n", + "| fps | 167 |\n", + "| time_elapsed | 802 |\n", + "| total_timesteps | 134112 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.55 |\n", + "| n_updates | 3504 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12128 |\n", + "| fps | 167 |\n", + "| time_elapsed | 803 |\n", + "| total_timesteps | 134160 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.87 |\n", + "| n_updates | 3506 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12132 |\n", + "| fps | 167 |\n", + "| time_elapsed | 803 |\n", + "| total_timesteps | 134202 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.64 |\n", + "| n_updates | 3508 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12136 |\n", + "| fps | 166 |\n", + "| time_elapsed | 803 |\n", + "| total_timesteps | 134244 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.69 |\n", + "| n_updates | 3510 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12140 |\n", + "| fps | 166 |\n", + "| time_elapsed | 804 |\n", + "| total_timesteps | 134310 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.98 |\n", + "| n_updates | 3513 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12144 |\n", + "| fps | 166 |\n", + "| time_elapsed | 804 |\n", + "| total_timesteps | 134352 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.07 |\n", + "| n_updates | 3514 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12148 |\n", + "| fps | 166 |\n", + "| time_elapsed | 805 |\n", + "| total_timesteps | 134388 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 3516 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12152 |\n", + "| fps | 166 |\n", + "| time_elapsed | 805 |\n", + "| total_timesteps | 134430 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.67 |\n", + "| n_updates | 3518 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12156 |\n", + "| fps | 166 |\n", + "| time_elapsed | 805 |\n", + "| total_timesteps | 134484 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.77 |\n", + "| n_updates | 3520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12160 |\n", + "| fps | 166 |\n", + "| time_elapsed | 806 |\n", + "| total_timesteps | 134526 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.1 |\n", + "| n_updates | 3522 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12164 |\n", + "| fps | 166 |\n", + "| time_elapsed | 806 |\n", + "| total_timesteps | 134598 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.48 |\n", + "| n_updates | 3525 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12168 |\n", + "| fps | 166 |\n", + "| time_elapsed | 807 |\n", + "| total_timesteps | 134622 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.7 |\n", + "| n_updates | 3526 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12172 |\n", + "| fps | 166 |\n", + "| time_elapsed | 807 |\n", + "| total_timesteps | 134658 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.41 |\n", + "| n_updates | 3527 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12176 |\n", + "| fps | 166 |\n", + "| time_elapsed | 807 |\n", + "| total_timesteps | 134688 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.23 |\n", + "| n_updates | 3528 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12180 |\n", + "| fps | 166 |\n", + "| time_elapsed | 807 |\n", + "| total_timesteps | 134712 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.27 |\n", + "| n_updates | 3529 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12184 |\n", + "| fps | 166 |\n", + "| time_elapsed | 808 |\n", + "| total_timesteps | 134742 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 3531 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12188 |\n", + "| fps | 166 |\n", + "| time_elapsed | 808 |\n", + "| total_timesteps | 134784 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.79 |\n", + "| n_updates | 3532 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12192 |\n", + "| fps | 166 |\n", + "| time_elapsed | 808 |\n", + "| total_timesteps | 134820 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.08 |\n", + "| n_updates | 3534 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12196 |\n", + "| fps | 166 |\n", + "| time_elapsed | 809 |\n", + "| total_timesteps | 134880 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.82 |\n", + "| n_updates | 3536 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12200 |\n", + "| fps | 166 |\n", + "| time_elapsed | 809 |\n", + "| total_timesteps | 134940 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 3539 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12204 |\n", + "| fps | 166 |\n", + "| time_elapsed | 809 |\n", + "| total_timesteps | 134964 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.59 |\n", + "| n_updates | 3540 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12208 |\n", + "| fps | 166 |\n", + "| time_elapsed | 810 |\n", + "| total_timesteps | 135006 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.07 |\n", + "| n_updates | 3542 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12212 |\n", + "| fps | 166 |\n", + "| time_elapsed | 810 |\n", + "| total_timesteps | 135060 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.71 |\n", + "| n_updates | 3544 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12216 |\n", + "| fps | 166 |\n", + "| time_elapsed | 811 |\n", + "| total_timesteps | 135114 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.33 |\n", + "| n_updates | 3546 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12220 |\n", + "| fps | 166 |\n", + "| time_elapsed | 811 |\n", + "| total_timesteps | 135162 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.14 |\n", + "| n_updates | 3548 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12224 |\n", + "| fps | 166 |\n", + "| time_elapsed | 811 |\n", + "| total_timesteps | 135192 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.83 |\n", + "| n_updates | 3549 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12228 |\n", + "| fps | 166 |\n", + "| time_elapsed | 811 |\n", + "| total_timesteps | 135216 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.95 |\n", + "| n_updates | 3550 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12232 |\n", + "| fps | 166 |\n", + "| time_elapsed | 812 |\n", + "| total_timesteps | 135252 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.67 |\n", + "| n_updates | 3552 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12236 |\n", + "| fps | 166 |\n", + "| time_elapsed | 812 |\n", + "| total_timesteps | 135282 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.66 |\n", + "| n_updates | 3553 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12240 |\n", + "| fps | 166 |\n", + "| time_elapsed | 812 |\n", + "| total_timesteps | 135300 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.27 |\n", + "| n_updates | 3554 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12244 |\n", + "| fps | 166 |\n", + "| time_elapsed | 812 |\n", + "| total_timesteps | 135330 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.71 |\n", + "| n_updates | 3555 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12248 |\n", + "| fps | 166 |\n", + "| time_elapsed | 813 |\n", + "| total_timesteps | 135384 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.3 |\n", + "| n_updates | 3557 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12252 |\n", + "| fps | 166 |\n", + "| time_elapsed | 813 |\n", + "| total_timesteps | 135432 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.6 |\n", + "| n_updates | 3559 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12256 |\n", + "| fps | 166 |\n", + "| time_elapsed | 814 |\n", + "| total_timesteps | 135462 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.6 |\n", + "| n_updates | 3561 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12260 |\n", + "| fps | 166 |\n", + "| time_elapsed | 814 |\n", + "| total_timesteps | 135486 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.74 |\n", + "| n_updates | 3562 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12264 |\n", + "| fps | 166 |\n", + "| time_elapsed | 814 |\n", + "| total_timesteps | 135522 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.01 |\n", + "| n_updates | 3563 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12268 |\n", + "| fps | 166 |\n", + "| time_elapsed | 814 |\n", + "| total_timesteps | 135570 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.18 |\n", + "| n_updates | 3565 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12272 |\n", + "| fps | 166 |\n", + "| time_elapsed | 815 |\n", + "| total_timesteps | 135594 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.18 |\n", + "| n_updates | 3566 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12276 |\n", + "| fps | 166 |\n", + "| time_elapsed | 815 |\n", + "| total_timesteps | 135654 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.01 |\n", + "| n_updates | 3569 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12280 |\n", + "| fps | 166 |\n", + "| time_elapsed | 816 |\n", + "| total_timesteps | 135708 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.1 |\n", + "| n_updates | 3571 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12284 |\n", + "| fps | 166 |\n", + "| time_elapsed | 816 |\n", + "| total_timesteps | 135732 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.33 |\n", + "| n_updates | 3572 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12288 |\n", + "| fps | 166 |\n", + "| time_elapsed | 816 |\n", + "| total_timesteps | 135750 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 3573 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12292 |\n", + "| fps | 166 |\n", + "| time_elapsed | 816 |\n", + "| total_timesteps | 135792 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 3574 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12296 |\n", + "| fps | 166 |\n", + "| time_elapsed | 817 |\n", + "| total_timesteps | 135840 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 3576 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12300 |\n", + "| fps | 166 |\n", + "| time_elapsed | 817 |\n", + "| total_timesteps | 135864 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 3577 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12304 |\n", + "| fps | 166 |\n", + "| time_elapsed | 817 |\n", + "| total_timesteps | 135894 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.36 |\n", + "| n_updates | 3579 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12308 |\n", + "| fps | 166 |\n", + "| time_elapsed | 817 |\n", + "| total_timesteps | 135930 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.07 |\n", + "| n_updates | 3580 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12312 |\n", + "| fps | 166 |\n", + "| time_elapsed | 818 |\n", + "| total_timesteps | 135948 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.95 |\n", + "| n_updates | 3581 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12316 |\n", + "| fps | 166 |\n", + "| time_elapsed | 818 |\n", + "| total_timesteps | 135972 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.22 |\n", + "| n_updates | 3582 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12320 |\n", + "| fps | 166 |\n", + "| time_elapsed | 818 |\n", + "| total_timesteps | 136008 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.87 |\n", + "| n_updates | 3583 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12324 |\n", + "| fps | 166 |\n", + "| time_elapsed | 818 |\n", + "| total_timesteps | 136044 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.7 |\n", + "| n_updates | 3585 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12328 |\n", + "| fps | 166 |\n", + "| time_elapsed | 819 |\n", + "| total_timesteps | 136080 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.18 |\n", + "| n_updates | 3586 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12332 |\n", + "| fps | 166 |\n", + "| time_elapsed | 819 |\n", + "| total_timesteps | 136140 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.15 |\n", + "| n_updates | 3589 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12336 |\n", + "| fps | 166 |\n", + "| time_elapsed | 820 |\n", + "| total_timesteps | 136182 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.6 |\n", + "| n_updates | 3591 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12340 |\n", + "| fps | 166 |\n", + "| time_elapsed | 820 |\n", + "| total_timesteps | 136224 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.42 |\n", + "| n_updates | 3592 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12344 |\n", + "| fps | 166 |\n", + "| time_elapsed | 820 |\n", + "| total_timesteps | 136248 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.85 |\n", + "| n_updates | 3593 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12348 |\n", + "| fps | 166 |\n", + "| time_elapsed | 820 |\n", + "| total_timesteps | 136284 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.68 |\n", + "| n_updates | 3595 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12352 |\n", + "| fps | 166 |\n", + "| time_elapsed | 821 |\n", + "| total_timesteps | 136320 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.02 |\n", + "| n_updates | 3596 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12356 |\n", + "| fps | 165 |\n", + "| time_elapsed | 821 |\n", + "| total_timesteps | 136368 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.75 |\n", + "| n_updates | 3598 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12360 |\n", + "| fps | 165 |\n", + "| time_elapsed | 822 |\n", + "| total_timesteps | 136428 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.12 |\n", + "| n_updates | 3601 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12364 |\n", + "| fps | 165 |\n", + "| time_elapsed | 822 |\n", + "| total_timesteps | 136464 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.53 |\n", + "| n_updates | 3602 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12368 |\n", + "| fps | 165 |\n", + "| time_elapsed | 822 |\n", + "| total_timesteps | 136500 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 3604 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12372 |\n", + "| fps | 165 |\n", + "| time_elapsed | 822 |\n", + "| total_timesteps | 136530 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.03 |\n", + "| n_updates | 3605 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12376 |\n", + "| fps | 165 |\n", + "| time_elapsed | 823 |\n", + "| total_timesteps | 136548 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.61 |\n", + "| n_updates | 3606 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12380 |\n", + "| fps | 165 |\n", + "| time_elapsed | 823 |\n", + "| total_timesteps | 136596 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.17 |\n", + "| n_updates | 3608 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12384 |\n", + "| fps | 165 |\n", + "| time_elapsed | 823 |\n", + "| total_timesteps | 136650 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 3610 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12388 |\n", + "| fps | 165 |\n", + "| time_elapsed | 824 |\n", + "| total_timesteps | 136716 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 3613 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12392 |\n", + "| fps | 165 |\n", + "| time_elapsed | 824 |\n", + "| total_timesteps | 136752 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.74 |\n", + "| n_updates | 3614 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12396 |\n", + "| fps | 165 |\n", + "| time_elapsed | 825 |\n", + "| total_timesteps | 136800 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.88 |\n", + "| n_updates | 3616 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12400 |\n", + "| fps | 165 |\n", + "| time_elapsed | 825 |\n", + "| total_timesteps | 136842 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 3618 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12404 |\n", + "| fps | 165 |\n", + "| time_elapsed | 825 |\n", + "| total_timesteps | 136854 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.89 |\n", + "| n_updates | 3619 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12408 |\n", + "| fps | 165 |\n", + "| time_elapsed | 826 |\n", + "| total_timesteps | 136914 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 3621 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12412 |\n", + "| fps | 165 |\n", + "| time_elapsed | 826 |\n", + "| total_timesteps | 136932 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.13 |\n", + "| n_updates | 3622 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12416 |\n", + "| fps | 165 |\n", + "| time_elapsed | 826 |\n", + "| total_timesteps | 136974 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.6 |\n", + "| n_updates | 3624 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12420 |\n", + "| fps | 165 |\n", + "| time_elapsed | 826 |\n", + "| total_timesteps | 137010 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.96 |\n", + "| n_updates | 3625 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12424 |\n", + "| fps | 165 |\n", + "| time_elapsed | 827 |\n", + "| total_timesteps | 137046 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.87 |\n", + "| n_updates | 3627 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12428 |\n", + "| fps | 165 |\n", + "| time_elapsed | 827 |\n", + "| total_timesteps | 137088 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.49 |\n", + "| n_updates | 3628 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12432 |\n", + "| fps | 165 |\n", + "| time_elapsed | 828 |\n", + "| total_timesteps | 137142 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.48 |\n", + "| n_updates | 3631 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12436 |\n", + "| fps | 165 |\n", + "| time_elapsed | 828 |\n", + "| total_timesteps | 137160 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12440 |\n", + "| fps | 165 |\n", + "| time_elapsed | 828 |\n", + "| total_timesteps | 137202 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.45 |\n", + "| n_updates | 3633 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12444 |\n", + "| fps | 165 |\n", + "| time_elapsed | 828 |\n", + "| total_timesteps | 137238 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.97 |\n", + "| n_updates | 3635 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12448 |\n", + "| fps | 165 |\n", + "| time_elapsed | 829 |\n", + "| total_timesteps | 137280 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.12 |\n", + "| n_updates | 3636 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12452 |\n", + "| fps | 165 |\n", + "| time_elapsed | 829 |\n", + "| total_timesteps | 137334 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.01 |\n", + "| n_updates | 3639 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12456 |\n", + "| fps | 165 |\n", + "| time_elapsed | 830 |\n", + "| total_timesteps | 137388 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.5 |\n", + "| n_updates | 3641 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12460 |\n", + "| fps | 165 |\n", + "| time_elapsed | 830 |\n", + "| total_timesteps | 137424 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.56 |\n", + "| n_updates | 3642 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12464 |\n", + "| fps | 165 |\n", + "| time_elapsed | 830 |\n", + "| total_timesteps | 137436 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.7 |\n", + "| n_updates | 3643 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12468 |\n", + "| fps | 165 |\n", + "| time_elapsed | 830 |\n", + "| total_timesteps | 137472 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.84 |\n", + "| n_updates | 3644 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12472 |\n", + "| fps | 165 |\n", + "| time_elapsed | 831 |\n", + "| total_timesteps | 137508 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.81 |\n", + "| n_updates | 3646 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12476 |\n", + "| fps | 165 |\n", + "| time_elapsed | 831 |\n", + "| total_timesteps | 137544 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.04 |\n", + "| n_updates | 3647 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12480 |\n", + "| fps | 165 |\n", + "| time_elapsed | 832 |\n", + "| total_timesteps | 137634 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 3651 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12484 |\n", + "| fps | 165 |\n", + "| time_elapsed | 832 |\n", + "| total_timesteps | 137706 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.64 |\n", + "| n_updates | 3654 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12488 |\n", + "| fps | 165 |\n", + "| time_elapsed | 833 |\n", + "| total_timesteps | 137772 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.13 |\n", + "| n_updates | 3657 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12492 |\n", + "| fps | 165 |\n", + "| time_elapsed | 833 |\n", + "| total_timesteps | 137844 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.6 |\n", + "| n_updates | 3660 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12496 |\n", + "| fps | 165 |\n", + "| time_elapsed | 834 |\n", + "| total_timesteps | 137904 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 3662 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12500 |\n", + "| fps | 165 |\n", + "| time_elapsed | 834 |\n", + "| total_timesteps | 137964 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.08 |\n", + "| n_updates | 3665 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12504 |\n", + "| fps | 165 |\n", + "| time_elapsed | 835 |\n", + "| total_timesteps | 138054 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.01 |\n", + "| n_updates | 3669 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12508 |\n", + "| fps | 165 |\n", + "| time_elapsed | 835 |\n", + "| total_timesteps | 138102 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.63 |\n", + "| n_updates | 3671 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12512 |\n", + "| fps | 165 |\n", + "| time_elapsed | 836 |\n", + "| total_timesteps | 138144 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.4 |\n", + "| n_updates | 3672 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12516 |\n", + "| fps | 165 |\n", + "| time_elapsed | 836 |\n", + "| total_timesteps | 138180 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.75 |\n", + "| n_updates | 3674 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12520 |\n", + "| fps | 165 |\n", + "| time_elapsed | 836 |\n", + "| total_timesteps | 138222 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.15 |\n", + "| n_updates | 3676 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12524 |\n", + "| fps | 165 |\n", + "| time_elapsed | 837 |\n", + "| total_timesteps | 138246 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.67 |\n", + "| n_updates | 3677 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12528 |\n", + "| fps | 165 |\n", + "| time_elapsed | 837 |\n", + "| total_timesteps | 138282 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.18 |\n", + "| n_updates | 3678 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12532 |\n", + "| fps | 165 |\n", + "| time_elapsed | 837 |\n", + "| total_timesteps | 138324 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.89 |\n", + "| n_updates | 3680 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12536 |\n", + "| fps | 165 |\n", + "| time_elapsed | 838 |\n", + "| total_timesteps | 138378 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.25 |\n", + "| n_updates | 3682 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12540 |\n", + "| fps | 165 |\n", + "| time_elapsed | 838 |\n", + "| total_timesteps | 138426 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.84 |\n", + "| n_updates | 3684 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12544 |\n", + "| fps | 165 |\n", + "| time_elapsed | 838 |\n", + "| total_timesteps | 138462 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.02 |\n", + "| n_updates | 3686 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12548 |\n", + "| fps | 165 |\n", + "| time_elapsed | 839 |\n", + "| total_timesteps | 138498 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.73 |\n", + "| n_updates | 3687 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12552 |\n", + "| fps | 165 |\n", + "| time_elapsed | 839 |\n", + "| total_timesteps | 138534 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 3689 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12556 |\n", + "| fps | 165 |\n", + "| time_elapsed | 839 |\n", + "| total_timesteps | 138576 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.04 |\n", + "| n_updates | 3690 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12560 |\n", + "| fps | 164 |\n", + "| time_elapsed | 840 |\n", + "| total_timesteps | 138618 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.79 |\n", + "| n_updates | 3692 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12564 |\n", + "| fps | 164 |\n", + "| time_elapsed | 840 |\n", + "| total_timesteps | 138642 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 3693 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12568 |\n", + "| fps | 164 |\n", + "| time_elapsed | 840 |\n", + "| total_timesteps | 138696 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.97 |\n", + "| n_updates | 3695 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12572 |\n", + "| fps | 164 |\n", + "| time_elapsed | 841 |\n", + "| total_timesteps | 138756 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.94 |\n", + "| n_updates | 3698 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12576 |\n", + "| fps | 164 |\n", + "| time_elapsed | 842 |\n", + "| total_timesteps | 138846 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.87 |\n", + "| n_updates | 3702 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12580 |\n", + "| fps | 164 |\n", + "| time_elapsed | 842 |\n", + "| total_timesteps | 138894 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.59 |\n", + "| n_updates | 3704 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12584 |\n", + "| fps | 164 |\n", + "| time_elapsed | 842 |\n", + "| total_timesteps | 138936 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.09 |\n", + "| n_updates | 3705 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12588 |\n", + "| fps | 164 |\n", + "| time_elapsed | 843 |\n", + "| total_timesteps | 138972 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.77 |\n", + "| n_updates | 3707 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12592 |\n", + "| fps | 164 |\n", + "| time_elapsed | 843 |\n", + "| total_timesteps | 139008 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.6 |\n", + "| n_updates | 3708 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12596 |\n", + "| fps | 164 |\n", + "| time_elapsed | 843 |\n", + "| total_timesteps | 139074 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.2 |\n", + "| n_updates | 3711 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12600 |\n", + "| fps | 164 |\n", + "| time_elapsed | 844 |\n", + "| total_timesteps | 139116 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.74 |\n", + "| n_updates | 3713 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12604 |\n", + "| fps | 164 |\n", + "| time_elapsed | 844 |\n", + "| total_timesteps | 139164 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.96 |\n", + "| n_updates | 3715 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12608 |\n", + "| fps | 164 |\n", + "| time_elapsed | 844 |\n", + "| total_timesteps | 139200 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.76 |\n", + "| n_updates | 3716 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12612 |\n", + "| fps | 164 |\n", + "| time_elapsed | 845 |\n", + "| total_timesteps | 139242 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.77 |\n", + "| n_updates | 3718 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12616 |\n", + "| fps | 164 |\n", + "| time_elapsed | 845 |\n", + "| total_timesteps | 139278 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.92 |\n", + "| n_updates | 3720 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12620 |\n", + "| fps | 164 |\n", + "| time_elapsed | 845 |\n", + "| total_timesteps | 139302 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.48 |\n", + "| n_updates | 3721 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12624 |\n", + "| fps | 164 |\n", + "| time_elapsed | 845 |\n", + "| total_timesteps | 139320 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12628 |\n", + "| fps | 164 |\n", + "| time_elapsed | 846 |\n", + "| total_timesteps | 139350 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.19 |\n", + "| n_updates | 3723 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12632 |\n", + "| fps | 164 |\n", + "| time_elapsed | 846 |\n", + "| total_timesteps | 139410 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.33 |\n", + "| n_updates | 3725 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12636 |\n", + "| fps | 164 |\n", + "| time_elapsed | 846 |\n", + "| total_timesteps | 139440 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.96 |\n", + "| n_updates | 3726 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12640 |\n", + "| fps | 164 |\n", + "| time_elapsed | 847 |\n", + "| total_timesteps | 139470 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.23 |\n", + "| n_updates | 3728 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12644 |\n", + "| fps | 164 |\n", + "| time_elapsed | 847 |\n", + "| total_timesteps | 139530 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.51 |\n", + "| n_updates | 3730 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12648 |\n", + "| fps | 164 |\n", + "| time_elapsed | 847 |\n", + "| total_timesteps | 139560 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.73 |\n", + "| n_updates | 3731 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12652 |\n", + "| fps | 164 |\n", + "| time_elapsed | 848 |\n", + "| total_timesteps | 139584 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.71 |\n", + "| n_updates | 3732 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12656 |\n", + "| fps | 164 |\n", + "| time_elapsed | 848 |\n", + "| total_timesteps | 139614 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.69 |\n", + "| n_updates | 3734 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12660 |\n", + "| fps | 164 |\n", + "| time_elapsed | 849 |\n", + "| total_timesteps | 139686 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.91 |\n", + "| n_updates | 3737 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12664 |\n", + "| fps | 164 |\n", + "| time_elapsed | 849 |\n", + "| total_timesteps | 139704 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12668 |\n", + "| fps | 164 |\n", + "| time_elapsed | 849 |\n", + "| total_timesteps | 139764 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.47 |\n", + "| n_updates | 3740 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12672 |\n", + "| fps | 164 |\n", + "| time_elapsed | 850 |\n", + "| total_timesteps | 139824 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 3742 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12676 |\n", + "| fps | 164 |\n", + "| time_elapsed | 850 |\n", + "| total_timesteps | 139920 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.88 |\n", + "| n_updates | 3746 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12680 |\n", + "| fps | 164 |\n", + "| time_elapsed | 851 |\n", + "| total_timesteps | 139980 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.28 |\n", + "| n_updates | 3749 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12684 |\n", + "| fps | 164 |\n", + "| time_elapsed | 852 |\n", + "| total_timesteps | 140052 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.61 |\n", + "| n_updates | 3752 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12688 |\n", + "| fps | 164 |\n", + "| time_elapsed | 852 |\n", + "| total_timesteps | 140112 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.98 |\n", + "| n_updates | 3754 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12692 |\n", + "| fps | 164 |\n", + "| time_elapsed | 852 |\n", + "| total_timesteps | 140172 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.39 |\n", + "| n_updates | 3757 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12696 |\n", + "| fps | 164 |\n", + "| time_elapsed | 853 |\n", + "| total_timesteps | 140208 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.52 |\n", + "| n_updates | 3758 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12700 |\n", + "| fps | 164 |\n", + "| time_elapsed | 853 |\n", + "| total_timesteps | 140238 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.24 |\n", + "| n_updates | 3760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12704 |\n", + "| fps | 164 |\n", + "| time_elapsed | 853 |\n", + "| total_timesteps | 140268 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.3 |\n", + "| n_updates | 3761 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12708 |\n", + "| fps | 164 |\n", + "| time_elapsed | 853 |\n", + "| total_timesteps | 140298 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.11 |\n", + "| n_updates | 3762 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12712 |\n", + "| fps | 164 |\n", + "| time_elapsed | 854 |\n", + "| total_timesteps | 140334 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.18 |\n", + "| n_updates | 3764 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12716 |\n", + "| fps | 164 |\n", + "| time_elapsed | 854 |\n", + "| total_timesteps | 140406 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.92 |\n", + "| n_updates | 3767 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12720 |\n", + "| fps | 164 |\n", + "| time_elapsed | 855 |\n", + "| total_timesteps | 140442 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.47 |\n", + "| n_updates | 3768 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12724 |\n", + "| fps | 164 |\n", + "| time_elapsed | 855 |\n", + "| total_timesteps | 140496 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.57 |\n", + "| n_updates | 3770 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12728 |\n", + "| fps | 164 |\n", + "| time_elapsed | 856 |\n", + "| total_timesteps | 140580 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 3774 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12732 |\n", + "| fps | 164 |\n", + "| time_elapsed | 856 |\n", + "| total_timesteps | 140634 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.91 |\n", + "| n_updates | 3776 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12736 |\n", + "| fps | 164 |\n", + "| time_elapsed | 857 |\n", + "| total_timesteps | 140670 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.65 |\n", + "| n_updates | 3778 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12740 |\n", + "| fps | 164 |\n", + "| time_elapsed | 857 |\n", + "| total_timesteps | 140718 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.9 |\n", + "| n_updates | 3780 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12744 |\n", + "| fps | 164 |\n", + "| time_elapsed | 858 |\n", + "| total_timesteps | 140790 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.93 |\n", + "| n_updates | 3783 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12748 |\n", + "| fps | 164 |\n", + "| time_elapsed | 858 |\n", + "| total_timesteps | 140826 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.75 |\n", + "| n_updates | 3784 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12752 |\n", + "| fps | 164 |\n", + "| time_elapsed | 858 |\n", + "| total_timesteps | 140868 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.95 |\n", + "| n_updates | 3786 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12756 |\n", + "| fps | 164 |\n", + "| time_elapsed | 859 |\n", + "| total_timesteps | 140916 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.28 |\n", + "| n_updates | 3788 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12760 |\n", + "| fps | 164 |\n", + "| time_elapsed | 859 |\n", + "| total_timesteps | 140952 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.96 |\n", + "| n_updates | 3789 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12764 |\n", + "| fps | 164 |\n", + "| time_elapsed | 859 |\n", + "| total_timesteps | 140970 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.35 |\n", + "| n_updates | 3790 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12768 |\n", + "| fps | 163 |\n", + "| time_elapsed | 859 |\n", + "| total_timesteps | 141006 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.05 |\n", + "| n_updates | 3792 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12772 |\n", + "| fps | 163 |\n", + "| time_elapsed | 860 |\n", + "| total_timesteps | 141048 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.59 |\n", + "| n_updates | 3793 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12776 |\n", + "| fps | 163 |\n", + "| time_elapsed | 860 |\n", + "| total_timesteps | 141084 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.91 |\n", + "| n_updates | 3795 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12780 |\n", + "| fps | 163 |\n", + "| time_elapsed | 860 |\n", + "| total_timesteps | 141126 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.02 |\n", + "| n_updates | 3797 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12784 |\n", + "| fps | 163 |\n", + "| time_elapsed | 861 |\n", + "| total_timesteps | 141162 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.8 |\n", + "| n_updates | 3798 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12788 |\n", + "| fps | 163 |\n", + "| time_elapsed | 861 |\n", + "| total_timesteps | 141204 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.64 |\n", + "| n_updates | 3800 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12792 |\n", + "| fps | 163 |\n", + "| time_elapsed | 861 |\n", + "| total_timesteps | 141240 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.75 |\n", + "| n_updates | 3801 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12796 |\n", + "| fps | 163 |\n", + "| time_elapsed | 862 |\n", + "| total_timesteps | 141282 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.88 |\n", + "| n_updates | 3803 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12800 |\n", + "| fps | 163 |\n", + "| time_elapsed | 862 |\n", + "| total_timesteps | 141330 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 3805 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12804 |\n", + "| fps | 163 |\n", + "| time_elapsed | 862 |\n", + "| total_timesteps | 141366 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.51 |\n", + "| n_updates | 3807 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12808 |\n", + "| fps | 163 |\n", + "| time_elapsed | 863 |\n", + "| total_timesteps | 141426 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.04 |\n", + "| n_updates | 3809 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12812 |\n", + "| fps | 163 |\n", + "| time_elapsed | 863 |\n", + "| total_timesteps | 141462 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.77 |\n", + "| n_updates | 3811 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12816 |\n", + "| fps | 163 |\n", + "| time_elapsed | 863 |\n", + "| total_timesteps | 141468 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12820 |\n", + "| fps | 163 |\n", + "| time_elapsed | 863 |\n", + "| total_timesteps | 141504 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.69 |\n", + "| n_updates | 3812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12824 |\n", + "| fps | 163 |\n", + "| time_elapsed | 864 |\n", + "| total_timesteps | 141546 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.31 |\n", + "| n_updates | 3814 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12828 |\n", + "| fps | 163 |\n", + "| time_elapsed | 864 |\n", + "| total_timesteps | 141582 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 3816 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12832 |\n", + "| fps | 163 |\n", + "| time_elapsed | 864 |\n", + "| total_timesteps | 141618 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.77 |\n", + "| n_updates | 3817 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12836 |\n", + "| fps | 163 |\n", + "| time_elapsed | 865 |\n", + "| total_timesteps | 141678 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.03 |\n", + "| n_updates | 3820 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12840 |\n", + "| fps | 163 |\n", + "| time_elapsed | 865 |\n", + "| total_timesteps | 141708 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.8 |\n", + "| n_updates | 3821 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12844 |\n", + "| fps | 163 |\n", + "| time_elapsed | 866 |\n", + "| total_timesteps | 141786 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.97 |\n", + "| n_updates | 3824 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12848 |\n", + "| fps | 163 |\n", + "| time_elapsed | 866 |\n", + "| total_timesteps | 141792 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12852 |\n", + "| fps | 163 |\n", + "| time_elapsed | 866 |\n", + "| total_timesteps | 141840 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.84 |\n", + "| n_updates | 3826 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12856 |\n", + "| fps | 163 |\n", + "| time_elapsed | 867 |\n", + "| total_timesteps | 141882 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.03 |\n", + "| n_updates | 3828 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12860 |\n", + "| fps | 163 |\n", + "| time_elapsed | 867 |\n", + "| total_timesteps | 141918 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.36 |\n", + "| n_updates | 3830 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12864 |\n", + "| fps | 163 |\n", + "| time_elapsed | 867 |\n", + "| total_timesteps | 141960 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.7 |\n", + "| n_updates | 3831 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12868 |\n", + "| fps | 163 |\n", + "| time_elapsed | 868 |\n", + "| total_timesteps | 142002 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 3833 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12872 |\n", + "| fps | 163 |\n", + "| time_elapsed | 868 |\n", + "| total_timesteps | 142044 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.97 |\n", + "| n_updates | 3835 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12876 |\n", + "| fps | 163 |\n", + "| time_elapsed | 868 |\n", + "| total_timesteps | 142080 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.8 |\n", + "| n_updates | 3836 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12880 |\n", + "| fps | 163 |\n", + "| time_elapsed | 869 |\n", + "| total_timesteps | 142116 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.17 |\n", + "| n_updates | 3838 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12884 |\n", + "| fps | 163 |\n", + "| time_elapsed | 869 |\n", + "| total_timesteps | 142146 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.07 |\n", + "| n_updates | 3839 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12888 |\n", + "| fps | 163 |\n", + "| time_elapsed | 869 |\n", + "| total_timesteps | 142176 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.31 |\n", + "| n_updates | 3840 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12892 |\n", + "| fps | 163 |\n", + "| time_elapsed | 869 |\n", + "| total_timesteps | 142212 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.85 |\n", + "| n_updates | 3842 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12896 |\n", + "| fps | 163 |\n", + "| time_elapsed | 870 |\n", + "| total_timesteps | 142242 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.21 |\n", + "| n_updates | 3843 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12900 |\n", + "| fps | 163 |\n", + "| time_elapsed | 870 |\n", + "| total_timesteps | 142272 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.8 |\n", + "| n_updates | 3844 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12904 |\n", + "| fps | 163 |\n", + "| time_elapsed | 870 |\n", + "| total_timesteps | 142314 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.64 |\n", + "| n_updates | 3846 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12908 |\n", + "| fps | 163 |\n", + "| time_elapsed | 871 |\n", + "| total_timesteps | 142350 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.88 |\n", + "| n_updates | 3848 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12912 |\n", + "| fps | 163 |\n", + "| time_elapsed | 871 |\n", + "| total_timesteps | 142380 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.91 |\n", + "| n_updates | 3849 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12916 |\n", + "| fps | 163 |\n", + "| time_elapsed | 871 |\n", + "| total_timesteps | 142422 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.07 |\n", + "| n_updates | 3851 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12920 |\n", + "| fps | 163 |\n", + "| time_elapsed | 872 |\n", + "| total_timesteps | 142470 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.97 |\n", + "| n_updates | 3853 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12924 |\n", + "| fps | 163 |\n", + "| time_elapsed | 872 |\n", + "| total_timesteps | 142500 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.63 |\n", + "| n_updates | 3854 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12928 |\n", + "| fps | 163 |\n", + "| time_elapsed | 872 |\n", + "| total_timesteps | 142536 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.81 |\n", + "| n_updates | 3855 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12932 |\n", + "| fps | 163 |\n", + "| time_elapsed | 873 |\n", + "| total_timesteps | 142602 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.66 |\n", + "| n_updates | 3858 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12936 |\n", + "| fps | 163 |\n", + "| time_elapsed | 873 |\n", + "| total_timesteps | 142686 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.63 |\n", + "| n_updates | 3862 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12940 |\n", + "| fps | 163 |\n", + "| time_elapsed | 874 |\n", + "| total_timesteps | 142800 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.75 |\n", + "| n_updates | 3866 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12944 |\n", + "| fps | 163 |\n", + "| time_elapsed | 875 |\n", + "| total_timesteps | 142848 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.34 |\n", + "| n_updates | 3868 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12948 |\n", + "| fps | 163 |\n", + "| time_elapsed | 875 |\n", + "| total_timesteps | 142926 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.46 |\n", + "| n_updates | 3872 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12952 |\n", + "| fps | 163 |\n", + "| time_elapsed | 876 |\n", + "| total_timesteps | 142998 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.08 |\n", + "| n_updates | 3875 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12956 |\n", + "| fps | 163 |\n", + "| time_elapsed | 876 |\n", + "| total_timesteps | 143034 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.3 |\n", + "| n_updates | 3876 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12960 |\n", + "| fps | 163 |\n", + "| time_elapsed | 876 |\n", + "| total_timesteps | 143070 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.22 |\n", + "| n_updates | 3878 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12964 |\n", + "| fps | 163 |\n", + "| time_elapsed | 877 |\n", + "| total_timesteps | 143112 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.73 |\n", + "| n_updates | 3879 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12968 |\n", + "| fps | 163 |\n", + "| time_elapsed | 877 |\n", + "| total_timesteps | 143154 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.77 |\n", + "| n_updates | 3881 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12972 |\n", + "| fps | 163 |\n", + "| time_elapsed | 877 |\n", + "| total_timesteps | 143196 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.73 |\n", + "| n_updates | 3883 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12976 |\n", + "| fps | 163 |\n", + "| time_elapsed | 878 |\n", + "| total_timesteps | 143238 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.46 |\n", + "| n_updates | 3885 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12980 |\n", + "| fps | 163 |\n", + "| time_elapsed | 878 |\n", + "| total_timesteps | 143310 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.45 |\n", + "| n_updates | 3888 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12984 |\n", + "| fps | 163 |\n", + "| time_elapsed | 879 |\n", + "| total_timesteps | 143388 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.8 |\n", + "| n_updates | 3891 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12988 |\n", + "| fps | 163 |\n", + "| time_elapsed | 879 |\n", + "| total_timesteps | 143454 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.03 |\n", + "| n_updates | 3894 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12992 |\n", + "| fps | 163 |\n", + "| time_elapsed | 880 |\n", + "| total_timesteps | 143490 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.86 |\n", + "| n_updates | 3895 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 12996 |\n", + "| fps | 162 |\n", + "| time_elapsed | 880 |\n", + "| total_timesteps | 143550 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.95 |\n", + "| n_updates | 3898 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13000 |\n", + "| fps | 162 |\n", + "| time_elapsed | 881 |\n", + "| total_timesteps | 143580 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.15 |\n", + "| n_updates | 3899 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13004 |\n", + "| fps | 162 |\n", + "| time_elapsed | 881 |\n", + "| total_timesteps | 143610 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.9 |\n", + "| n_updates | 3900 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13008 |\n", + "| fps | 162 |\n", + "| time_elapsed | 882 |\n", + "| total_timesteps | 143718 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.66 |\n", + "| n_updates | 3905 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13012 |\n", + "| fps | 162 |\n", + "| time_elapsed | 882 |\n", + "| total_timesteps | 143772 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.86 |\n", + "| n_updates | 3907 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13016 |\n", + "| fps | 162 |\n", + "| time_elapsed | 882 |\n", + "| total_timesteps | 143808 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.81 |\n", + "| n_updates | 3908 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13020 |\n", + "| fps | 162 |\n", + "| time_elapsed | 883 |\n", + "| total_timesteps | 143838 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.01 |\n", + "| n_updates | 3910 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13024 |\n", + "| fps | 162 |\n", + "| time_elapsed | 883 |\n", + "| total_timesteps | 143856 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13028 |\n", + "| fps | 162 |\n", + "| time_elapsed | 883 |\n", + "| total_timesteps | 143898 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2 |\n", + "| n_updates | 3912 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13032 |\n", + "| fps | 162 |\n", + "| time_elapsed | 883 |\n", + "| total_timesteps | 143940 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.93 |\n", + "| n_updates | 3914 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13036 |\n", + "| fps | 162 |\n", + "| time_elapsed | 884 |\n", + "| total_timesteps | 143976 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.94 |\n", + "| n_updates | 3915 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13040 |\n", + "| fps | 162 |\n", + "| time_elapsed | 884 |\n", + "| total_timesteps | 144042 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.18 |\n", + "| n_updates | 3918 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13044 |\n", + "| fps | 162 |\n", + "| time_elapsed | 885 |\n", + "| total_timesteps | 144120 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.8 |\n", + "| n_updates | 3921 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13048 |\n", + "| fps | 162 |\n", + "| time_elapsed | 885 |\n", + "| total_timesteps | 144162 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.76 |\n", + "| n_updates | 3923 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13052 |\n", + "| fps | 162 |\n", + "| time_elapsed | 886 |\n", + "| total_timesteps | 144210 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.73 |\n", + "| n_updates | 3925 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13056 |\n", + "| fps | 162 |\n", + "| time_elapsed | 886 |\n", + "| total_timesteps | 144246 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.37 |\n", + "| n_updates | 3927 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13060 |\n", + "| fps | 162 |\n", + "| time_elapsed | 887 |\n", + "| total_timesteps | 144318 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.27 |\n", + "| n_updates | 3930 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13064 |\n", + "| fps | 162 |\n", + "| time_elapsed | 887 |\n", + "| total_timesteps | 144384 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.83 |\n", + "| n_updates | 3932 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13068 |\n", + "| fps | 162 |\n", + "| time_elapsed | 887 |\n", + "| total_timesteps | 144426 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.18 |\n", + "| n_updates | 3934 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13072 |\n", + "| fps | 162 |\n", + "| time_elapsed | 888 |\n", + "| total_timesteps | 144462 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.41 |\n", + "| n_updates | 3936 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13076 |\n", + "| fps | 162 |\n", + "| time_elapsed | 888 |\n", + "| total_timesteps | 144522 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.68 |\n", + "| n_updates | 3938 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13080 |\n", + "| fps | 162 |\n", + "| time_elapsed | 889 |\n", + "| total_timesteps | 144612 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.14 |\n", + "| n_updates | 3942 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13084 |\n", + "| fps | 162 |\n", + "| time_elapsed | 889 |\n", + "| total_timesteps | 144654 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.19 |\n", + "| n_updates | 3944 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13088 |\n", + "| fps | 162 |\n", + "| time_elapsed | 890 |\n", + "| total_timesteps | 144690 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.32 |\n", + "| n_updates | 3945 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13092 |\n", + "| fps | 162 |\n", + "| time_elapsed | 890 |\n", + "| total_timesteps | 144726 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 3947 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13096 |\n", + "| fps | 162 |\n", + "| time_elapsed | 890 |\n", + "| total_timesteps | 144762 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3 |\n", + "| n_updates | 3948 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13100 |\n", + "| fps | 162 |\n", + "| time_elapsed | 891 |\n", + "| total_timesteps | 144804 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.58 |\n", + "| n_updates | 3950 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13104 |\n", + "| fps | 162 |\n", + "| time_elapsed | 891 |\n", + "| total_timesteps | 144816 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13108 |\n", + "| fps | 162 |\n", + "| time_elapsed | 891 |\n", + "| total_timesteps | 144858 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.04 |\n", + "| n_updates | 3952 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.14 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13112 |\n", + "| fps | 162 |\n", + "| time_elapsed | 891 |\n", + "| total_timesteps | 144924 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.65 |\n", + "| n_updates | 3955 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13116 |\n", + "| fps | 162 |\n", + "| time_elapsed | 892 |\n", + "| total_timesteps | 144966 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.85 |\n", + "| n_updates | 3957 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13120 |\n", + "| fps | 162 |\n", + "| time_elapsed | 892 |\n", + "| total_timesteps | 145020 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.96 |\n", + "| n_updates | 3959 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13124 |\n", + "| fps | 162 |\n", + "| time_elapsed | 892 |\n", + "| total_timesteps | 145050 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.73 |\n", + "| n_updates | 3960 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13128 |\n", + "| fps | 162 |\n", + "| time_elapsed | 893 |\n", + "| total_timesteps | 145092 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.07 |\n", + "| n_updates | 3962 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13132 |\n", + "| fps | 162 |\n", + "| time_elapsed | 893 |\n", + "| total_timesteps | 145134 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.99 |\n", + "| n_updates | 3964 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13136 |\n", + "| fps | 162 |\n", + "| time_elapsed | 893 |\n", + "| total_timesteps | 145164 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.87 |\n", + "| n_updates | 3965 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13140 |\n", + "| fps | 162 |\n", + "| time_elapsed | 894 |\n", + "| total_timesteps | 145194 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 3966 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13144 |\n", + "| fps | 162 |\n", + "| time_elapsed | 894 |\n", + "| total_timesteps | 145224 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.66 |\n", + "| n_updates | 3967 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13148 |\n", + "| fps | 162 |\n", + "| time_elapsed | 894 |\n", + "| total_timesteps | 145260 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.77 |\n", + "| n_updates | 3969 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13152 |\n", + "| fps | 162 |\n", + "| time_elapsed | 895 |\n", + "| total_timesteps | 145302 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.99 |\n", + "| n_updates | 3971 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13156 |\n", + "| fps | 162 |\n", + "| time_elapsed | 895 |\n", + "| total_timesteps | 145308 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13160 |\n", + "| fps | 162 |\n", + "| time_elapsed | 895 |\n", + "| total_timesteps | 145350 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.05 |\n", + "| n_updates | 3973 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13164 |\n", + "| fps | 162 |\n", + "| time_elapsed | 895 |\n", + "| total_timesteps | 145404 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.52 |\n", + "| n_updates | 3975 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13168 |\n", + "| fps | 162 |\n", + "| time_elapsed | 896 |\n", + "| total_timesteps | 145440 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 3976 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13172 |\n", + "| fps | 162 |\n", + "| time_elapsed | 896 |\n", + "| total_timesteps | 145476 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 3978 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13176 |\n", + "| fps | 162 |\n", + "| time_elapsed | 896 |\n", + "| total_timesteps | 145536 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 3980 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13180 |\n", + "| fps | 162 |\n", + "| time_elapsed | 897 |\n", + "| total_timesteps | 145566 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 3982 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13184 |\n", + "| fps | 162 |\n", + "| time_elapsed | 897 |\n", + "| total_timesteps | 145620 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.38 |\n", + "| n_updates | 3984 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13188 |\n", + "| fps | 162 |\n", + "| time_elapsed | 898 |\n", + "| total_timesteps | 145662 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 3986 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13192 |\n", + "| fps | 162 |\n", + "| time_elapsed | 898 |\n", + "| total_timesteps | 145692 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.77 |\n", + "| n_updates | 3987 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13196 |\n", + "| fps | 162 |\n", + "| time_elapsed | 898 |\n", + "| total_timesteps | 145722 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.68 |\n", + "| n_updates | 3988 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13200 |\n", + "| fps | 162 |\n", + "| time_elapsed | 899 |\n", + "| total_timesteps | 145782 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.8 |\n", + "| n_updates | 3991 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13204 |\n", + "| fps | 162 |\n", + "| time_elapsed | 899 |\n", + "| total_timesteps | 145800 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13208 |\n", + "| fps | 162 |\n", + "| time_elapsed | 899 |\n", + "| total_timesteps | 145824 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.18 |\n", + "| n_updates | 3992 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13212 |\n", + "| fps | 162 |\n", + "| time_elapsed | 899 |\n", + "| total_timesteps | 145890 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.78 |\n", + "| n_updates | 3995 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13216 |\n", + "| fps | 162 |\n", + "| time_elapsed | 900 |\n", + "| total_timesteps | 145908 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.74 |\n", + "| n_updates | 3996 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13220 |\n", + "| fps | 162 |\n", + "| time_elapsed | 900 |\n", + "| total_timesteps | 145932 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 3997 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13224 |\n", + "| fps | 162 |\n", + "| time_elapsed | 900 |\n", + "| total_timesteps | 145962 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 3998 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13228 |\n", + "| fps | 162 |\n", + "| time_elapsed | 900 |\n", + "| total_timesteps | 146010 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.99 |\n", + "| n_updates | 4000 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13232 |\n", + "| fps | 162 |\n", + "| time_elapsed | 901 |\n", + "| total_timesteps | 146052 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.66 |\n", + "| n_updates | 4002 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13236 |\n", + "| fps | 162 |\n", + "| time_elapsed | 901 |\n", + "| total_timesteps | 146088 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.38 |\n", + "| n_updates | 4003 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13240 |\n", + "| fps | 162 |\n", + "| time_elapsed | 901 |\n", + "| total_timesteps | 146124 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.74 |\n", + "| n_updates | 4005 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13244 |\n", + "| fps | 161 |\n", + "| time_elapsed | 902 |\n", + "| total_timesteps | 146178 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.04 |\n", + "| n_updates | 4007 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13248 |\n", + "| fps | 161 |\n", + "| time_elapsed | 902 |\n", + "| total_timesteps | 146214 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.99 |\n", + "| n_updates | 4009 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13252 |\n", + "| fps | 161 |\n", + "| time_elapsed | 902 |\n", + "| total_timesteps | 146238 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 4010 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13256 |\n", + "| fps | 161 |\n", + "| time_elapsed | 903 |\n", + "| total_timesteps | 146304 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.06 |\n", + "| n_updates | 4012 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13260 |\n", + "| fps | 161 |\n", + "| time_elapsed | 903 |\n", + "| total_timesteps | 146334 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.2 |\n", + "| n_updates | 4014 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13264 |\n", + "| fps | 161 |\n", + "| time_elapsed | 903 |\n", + "| total_timesteps | 146358 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.96 |\n", + "| n_updates | 4015 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13268 |\n", + "| fps | 161 |\n", + "| time_elapsed | 904 |\n", + "| total_timesteps | 146370 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13272 |\n", + "| fps | 161 |\n", + "| time_elapsed | 904 |\n", + "| total_timesteps | 146406 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.11 |\n", + "| n_updates | 4017 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13276 |\n", + "| fps | 161 |\n", + "| time_elapsed | 904 |\n", + "| total_timesteps | 146448 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.39 |\n", + "| n_updates | 4018 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13280 |\n", + "| fps | 161 |\n", + "| time_elapsed | 905 |\n", + "| total_timesteps | 146496 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.11 |\n", + "| n_updates | 4020 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13284 |\n", + "| fps | 161 |\n", + "| time_elapsed | 905 |\n", + "| total_timesteps | 146538 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.75 |\n", + "| n_updates | 4022 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13288 |\n", + "| fps | 161 |\n", + "| time_elapsed | 905 |\n", + "| total_timesteps | 146568 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 4023 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13292 |\n", + "| fps | 161 |\n", + "| time_elapsed | 906 |\n", + "| total_timesteps | 146682 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 4028 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13296 |\n", + "| fps | 161 |\n", + "| time_elapsed | 907 |\n", + "| total_timesteps | 146748 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.54 |\n", + "| n_updates | 4031 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13300 |\n", + "| fps | 161 |\n", + "| time_elapsed | 907 |\n", + "| total_timesteps | 146778 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.84 |\n", + "| n_updates | 4032 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13304 |\n", + "| fps | 161 |\n", + "| time_elapsed | 907 |\n", + "| total_timesteps | 146802 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.04 |\n", + "| n_updates | 4033 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13308 |\n", + "| fps | 161 |\n", + "| time_elapsed | 907 |\n", + "| total_timesteps | 146826 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.94 |\n", + "| n_updates | 4034 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13312 |\n", + "| fps | 161 |\n", + "| time_elapsed | 908 |\n", + "| total_timesteps | 146892 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.69 |\n", + "| n_updates | 4037 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13316 |\n", + "| fps | 161 |\n", + "| time_elapsed | 908 |\n", + "| total_timesteps | 146940 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.82 |\n", + "| n_updates | 4039 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13320 |\n", + "| fps | 161 |\n", + "| time_elapsed | 909 |\n", + "| total_timesteps | 146982 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.76 |\n", + "| n_updates | 4041 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13324 |\n", + "| fps | 161 |\n", + "| time_elapsed | 909 |\n", + "| total_timesteps | 147012 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.94 |\n", + "| n_updates | 4042 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13328 |\n", + "| fps | 161 |\n", + "| time_elapsed | 909 |\n", + "| total_timesteps | 147048 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.05 |\n", + "| n_updates | 4043 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13332 |\n", + "| fps | 161 |\n", + "| time_elapsed | 909 |\n", + "| total_timesteps | 147066 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.8 |\n", + "| n_updates | 4044 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13336 |\n", + "| fps | 161 |\n", + "| time_elapsed | 910 |\n", + "| total_timesteps | 147138 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.62 |\n", + "| n_updates | 4047 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13340 |\n", + "| fps | 161 |\n", + "| time_elapsed | 910 |\n", + "| total_timesteps | 147204 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.12 |\n", + "| n_updates | 4050 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13344 |\n", + "| fps | 161 |\n", + "| time_elapsed | 911 |\n", + "| total_timesteps | 147240 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.48 |\n", + "| n_updates | 4051 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13348 |\n", + "| fps | 161 |\n", + "| time_elapsed | 911 |\n", + "| total_timesteps | 147276 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.55 |\n", + "| n_updates | 4053 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13352 |\n", + "| fps | 161 |\n", + "| time_elapsed | 911 |\n", + "| total_timesteps | 147318 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.12 |\n", + "| n_updates | 4055 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13356 |\n", + "| fps | 161 |\n", + "| time_elapsed | 912 |\n", + "| total_timesteps | 147360 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.83 |\n", + "| n_updates | 4056 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13360 |\n", + "| fps | 161 |\n", + "| time_elapsed | 912 |\n", + "| total_timesteps | 147396 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.29 |\n", + "| n_updates | 4058 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13364 |\n", + "| fps | 161 |\n", + "| time_elapsed | 912 |\n", + "| total_timesteps | 147456 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.88 |\n", + "| n_updates | 4060 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13368 |\n", + "| fps | 161 |\n", + "| time_elapsed | 913 |\n", + "| total_timesteps | 147498 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.75 |\n", + "| n_updates | 4062 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13372 |\n", + "| fps | 161 |\n", + "| time_elapsed | 913 |\n", + "| total_timesteps | 147552 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.55 |\n", + "| n_updates | 4064 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13376 |\n", + "| fps | 161 |\n", + "| time_elapsed | 914 |\n", + "| total_timesteps | 147588 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.7 |\n", + "| n_updates | 4066 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13380 |\n", + "| fps | 161 |\n", + "| time_elapsed | 914 |\n", + "| total_timesteps | 147654 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.18 |\n", + "| n_updates | 4069 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13384 |\n", + "| fps | 161 |\n", + "| time_elapsed | 915 |\n", + "| total_timesteps | 147696 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.37 |\n", + "| n_updates | 4070 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13388 |\n", + "| fps | 161 |\n", + "| time_elapsed | 916 |\n", + "| total_timesteps | 147834 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.52 |\n", + "| n_updates | 4076 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13392 |\n", + "| fps | 161 |\n", + "| time_elapsed | 916 |\n", + "| total_timesteps | 147870 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.28 |\n", + "| n_updates | 4078 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13396 |\n", + "| fps | 161 |\n", + "| time_elapsed | 916 |\n", + "| total_timesteps | 147894 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.97 |\n", + "| n_updates | 4079 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13400 |\n", + "| fps | 161 |\n", + "| time_elapsed | 916 |\n", + "| total_timesteps | 147918 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.74 |\n", + "| n_updates | 4080 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13404 |\n", + "| fps | 161 |\n", + "| time_elapsed | 917 |\n", + "| total_timesteps | 147948 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.26 |\n", + "| n_updates | 4081 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13408 |\n", + "| fps | 161 |\n", + "| time_elapsed | 917 |\n", + "| total_timesteps | 147990 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.64 |\n", + "| n_updates | 4083 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13412 |\n", + "| fps | 161 |\n", + "| time_elapsed | 917 |\n", + "| total_timesteps | 148068 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.88 |\n", + "| n_updates | 4086 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13416 |\n", + "| fps | 161 |\n", + "| time_elapsed | 918 |\n", + "| total_timesteps | 148110 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.88 |\n", + "| n_updates | 4088 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13420 |\n", + "| fps | 161 |\n", + "| time_elapsed | 918 |\n", + "| total_timesteps | 148116 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13424 |\n", + "| fps | 161 |\n", + "| time_elapsed | 919 |\n", + "| total_timesteps | 148182 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.01 |\n", + "| n_updates | 4091 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13428 |\n", + "| fps | 161 |\n", + "| time_elapsed | 919 |\n", + "| total_timesteps | 148200 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.17 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13432 |\n", + "| fps | 161 |\n", + "| time_elapsed | 919 |\n", + "| total_timesteps | 148224 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.74 |\n", + "| n_updates | 4092 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13436 |\n", + "| fps | 161 |\n", + "| time_elapsed | 919 |\n", + "| total_timesteps | 148254 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.73 |\n", + "| n_updates | 4094 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13440 |\n", + "| fps | 161 |\n", + "| time_elapsed | 919 |\n", + "| total_timesteps | 148284 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.69 |\n", + "| n_updates | 4095 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.15 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13444 |\n", + "| fps | 161 |\n", + "| time_elapsed | 920 |\n", + "| total_timesteps | 148308 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.05 |\n", + "| n_updates | 4096 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13448 |\n", + "| fps | 161 |\n", + "| time_elapsed | 920 |\n", + "| total_timesteps | 148338 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.55 |\n", + "| n_updates | 4097 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13452 |\n", + "| fps | 161 |\n", + "| time_elapsed | 920 |\n", + "| total_timesteps | 148380 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.7 |\n", + "| n_updates | 4099 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13456 |\n", + "| fps | 161 |\n", + "| time_elapsed | 921 |\n", + "| total_timesteps | 148398 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 4100 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13460 |\n", + "| fps | 161 |\n", + "| time_elapsed | 921 |\n", + "| total_timesteps | 148434 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.8 |\n", + "| n_updates | 4101 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13464 |\n", + "| fps | 161 |\n", + "| time_elapsed | 921 |\n", + "| total_timesteps | 148470 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.89 |\n", + "| n_updates | 4103 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13468 |\n", + "| fps | 161 |\n", + "| time_elapsed | 922 |\n", + "| total_timesteps | 148506 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.09 |\n", + "| n_updates | 4104 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13472 |\n", + "| fps | 161 |\n", + "| time_elapsed | 922 |\n", + "| total_timesteps | 148530 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.75 |\n", + "| n_updates | 4105 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13476 |\n", + "| fps | 161 |\n", + "| time_elapsed | 922 |\n", + "| total_timesteps | 148566 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.69 |\n", + "| n_updates | 4107 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13480 |\n", + "| fps | 161 |\n", + "| time_elapsed | 922 |\n", + "| total_timesteps | 148596 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.87 |\n", + "| n_updates | 4108 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13484 |\n", + "| fps | 161 |\n", + "| time_elapsed | 923 |\n", + "| total_timesteps | 148632 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.66 |\n", + "| n_updates | 4109 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13488 |\n", + "| fps | 161 |\n", + "| time_elapsed | 923 |\n", + "| total_timesteps | 148656 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.73 |\n", + "| n_updates | 4110 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13492 |\n", + "| fps | 160 |\n", + "| time_elapsed | 923 |\n", + "| total_timesteps | 148686 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.02 |\n", + "| n_updates | 4112 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13496 |\n", + "| fps | 160 |\n", + "| time_elapsed | 923 |\n", + "| total_timesteps | 148710 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.4 |\n", + "| n_updates | 4113 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13500 |\n", + "| fps | 160 |\n", + "| time_elapsed | 924 |\n", + "| total_timesteps | 148740 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.2 |\n", + "| n_updates | 4114 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13504 |\n", + "| fps | 160 |\n", + "| time_elapsed | 924 |\n", + "| total_timesteps | 148776 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 4115 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13508 |\n", + "| fps | 160 |\n", + "| time_elapsed | 924 |\n", + "| total_timesteps | 148818 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 4117 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13512 |\n", + "| fps | 160 |\n", + "| time_elapsed | 924 |\n", + "| total_timesteps | 148854 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.01 |\n", + "| n_updates | 4119 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13516 |\n", + "| fps | 160 |\n", + "| time_elapsed | 925 |\n", + "| total_timesteps | 148890 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.06 |\n", + "| n_updates | 4120 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13520 |\n", + "| fps | 160 |\n", + "| time_elapsed | 925 |\n", + "| total_timesteps | 148926 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.51 |\n", + "| n_updates | 4122 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13524 |\n", + "| fps | 160 |\n", + "| time_elapsed | 925 |\n", + "| total_timesteps | 148962 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 4123 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13528 |\n", + "| fps | 160 |\n", + "| time_elapsed | 926 |\n", + "| total_timesteps | 148992 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5 |\n", + "| n_updates | 4124 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13532 |\n", + "| fps | 160 |\n", + "| time_elapsed | 926 |\n", + "| total_timesteps | 149016 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.59 |\n", + "| n_updates | 4125 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13536 |\n", + "| fps | 160 |\n", + "| time_elapsed | 926 |\n", + "| total_timesteps | 149058 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.87 |\n", + "| n_updates | 4127 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13540 |\n", + "| fps | 160 |\n", + "| time_elapsed | 927 |\n", + "| total_timesteps | 149124 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 4130 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13544 |\n", + "| fps | 160 |\n", + "| time_elapsed | 927 |\n", + "| total_timesteps | 149142 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.14 |\n", + "| n_updates | 4131 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13548 |\n", + "| fps | 160 |\n", + "| time_elapsed | 927 |\n", + "| total_timesteps | 149160 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13552 |\n", + "| fps | 160 |\n", + "| time_elapsed | 927 |\n", + "| total_timesteps | 149196 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.35 |\n", + "| n_updates | 4133 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13556 |\n", + "| fps | 160 |\n", + "| time_elapsed | 928 |\n", + "| total_timesteps | 149226 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.36 |\n", + "| n_updates | 4134 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13560 |\n", + "| fps | 160 |\n", + "| time_elapsed | 928 |\n", + "| total_timesteps | 149244 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.73 |\n", + "| n_updates | 4135 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13564 |\n", + "| fps | 160 |\n", + "| time_elapsed | 928 |\n", + "| total_timesteps | 149280 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.67 |\n", + "| n_updates | 4136 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13568 |\n", + "| fps | 160 |\n", + "| time_elapsed | 929 |\n", + "| total_timesteps | 149388 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.54 |\n", + "| n_updates | 4141 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13572 |\n", + "| fps | 160 |\n", + "| time_elapsed | 929 |\n", + "| total_timesteps | 149436 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.76 |\n", + "| n_updates | 4143 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13576 |\n", + "| fps | 160 |\n", + "| time_elapsed | 930 |\n", + "| total_timesteps | 149472 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.13 |\n", + "| n_updates | 4144 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13580 |\n", + "| fps | 160 |\n", + "| time_elapsed | 930 |\n", + "| total_timesteps | 149508 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.74 |\n", + "| n_updates | 4146 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13584 |\n", + "| fps | 160 |\n", + "| time_elapsed | 930 |\n", + "| total_timesteps | 149526 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.78 |\n", + "| n_updates | 4147 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13588 |\n", + "| fps | 160 |\n", + "| time_elapsed | 930 |\n", + "| total_timesteps | 149550 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.02 |\n", + "| n_updates | 4148 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13592 |\n", + "| fps | 160 |\n", + "| time_elapsed | 931 |\n", + "| total_timesteps | 149586 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.08 |\n", + "| n_updates | 4149 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13596 |\n", + "| fps | 160 |\n", + "| time_elapsed | 931 |\n", + "| total_timesteps | 149640 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.94 |\n", + "| n_updates | 4151 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13600 |\n", + "| fps | 160 |\n", + "| time_elapsed | 932 |\n", + "| total_timesteps | 149748 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.08 |\n", + "| n_updates | 4156 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13604 |\n", + "| fps | 160 |\n", + "| time_elapsed | 932 |\n", + "| total_timesteps | 149790 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.58 |\n", + "| n_updates | 4158 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13608 |\n", + "| fps | 160 |\n", + "| time_elapsed | 932 |\n", + "| total_timesteps | 149820 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.99 |\n", + "| n_updates | 4159 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13612 |\n", + "| fps | 160 |\n", + "| time_elapsed | 933 |\n", + "| total_timesteps | 149856 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.12 |\n", + "| n_updates | 4160 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13616 |\n", + "| fps | 160 |\n", + "| time_elapsed | 933 |\n", + "| total_timesteps | 149886 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.12 |\n", + "| n_updates | 4162 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13620 |\n", + "| fps | 160 |\n", + "| time_elapsed | 933 |\n", + "| total_timesteps | 149922 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.31 |\n", + "| n_updates | 4163 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13624 |\n", + "| fps | 160 |\n", + "| time_elapsed | 934 |\n", + "| total_timesteps | 149964 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.59 |\n", + "| n_updates | 4165 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13628 |\n", + "| fps | 160 |\n", + "| time_elapsed | 934 |\n", + "| total_timesteps | 150024 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.13 |\n", + "| n_updates | 4167 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13632 |\n", + "| fps | 160 |\n", + "| time_elapsed | 934 |\n", + "| total_timesteps | 150054 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.69 |\n", + "| n_updates | 4169 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13636 |\n", + "| fps | 160 |\n", + "| time_elapsed | 935 |\n", + "| total_timesteps | 150096 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.71 |\n", + "| n_updates | 4170 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13640 |\n", + "| fps | 160 |\n", + "| time_elapsed | 935 |\n", + "| total_timesteps | 150132 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.12 |\n", + "| n_updates | 4172 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13644 |\n", + "| fps | 160 |\n", + "| time_elapsed | 935 |\n", + "| total_timesteps | 150162 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.45 |\n", + "| n_updates | 4173 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13648 |\n", + "| fps | 160 |\n", + "| time_elapsed | 936 |\n", + "| total_timesteps | 150204 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.08 |\n", + "| n_updates | 4175 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13652 |\n", + "| fps | 160 |\n", + "| time_elapsed | 936 |\n", + "| total_timesteps | 150246 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.49 |\n", + "| n_updates | 4177 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13656 |\n", + "| fps | 160 |\n", + "| time_elapsed | 936 |\n", + "| total_timesteps | 150294 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.47 |\n", + "| n_updates | 4179 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13660 |\n", + "| fps | 160 |\n", + "| time_elapsed | 937 |\n", + "| total_timesteps | 150336 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 4180 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13664 |\n", + "| fps | 160 |\n", + "| time_elapsed | 937 |\n", + "| total_timesteps | 150372 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.99 |\n", + "| n_updates | 4182 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13668 |\n", + "| fps | 160 |\n", + "| time_elapsed | 937 |\n", + "| total_timesteps | 150420 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.64 |\n", + "| n_updates | 4184 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13672 |\n", + "| fps | 160 |\n", + "| time_elapsed | 938 |\n", + "| total_timesteps | 150462 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.14 |\n", + "| n_updates | 4186 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13676 |\n", + "| fps | 160 |\n", + "| time_elapsed | 938 |\n", + "| total_timesteps | 150504 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 4187 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13680 |\n", + "| fps | 160 |\n", + "| time_elapsed | 939 |\n", + "| total_timesteps | 150558 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.06 |\n", + "| n_updates | 4190 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13684 |\n", + "| fps | 160 |\n", + "| time_elapsed | 939 |\n", + "| total_timesteps | 150600 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.82 |\n", + "| n_updates | 4191 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13688 |\n", + "| fps | 160 |\n", + "| time_elapsed | 939 |\n", + "| total_timesteps | 150648 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 4193 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13692 |\n", + "| fps | 160 |\n", + "| time_elapsed | 940 |\n", + "| total_timesteps | 150720 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.79 |\n", + "| n_updates | 4196 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13696 |\n", + "| fps | 160 |\n", + "| time_elapsed | 940 |\n", + "| total_timesteps | 150774 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.41 |\n", + "| n_updates | 4199 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13700 |\n", + "| fps | 160 |\n", + "| time_elapsed | 940 |\n", + "| total_timesteps | 150816 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.24 |\n", + "| n_updates | 4200 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13704 |\n", + "| fps | 160 |\n", + "| time_elapsed | 941 |\n", + "| total_timesteps | 150852 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.64 |\n", + "| n_updates | 4202 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13708 |\n", + "| fps | 160 |\n", + "| time_elapsed | 941 |\n", + "| total_timesteps | 150900 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.61 |\n", + "| n_updates | 4204 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13712 |\n", + "| fps | 160 |\n", + "| time_elapsed | 942 |\n", + "| total_timesteps | 150954 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.02 |\n", + "| n_updates | 4206 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13716 |\n", + "| fps | 160 |\n", + "| time_elapsed | 942 |\n", + "| total_timesteps | 151020 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.18 |\n", + "| n_updates | 4209 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13720 |\n", + "| fps | 160 |\n", + "| time_elapsed | 942 |\n", + "| total_timesteps | 151032 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13724 |\n", + "| fps | 160 |\n", + "| time_elapsed | 943 |\n", + "| total_timesteps | 151074 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.63 |\n", + "| n_updates | 4211 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13728 |\n", + "| fps | 160 |\n", + "| time_elapsed | 943 |\n", + "| total_timesteps | 151110 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.69 |\n", + "| n_updates | 4213 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13732 |\n", + "| fps | 160 |\n", + "| time_elapsed | 943 |\n", + "| total_timesteps | 151134 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.59 |\n", + "| n_updates | 4214 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13736 |\n", + "| fps | 160 |\n", + "| time_elapsed | 944 |\n", + "| total_timesteps | 151188 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.3 |\n", + "| n_updates | 4216 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13740 |\n", + "| fps | 160 |\n", + "| time_elapsed | 944 |\n", + "| total_timesteps | 151254 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.5 |\n", + "| n_updates | 4219 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13744 |\n", + "| fps | 160 |\n", + "| time_elapsed | 945 |\n", + "| total_timesteps | 151314 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.3 |\n", + "| n_updates | 4221 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13748 |\n", + "| fps | 160 |\n", + "| time_elapsed | 945 |\n", + "| total_timesteps | 151362 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.51 |\n", + "| n_updates | 4223 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13752 |\n", + "| fps | 160 |\n", + "| time_elapsed | 945 |\n", + "| total_timesteps | 151386 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.67 |\n", + "| n_updates | 4224 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13756 |\n", + "| fps | 160 |\n", + "| time_elapsed | 946 |\n", + "| total_timesteps | 151440 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.77 |\n", + "| n_updates | 4226 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13760 |\n", + "| fps | 160 |\n", + "| time_elapsed | 946 |\n", + "| total_timesteps | 151482 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.64 |\n", + "| n_updates | 4228 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13764 |\n", + "| fps | 160 |\n", + "| time_elapsed | 947 |\n", + "| total_timesteps | 151554 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.54 |\n", + "| n_updates | 4231 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13768 |\n", + "| fps | 159 |\n", + "| time_elapsed | 947 |\n", + "| total_timesteps | 151590 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.24 |\n", + "| n_updates | 4233 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13772 |\n", + "| fps | 159 |\n", + "| time_elapsed | 947 |\n", + "| total_timesteps | 151626 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.1 |\n", + "| n_updates | 4234 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13776 |\n", + "| fps | 159 |\n", + "| time_elapsed | 948 |\n", + "| total_timesteps | 151656 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.09 |\n", + "| n_updates | 4235 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13780 |\n", + "| fps | 159 |\n", + "| time_elapsed | 948 |\n", + "| total_timesteps | 151686 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.16 |\n", + "| n_updates | 4237 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13784 |\n", + "| fps | 159 |\n", + "| time_elapsed | 948 |\n", + "| total_timesteps | 151740 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.62 |\n", + "| n_updates | 4239 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13788 |\n", + "| fps | 159 |\n", + "| time_elapsed | 949 |\n", + "| total_timesteps | 151806 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.31 |\n", + "| n_updates | 4242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13792 |\n", + "| fps | 159 |\n", + "| time_elapsed | 949 |\n", + "| total_timesteps | 151836 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.34 |\n", + "| n_updates | 4243 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13796 |\n", + "| fps | 159 |\n", + "| time_elapsed | 949 |\n", + "| total_timesteps | 151860 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.64 |\n", + "| n_updates | 4244 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13800 |\n", + "| fps | 159 |\n", + "| time_elapsed | 950 |\n", + "| total_timesteps | 151908 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.63 |\n", + "| n_updates | 4246 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13804 |\n", + "| fps | 159 |\n", + "| time_elapsed | 950 |\n", + "| total_timesteps | 151980 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.61 |\n", + "| n_updates | 4249 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13808 |\n", + "| fps | 159 |\n", + "| time_elapsed | 951 |\n", + "| total_timesteps | 152052 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.53 |\n", + "| n_updates | 4252 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13812 |\n", + "| fps | 159 |\n", + "| time_elapsed | 951 |\n", + "| total_timesteps | 152082 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.02 |\n", + "| n_updates | 4253 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13816 |\n", + "| fps | 159 |\n", + "| time_elapsed | 951 |\n", + "| total_timesteps | 152118 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.62 |\n", + "| n_updates | 4255 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13820 |\n", + "| fps | 159 |\n", + "| time_elapsed | 952 |\n", + "| total_timesteps | 152160 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.02 |\n", + "| n_updates | 4256 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13824 |\n", + "| fps | 159 |\n", + "| time_elapsed | 952 |\n", + "| total_timesteps | 152202 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.44 |\n", + "| n_updates | 4258 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13828 |\n", + "| fps | 159 |\n", + "| time_elapsed | 952 |\n", + "| total_timesteps | 152250 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.43 |\n", + "| n_updates | 4260 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13832 |\n", + "| fps | 159 |\n", + "| time_elapsed | 953 |\n", + "| total_timesteps | 152286 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.43 |\n", + "| n_updates | 4262 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13836 |\n", + "| fps | 159 |\n", + "| time_elapsed | 953 |\n", + "| total_timesteps | 152322 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.08 |\n", + "| n_updates | 4263 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13840 |\n", + "| fps | 159 |\n", + "| time_elapsed | 953 |\n", + "| total_timesteps | 152358 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 4265 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13844 |\n", + "| fps | 159 |\n", + "| time_elapsed | 954 |\n", + "| total_timesteps | 152448 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.83 |\n", + "| n_updates | 4268 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13848 |\n", + "| fps | 159 |\n", + "| time_elapsed | 955 |\n", + "| total_timesteps | 152514 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.65 |\n", + "| n_updates | 4271 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13852 |\n", + "| fps | 159 |\n", + "| time_elapsed | 955 |\n", + "| total_timesteps | 152532 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.17 |\n", + "| n_updates | 4272 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13856 |\n", + "| fps | 159 |\n", + "| time_elapsed | 955 |\n", + "| total_timesteps | 152574 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.03 |\n", + "| n_updates | 4274 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13860 |\n", + "| fps | 159 |\n", + "| time_elapsed | 956 |\n", + "| total_timesteps | 152634 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.5 |\n", + "| n_updates | 4276 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13864 |\n", + "| fps | 159 |\n", + "| time_elapsed | 956 |\n", + "| total_timesteps | 152688 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 4278 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13868 |\n", + "| fps | 159 |\n", + "| time_elapsed | 956 |\n", + "| total_timesteps | 152718 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.58 |\n", + "| n_updates | 4280 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13872 |\n", + "| fps | 159 |\n", + "| time_elapsed | 957 |\n", + "| total_timesteps | 152766 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.71 |\n", + "| n_updates | 4282 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13876 |\n", + "| fps | 159 |\n", + "| time_elapsed | 957 |\n", + "| total_timesteps | 152796 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.93 |\n", + "| n_updates | 4283 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13880 |\n", + "| fps | 159 |\n", + "| time_elapsed | 957 |\n", + "| total_timesteps | 152814 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.73 |\n", + "| n_updates | 4284 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13884 |\n", + "| fps | 159 |\n", + "| time_elapsed | 957 |\n", + "| total_timesteps | 152844 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.01 |\n", + "| n_updates | 4285 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13888 |\n", + "| fps | 159 |\n", + "| time_elapsed | 958 |\n", + "| total_timesteps | 152874 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.48 |\n", + "| n_updates | 4286 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13892 |\n", + "| fps | 159 |\n", + "| time_elapsed | 958 |\n", + "| total_timesteps | 152934 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.36 |\n", + "| n_updates | 4289 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13896 |\n", + "| fps | 159 |\n", + "| time_elapsed | 958 |\n", + "| total_timesteps | 152964 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 4290 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13900 |\n", + "| fps | 159 |\n", + "| time_elapsed | 959 |\n", + "| total_timesteps | 152994 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.84 |\n", + "| n_updates | 4291 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13904 |\n", + "| fps | 159 |\n", + "| time_elapsed | 959 |\n", + "| total_timesteps | 153030 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.03 |\n", + "| n_updates | 4293 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13908 |\n", + "| fps | 159 |\n", + "| time_elapsed | 959 |\n", + "| total_timesteps | 153060 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.05 |\n", + "| n_updates | 4294 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13912 |\n", + "| fps | 159 |\n", + "| time_elapsed | 959 |\n", + "| total_timesteps | 153072 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13916 |\n", + "| fps | 159 |\n", + "| time_elapsed | 960 |\n", + "| total_timesteps | 153102 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.4 |\n", + "| n_updates | 4296 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13920 |\n", + "| fps | 159 |\n", + "| time_elapsed | 960 |\n", + "| total_timesteps | 153132 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.52 |\n", + "| n_updates | 4297 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13924 |\n", + "| fps | 159 |\n", + "| time_elapsed | 960 |\n", + "| total_timesteps | 153162 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.34 |\n", + "| n_updates | 4298 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13928 |\n", + "| fps | 159 |\n", + "| time_elapsed | 960 |\n", + "| total_timesteps | 153204 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.74 |\n", + "| n_updates | 4300 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13932 |\n", + "| fps | 159 |\n", + "| time_elapsed | 961 |\n", + "| total_timesteps | 153234 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.87 |\n", + "| n_updates | 4301 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13936 |\n", + "| fps | 159 |\n", + "| time_elapsed | 961 |\n", + "| total_timesteps | 153288 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.75 |\n", + "| n_updates | 4303 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13940 |\n", + "| fps | 159 |\n", + "| time_elapsed | 961 |\n", + "| total_timesteps | 153324 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.02 |\n", + "| n_updates | 4305 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13944 |\n", + "| fps | 159 |\n", + "| time_elapsed | 962 |\n", + "| total_timesteps | 153378 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.56 |\n", + "| n_updates | 4307 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13948 |\n", + "| fps | 159 |\n", + "| time_elapsed | 962 |\n", + "| total_timesteps | 153456 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.98 |\n", + "| n_updates | 4310 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13952 |\n", + "| fps | 159 |\n", + "| time_elapsed | 963 |\n", + "| total_timesteps | 153504 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.85 |\n", + "| n_updates | 4312 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13956 |\n", + "| fps | 159 |\n", + "| time_elapsed | 963 |\n", + "| total_timesteps | 153558 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.3 |\n", + "| n_updates | 4315 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13960 |\n", + "| fps | 159 |\n", + "| time_elapsed | 964 |\n", + "| total_timesteps | 153606 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.28 |\n", + "| n_updates | 4317 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13964 |\n", + "| fps | 159 |\n", + "| time_elapsed | 964 |\n", + "| total_timesteps | 153672 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.36 |\n", + "| n_updates | 4319 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13968 |\n", + "| fps | 159 |\n", + "| time_elapsed | 965 |\n", + "| total_timesteps | 153720 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.29 |\n", + "| n_updates | 4321 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13972 |\n", + "| fps | 159 |\n", + "| time_elapsed | 965 |\n", + "| total_timesteps | 153774 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.53 |\n", + "| n_updates | 4324 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13976 |\n", + "| fps | 159 |\n", + "| time_elapsed | 965 |\n", + "| total_timesteps | 153840 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.88 |\n", + "| n_updates | 4326 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13980 |\n", + "| fps | 159 |\n", + "| time_elapsed | 966 |\n", + "| total_timesteps | 153888 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.79 |\n", + "| n_updates | 4328 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13984 |\n", + "| fps | 159 |\n", + "| time_elapsed | 966 |\n", + "| total_timesteps | 153924 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.07 |\n", + "| n_updates | 4330 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13988 |\n", + "| fps | 159 |\n", + "| time_elapsed | 966 |\n", + "| total_timesteps | 153960 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.94 |\n", + "| n_updates | 4331 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13992 |\n", + "| fps | 159 |\n", + "| time_elapsed | 967 |\n", + "| total_timesteps | 153990 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.32 |\n", + "| n_updates | 4333 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 13996 |\n", + "| fps | 159 |\n", + "| time_elapsed | 967 |\n", + "| total_timesteps | 154020 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.34 |\n", + "| n_updates | 4334 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14000 |\n", + "| fps | 159 |\n", + "| time_elapsed | 967 |\n", + "| total_timesteps | 154044 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.68 |\n", + "| n_updates | 4335 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14004 |\n", + "| fps | 159 |\n", + "| time_elapsed | 967 |\n", + "| total_timesteps | 154062 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.24 |\n", + "| n_updates | 4336 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14008 |\n", + "| fps | 159 |\n", + "| time_elapsed | 968 |\n", + "| total_timesteps | 154104 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.52 |\n", + "| n_updates | 4337 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14012 |\n", + "| fps | 159 |\n", + "| time_elapsed | 968 |\n", + "| total_timesteps | 154140 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.49 |\n", + "| n_updates | 4339 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14016 |\n", + "| fps | 159 |\n", + "| time_elapsed | 968 |\n", + "| total_timesteps | 154194 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.36 |\n", + "| n_updates | 4341 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14020 |\n", + "| fps | 159 |\n", + "| time_elapsed | 969 |\n", + "| total_timesteps | 154230 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.53 |\n", + "| n_updates | 4343 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14024 |\n", + "| fps | 159 |\n", + "| time_elapsed | 969 |\n", + "| total_timesteps | 154278 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.56 |\n", + "| n_updates | 4345 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14028 |\n", + "| fps | 159 |\n", + "| time_elapsed | 970 |\n", + "| total_timesteps | 154326 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.74 |\n", + "| n_updates | 4347 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14032 |\n", + "| fps | 159 |\n", + "| time_elapsed | 970 |\n", + "| total_timesteps | 154368 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.98 |\n", + "| n_updates | 4348 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14036 |\n", + "| fps | 159 |\n", + "| time_elapsed | 970 |\n", + "| total_timesteps | 154410 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.52 |\n", + "| n_updates | 4350 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14040 |\n", + "| fps | 159 |\n", + "| time_elapsed | 971 |\n", + "| total_timesteps | 154452 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.58 |\n", + "| n_updates | 4352 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14044 |\n", + "| fps | 159 |\n", + "| time_elapsed | 971 |\n", + "| total_timesteps | 154536 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.49 |\n", + "| n_updates | 4355 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14048 |\n", + "| fps | 159 |\n", + "| time_elapsed | 972 |\n", + "| total_timesteps | 154572 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.89 |\n", + "| n_updates | 4357 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14052 |\n", + "| fps | 158 |\n", + "| time_elapsed | 972 |\n", + "| total_timesteps | 154614 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.16 |\n", + "| n_updates | 4359 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14056 |\n", + "| fps | 158 |\n", + "| time_elapsed | 973 |\n", + "| total_timesteps | 154692 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.73 |\n", + "| n_updates | 4362 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14060 |\n", + "| fps | 158 |\n", + "| time_elapsed | 973 |\n", + "| total_timesteps | 154770 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.25 |\n", + "| n_updates | 4365 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14064 |\n", + "| fps | 158 |\n", + "| time_elapsed | 974 |\n", + "| total_timesteps | 154836 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.24 |\n", + "| n_updates | 4368 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14068 |\n", + "| fps | 158 |\n", + "| time_elapsed | 974 |\n", + "| total_timesteps | 154866 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.5 |\n", + "| n_updates | 4369 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14072 |\n", + "| fps | 158 |\n", + "| time_elapsed | 974 |\n", + "| total_timesteps | 154932 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.93 |\n", + "| n_updates | 4372 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14076 |\n", + "| fps | 158 |\n", + "| time_elapsed | 975 |\n", + "| total_timesteps | 154968 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.14 |\n", + "| n_updates | 4373 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14080 |\n", + "| fps | 158 |\n", + "| time_elapsed | 975 |\n", + "| total_timesteps | 154998 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.26 |\n", + "| n_updates | 4375 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14084 |\n", + "| fps | 158 |\n", + "| time_elapsed | 975 |\n", + "| total_timesteps | 155022 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.15 |\n", + "| n_updates | 4376 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14088 |\n", + "| fps | 158 |\n", + "| time_elapsed | 976 |\n", + "| total_timesteps | 155052 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 4377 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14092 |\n", + "| fps | 158 |\n", + "| time_elapsed | 976 |\n", + "| total_timesteps | 155076 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 4378 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14096 |\n", + "| fps | 158 |\n", + "| time_elapsed | 976 |\n", + "| total_timesteps | 155112 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.14 |\n", + "| n_updates | 4379 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14100 |\n", + "| fps | 158 |\n", + "| time_elapsed | 976 |\n", + "| total_timesteps | 155154 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.15 |\n", + "| n_updates | 4381 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14104 |\n", + "| fps | 158 |\n", + "| time_elapsed | 977 |\n", + "| total_timesteps | 155190 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.91 |\n", + "| n_updates | 4383 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14108 |\n", + "| fps | 158 |\n", + "| time_elapsed | 977 |\n", + "| total_timesteps | 155226 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.76 |\n", + "| n_updates | 4384 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14112 |\n", + "| fps | 158 |\n", + "| time_elapsed | 977 |\n", + "| total_timesteps | 155286 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.2 |\n", + "| n_updates | 4387 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14116 |\n", + "| fps | 158 |\n", + "| time_elapsed | 978 |\n", + "| total_timesteps | 155310 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.19 |\n", + "| n_updates | 4388 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14120 |\n", + "| fps | 158 |\n", + "| time_elapsed | 978 |\n", + "| total_timesteps | 155346 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.04 |\n", + "| n_updates | 4389 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14124 |\n", + "| fps | 158 |\n", + "| time_elapsed | 978 |\n", + "| total_timesteps | 155394 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.45 |\n", + "| n_updates | 4391 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14128 |\n", + "| fps | 158 |\n", + "| time_elapsed | 979 |\n", + "| total_timesteps | 155424 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.33 |\n", + "| n_updates | 4392 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14132 |\n", + "| fps | 158 |\n", + "| time_elapsed | 979 |\n", + "| total_timesteps | 155472 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.53 |\n", + "| n_updates | 4394 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14136 |\n", + "| fps | 158 |\n", + "| time_elapsed | 980 |\n", + "| total_timesteps | 155550 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.08 |\n", + "| n_updates | 4398 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14140 |\n", + "| fps | 158 |\n", + "| time_elapsed | 980 |\n", + "| total_timesteps | 155610 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.07 |\n", + "| n_updates | 4400 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14144 |\n", + "| fps | 158 |\n", + "| time_elapsed | 981 |\n", + "| total_timesteps | 155646 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.1 |\n", + "| n_updates | 4402 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14148 |\n", + "| fps | 158 |\n", + "| time_elapsed | 981 |\n", + "| total_timesteps | 155706 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.72 |\n", + "| n_updates | 4404 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14152 |\n", + "| fps | 158 |\n", + "| time_elapsed | 982 |\n", + "| total_timesteps | 155766 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.38 |\n", + "| n_updates | 4407 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14156 |\n", + "| fps | 158 |\n", + "| time_elapsed | 982 |\n", + "| total_timesteps | 155796 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 4408 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14160 |\n", + "| fps | 158 |\n", + "| time_elapsed | 982 |\n", + "| total_timesteps | 155844 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.34 |\n", + "| n_updates | 4410 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14164 |\n", + "| fps | 158 |\n", + "| time_elapsed | 983 |\n", + "| total_timesteps | 155904 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.24 |\n", + "| n_updates | 4412 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14168 |\n", + "| fps | 158 |\n", + "| time_elapsed | 983 |\n", + "| total_timesteps | 155934 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.9 |\n", + "| n_updates | 4414 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14172 |\n", + "| fps | 158 |\n", + "| time_elapsed | 983 |\n", + "| total_timesteps | 155988 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.12 |\n", + "| n_updates | 4416 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14176 |\n", + "| fps | 158 |\n", + "| time_elapsed | 984 |\n", + "| total_timesteps | 156030 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.45 |\n", + "| n_updates | 4418 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14180 |\n", + "| fps | 158 |\n", + "| time_elapsed | 984 |\n", + "| total_timesteps | 156096 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.47 |\n", + "| n_updates | 4420 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14184 |\n", + "| fps | 158 |\n", + "| time_elapsed | 985 |\n", + "| total_timesteps | 156138 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.49 |\n", + "| n_updates | 4422 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14188 |\n", + "| fps | 158 |\n", + "| time_elapsed | 985 |\n", + "| total_timesteps | 156204 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.89 |\n", + "| n_updates | 4425 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14192 |\n", + "| fps | 158 |\n", + "| time_elapsed | 986 |\n", + "| total_timesteps | 156246 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.26 |\n", + "| n_updates | 4427 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14196 |\n", + "| fps | 158 |\n", + "| time_elapsed | 986 |\n", + "| total_timesteps | 156288 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.26 |\n", + "| n_updates | 4428 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14200 |\n", + "| fps | 158 |\n", + "| time_elapsed | 986 |\n", + "| total_timesteps | 156324 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 4430 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14204 |\n", + "| fps | 158 |\n", + "| time_elapsed | 986 |\n", + "| total_timesteps | 156360 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.27 |\n", + "| n_updates | 4431 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14208 |\n", + "| fps | 158 |\n", + "| time_elapsed | 987 |\n", + "| total_timesteps | 156426 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.77 |\n", + "| n_updates | 4434 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14212 |\n", + "| fps | 158 |\n", + "| time_elapsed | 988 |\n", + "| total_timesteps | 156534 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.7 |\n", + "| n_updates | 4439 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14216 |\n", + "| fps | 158 |\n", + "| time_elapsed | 988 |\n", + "| total_timesteps | 156594 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.37 |\n", + "| n_updates | 4441 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14220 |\n", + "| fps | 158 |\n", + "| time_elapsed | 989 |\n", + "| total_timesteps | 156624 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.26 |\n", + "| n_updates | 4442 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14224 |\n", + "| fps | 158 |\n", + "| time_elapsed | 989 |\n", + "| total_timesteps | 156732 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.27 |\n", + "| n_updates | 4447 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14228 |\n", + "| fps | 158 |\n", + "| time_elapsed | 990 |\n", + "| total_timesteps | 156768 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.17 |\n", + "| n_updates | 4448 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14232 |\n", + "| fps | 158 |\n", + "| time_elapsed | 990 |\n", + "| total_timesteps | 156804 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.96 |\n", + "| n_updates | 4450 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14236 |\n", + "| fps | 158 |\n", + "| time_elapsed | 990 |\n", + "| total_timesteps | 156846 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.04 |\n", + "| n_updates | 4452 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14240 |\n", + "| fps | 158 |\n", + "| time_elapsed | 991 |\n", + "| total_timesteps | 156888 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.14 |\n", + "| n_updates | 4453 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14244 |\n", + "| fps | 158 |\n", + "| time_elapsed | 992 |\n", + "| total_timesteps | 156996 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.02 |\n", + "| n_updates | 4458 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14248 |\n", + "| fps | 158 |\n", + "| time_elapsed | 992 |\n", + "| total_timesteps | 157068 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 4461 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14252 |\n", + "| fps | 158 |\n", + "| time_elapsed | 992 |\n", + "| total_timesteps | 157104 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.82 |\n", + "| n_updates | 4462 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14256 |\n", + "| fps | 158 |\n", + "| time_elapsed | 993 |\n", + "| total_timesteps | 157128 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.4 |\n", + "| n_updates | 4463 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14260 |\n", + "| fps | 158 |\n", + "| time_elapsed | 993 |\n", + "| total_timesteps | 157152 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.85 |\n", + "| n_updates | 4464 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14264 |\n", + "| fps | 158 |\n", + "| time_elapsed | 993 |\n", + "| total_timesteps | 157188 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.07 |\n", + "| n_updates | 4466 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14268 |\n", + "| fps | 158 |\n", + "| time_elapsed | 994 |\n", + "| total_timesteps | 157248 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.79 |\n", + "| n_updates | 4468 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14272 |\n", + "| fps | 158 |\n", + "| time_elapsed | 994 |\n", + "| total_timesteps | 157296 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.11 |\n", + "| n_updates | 4470 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14276 |\n", + "| fps | 158 |\n", + "| time_elapsed | 995 |\n", + "| total_timesteps | 157362 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.78 |\n", + "| n_updates | 4473 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14280 |\n", + "| fps | 158 |\n", + "| time_elapsed | 995 |\n", + "| total_timesteps | 157404 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.16 |\n", + "| n_updates | 4475 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14284 |\n", + "| fps | 158 |\n", + "| time_elapsed | 995 |\n", + "| total_timesteps | 157452 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.71 |\n", + "| n_updates | 4477 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14288 |\n", + "| fps | 158 |\n", + "| time_elapsed | 996 |\n", + "| total_timesteps | 157494 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.05 |\n", + "| n_updates | 4479 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14292 |\n", + "| fps | 158 |\n", + "| time_elapsed | 996 |\n", + "| total_timesteps | 157530 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3 |\n", + "| n_updates | 4480 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14296 |\n", + "| fps | 158 |\n", + "| time_elapsed | 996 |\n", + "| total_timesteps | 157554 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.59 |\n", + "| n_updates | 4481 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14300 |\n", + "| fps | 158 |\n", + "| time_elapsed | 996 |\n", + "| total_timesteps | 157590 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.79 |\n", + "| n_updates | 4483 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14304 |\n", + "| fps | 158 |\n", + "| time_elapsed | 997 |\n", + "| total_timesteps | 157626 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.13 |\n", + "| n_updates | 4484 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14308 |\n", + "| fps | 158 |\n", + "| time_elapsed | 997 |\n", + "| total_timesteps | 157674 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.13 |\n", + "| n_updates | 4486 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14312 |\n", + "| fps | 158 |\n", + "| time_elapsed | 997 |\n", + "| total_timesteps | 157722 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.33 |\n", + "| n_updates | 4488 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14316 |\n", + "| fps | 158 |\n", + "| time_elapsed | 998 |\n", + "| total_timesteps | 157758 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.89 |\n", + "| n_updates | 4490 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14320 |\n", + "| fps | 158 |\n", + "| time_elapsed | 998 |\n", + "| total_timesteps | 157812 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.92 |\n", + "| n_updates | 4492 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14324 |\n", + "| fps | 158 |\n", + "| time_elapsed | 998 |\n", + "| total_timesteps | 157848 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.4 |\n", + "| n_updates | 4493 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14328 |\n", + "| fps | 158 |\n", + "| time_elapsed | 999 |\n", + "| total_timesteps | 157872 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.76 |\n", + "| n_updates | 4494 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14332 |\n", + "| fps | 157 |\n", + "| time_elapsed | 999 |\n", + "| total_timesteps | 157896 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.2 |\n", + "| n_updates | 4495 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14336 |\n", + "| fps | 157 |\n", + "| time_elapsed | 999 |\n", + "| total_timesteps | 157932 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.36 |\n", + "| n_updates | 4497 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14340 |\n", + "| fps | 157 |\n", + "| time_elapsed | 999 |\n", + "| total_timesteps | 157950 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.47 |\n", + "| n_updates | 4498 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14344 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1000 |\n", + "| total_timesteps | 157998 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.13 |\n", + "| n_updates | 4500 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14348 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1000 |\n", + "| total_timesteps | 158028 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.07 |\n", + "| n_updates | 4501 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14352 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1000 |\n", + "| total_timesteps | 158058 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.12 |\n", + "| n_updates | 4502 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14356 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1001 |\n", + "| total_timesteps | 158088 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.32 |\n", + "| n_updates | 4503 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14360 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1001 |\n", + "| total_timesteps | 158130 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.98 |\n", + "| n_updates | 4505 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14364 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1001 |\n", + "| total_timesteps | 158166 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.08 |\n", + "| n_updates | 4507 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14368 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1002 |\n", + "| total_timesteps | 158274 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.46 |\n", + "| n_updates | 4511 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14372 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1003 |\n", + "| total_timesteps | 158334 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.38 |\n", + "| n_updates | 4514 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14376 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1003 |\n", + "| total_timesteps | 158388 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.37 |\n", + "| n_updates | 4516 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14380 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1003 |\n", + "| total_timesteps | 158442 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.79 |\n", + "| n_updates | 4518 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14384 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1004 |\n", + "| total_timesteps | 158460 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.41 |\n", + "| n_updates | 4519 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14388 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1004 |\n", + "| total_timesteps | 158490 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 4520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14392 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1004 |\n", + "| total_timesteps | 158532 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.7 |\n", + "| n_updates | 4522 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14396 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1005 |\n", + "| total_timesteps | 158592 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.84 |\n", + "| n_updates | 4524 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14400 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1005 |\n", + "| total_timesteps | 158640 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.1 |\n", + "| n_updates | 4526 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14404 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1005 |\n", + "| total_timesteps | 158688 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.19 |\n", + "| n_updates | 4528 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14408 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1006 |\n", + "| total_timesteps | 158724 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.3 |\n", + "| n_updates | 4530 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14412 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1006 |\n", + "| total_timesteps | 158802 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.62 |\n", + "| n_updates | 4533 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14416 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1007 |\n", + "| total_timesteps | 158850 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 4535 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14420 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1007 |\n", + "| total_timesteps | 158892 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.29 |\n", + "| n_updates | 4537 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14424 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1007 |\n", + "| total_timesteps | 158946 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.58 |\n", + "| n_updates | 4539 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14428 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1008 |\n", + "| total_timesteps | 158976 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.16 |\n", + "| n_updates | 4540 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14432 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1008 |\n", + "| total_timesteps | 159030 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.13 |\n", + "| n_updates | 4543 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14436 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1008 |\n", + "| total_timesteps | 159066 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.4 |\n", + "| n_updates | 4544 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14440 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1009 |\n", + "| total_timesteps | 159126 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.12 |\n", + "| n_updates | 4547 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14444 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1009 |\n", + "| total_timesteps | 159180 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.6 |\n", + "| n_updates | 4549 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14448 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1010 |\n", + "| total_timesteps | 159240 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.5 |\n", + "| n_updates | 4551 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14452 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1010 |\n", + "| total_timesteps | 159276 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.34 |\n", + "| n_updates | 4553 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.16 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14456 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1010 |\n", + "| total_timesteps | 159306 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.36 |\n", + "| n_updates | 4554 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14460 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1011 |\n", + "| total_timesteps | 159336 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.06 |\n", + "| n_updates | 4555 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14464 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1011 |\n", + "| total_timesteps | 159378 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.12 |\n", + "| n_updates | 4557 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14468 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1011 |\n", + "| total_timesteps | 159408 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.97 |\n", + "| n_updates | 4558 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14472 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1012 |\n", + "| total_timesteps | 159450 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.96 |\n", + "| n_updates | 4560 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14476 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1012 |\n", + "| total_timesteps | 159492 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.5 |\n", + "| n_updates | 4562 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14480 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1012 |\n", + "| total_timesteps | 159552 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.87 |\n", + "| n_updates | 4564 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14484 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1013 |\n", + "| total_timesteps | 159582 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.19 |\n", + "| n_updates | 4566 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14488 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1013 |\n", + "| total_timesteps | 159618 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.62 |\n", + "| n_updates | 4567 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14492 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1013 |\n", + "| total_timesteps | 159660 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.56 |\n", + "| n_updates | 4569 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14496 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1014 |\n", + "| total_timesteps | 159798 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.99 |\n", + "| n_updates | 4575 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14500 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1015 |\n", + "| total_timesteps | 159852 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.03 |\n", + "| n_updates | 4577 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14504 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1015 |\n", + "| total_timesteps | 159900 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 4579 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14508 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1016 |\n", + "| total_timesteps | 159978 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.14 |\n", + "| n_updates | 4582 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14512 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1016 |\n", + "| total_timesteps | 160020 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.09 |\n", + "| n_updates | 4584 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14516 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1016 |\n", + "| total_timesteps | 160062 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2 |\n", + "| n_updates | 4586 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14520 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1017 |\n", + "| total_timesteps | 160098 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.4 |\n", + "| n_updates | 4587 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14524 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1017 |\n", + "| total_timesteps | 160140 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.16 |\n", + "| n_updates | 4589 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.13 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14528 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1017 |\n", + "| total_timesteps | 160170 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.03 |\n", + "| n_updates | 4590 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14532 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1018 |\n", + "| total_timesteps | 160188 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.07 |\n", + "| n_updates | 4591 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14536 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1018 |\n", + "| total_timesteps | 160224 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.13 |\n", + "| n_updates | 4592 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14540 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1018 |\n", + "| total_timesteps | 160266 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.27 |\n", + "| n_updates | 4594 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14544 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1019 |\n", + "| total_timesteps | 160320 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.3 |\n", + "| n_updates | 4596 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14548 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1019 |\n", + "| total_timesteps | 160362 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.08 |\n", + "| n_updates | 4598 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14552 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1019 |\n", + "| total_timesteps | 160410 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.67 |\n", + "| n_updates | 4600 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14556 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1020 |\n", + "| total_timesteps | 160434 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.56 |\n", + "| n_updates | 4601 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14560 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1020 |\n", + "| total_timesteps | 160476 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.33 |\n", + "| n_updates | 4603 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14564 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1021 |\n", + "| total_timesteps | 160542 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.68 |\n", + "| n_updates | 4606 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14568 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1021 |\n", + "| total_timesteps | 160620 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.34 |\n", + "| n_updates | 4609 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14572 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1021 |\n", + "| total_timesteps | 160668 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.95 |\n", + "| n_updates | 4611 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14576 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1022 |\n", + "| total_timesteps | 160716 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.55 |\n", + "| n_updates | 4613 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14580 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1022 |\n", + "| total_timesteps | 160746 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.94 |\n", + "| n_updates | 4614 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14584 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1022 |\n", + "| total_timesteps | 160782 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.18 |\n", + "| n_updates | 4616 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14588 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1023 |\n", + "| total_timesteps | 160806 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.43 |\n", + "| n_updates | 4617 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14592 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1023 |\n", + "| total_timesteps | 160866 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.97 |\n", + "| n_updates | 4619 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14596 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1024 |\n", + "| total_timesteps | 160932 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.14 |\n", + "| n_updates | 4622 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14600 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1024 |\n", + "| total_timesteps | 161016 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.14 |\n", + "| n_updates | 4625 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14604 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1025 |\n", + "| total_timesteps | 161070 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.21 |\n", + "| n_updates | 4628 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14608 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1025 |\n", + "| total_timesteps | 161106 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.98 |\n", + "| n_updates | 4629 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14612 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1025 |\n", + "| total_timesteps | 161142 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.27 |\n", + "| n_updates | 4631 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14616 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1026 |\n", + "| total_timesteps | 161184 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.12 |\n", + "| n_updates | 4632 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14620 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1026 |\n", + "| total_timesteps | 161220 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.33 |\n", + "| n_updates | 4634 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14624 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1026 |\n", + "| total_timesteps | 161268 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.67 |\n", + "| n_updates | 4636 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14628 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1027 |\n", + "| total_timesteps | 161304 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.49 |\n", + "| n_updates | 4637 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14632 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1027 |\n", + "| total_timesteps | 161328 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.84 |\n", + "| n_updates | 4638 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14636 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1027 |\n", + "| total_timesteps | 161364 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.54 |\n", + "| n_updates | 4640 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14640 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1027 |\n", + "| total_timesteps | 161406 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.5 |\n", + "| n_updates | 4642 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14644 |\n", + "| fps | 157 |\n", + "| time_elapsed | 1028 |\n", + "| total_timesteps | 161442 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 8.65 |\n", + "| n_updates | 4643 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14648 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1028 |\n", + "| total_timesteps | 161478 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.61 |\n", + "| n_updates | 4645 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14652 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1028 |\n", + "| total_timesteps | 161514 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 4646 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14656 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1029 |\n", + "| total_timesteps | 161544 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.3 |\n", + "| n_updates | 4647 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14660 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1029 |\n", + "| total_timesteps | 161580 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.32 |\n", + "| n_updates | 4649 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 305 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14664 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1029 |\n", + "| total_timesteps | 161622 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.02 |\n", + "| n_updates | 4651 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14668 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1030 |\n", + "| total_timesteps | 161664 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.38 |\n", + "| n_updates | 4652 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14672 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1030 |\n", + "| total_timesteps | 161682 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.06 |\n", + "| n_updates | 4653 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14676 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1030 |\n", + "| total_timesteps | 161724 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.11 |\n", + "| n_updates | 4655 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14680 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1030 |\n", + "| total_timesteps | 161760 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.66 |\n", + "| n_updates | 4656 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14684 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1031 |\n", + "| total_timesteps | 161784 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 4657 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14688 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1031 |\n", + "| total_timesteps | 161850 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.92 |\n", + "| n_updates | 4660 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14692 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1031 |\n", + "| total_timesteps | 161868 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.84 |\n", + "| n_updates | 4661 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14696 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1032 |\n", + "| total_timesteps | 161898 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.3 |\n", + "| n_updates | 4662 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14700 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1032 |\n", + "| total_timesteps | 161940 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.31 |\n", + "| n_updates | 4664 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14704 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1032 |\n", + "| total_timesteps | 161988 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.66 |\n", + "| n_updates | 4666 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14708 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1033 |\n", + "| total_timesteps | 162036 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.33 |\n", + "| n_updates | 4668 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14712 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1033 |\n", + "| total_timesteps | 162066 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.61 |\n", + "| n_updates | 4669 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14716 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1033 |\n", + "| total_timesteps | 162102 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.01 |\n", + "| n_updates | 4671 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14720 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1034 |\n", + "| total_timesteps | 162162 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.48 |\n", + "| n_updates | 4673 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14724 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1034 |\n", + "| total_timesteps | 162198 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.69 |\n", + "| n_updates | 4675 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14728 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1034 |\n", + "| total_timesteps | 162210 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14732 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1035 |\n", + "| total_timesteps | 162246 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.62 |\n", + "| n_updates | 4677 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14736 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1035 |\n", + "| total_timesteps | 162300 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.31 |\n", + "| n_updates | 4679 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14740 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1035 |\n", + "| total_timesteps | 162330 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.19 |\n", + "| n_updates | 4680 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14744 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1035 |\n", + "| total_timesteps | 162360 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 4681 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14748 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1036 |\n", + "| total_timesteps | 162372 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 4682 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14752 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1036 |\n", + "| total_timesteps | 162402 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.79 |\n", + "| n_updates | 4683 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14756 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1036 |\n", + "| total_timesteps | 162444 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.98 |\n", + "| n_updates | 4685 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14760 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1036 |\n", + "| total_timesteps | 162474 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.92 |\n", + "| n_updates | 4686 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14764 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1037 |\n", + "| total_timesteps | 162516 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.17 |\n", + "| n_updates | 4688 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14768 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1037 |\n", + "| total_timesteps | 162564 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.13 |\n", + "| n_updates | 4690 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14772 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1038 |\n", + "| total_timesteps | 162612 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.01 |\n", + "| n_updates | 4692 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14776 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1038 |\n", + "| total_timesteps | 162630 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.36 |\n", + "| n_updates | 4693 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14780 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1038 |\n", + "| total_timesteps | 162684 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 4695 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14784 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1038 |\n", + "| total_timesteps | 162708 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.36 |\n", + "| n_updates | 4696 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14788 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1039 |\n", + "| total_timesteps | 162744 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.03 |\n", + "| n_updates | 4697 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14792 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1039 |\n", + "| total_timesteps | 162768 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.88 |\n", + "| n_updates | 4698 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14796 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1039 |\n", + "| total_timesteps | 162792 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.83 |\n", + "| n_updates | 4699 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14800 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1039 |\n", + "| total_timesteps | 162816 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.08 |\n", + "| n_updates | 4700 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14804 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1040 |\n", + "| total_timesteps | 162852 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.99 |\n", + "| n_updates | 4702 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14808 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1040 |\n", + "| total_timesteps | 162894 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.5 |\n", + "| n_updates | 4704 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14812 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1040 |\n", + "| total_timesteps | 162906 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14816 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1040 |\n", + "| total_timesteps | 162936 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6 |\n", + "| n_updates | 4705 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14820 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1041 |\n", + "| total_timesteps | 162978 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.62 |\n", + "| n_updates | 4707 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14824 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1041 |\n", + "| total_timesteps | 163020 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.83 |\n", + "| n_updates | 4709 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14828 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1041 |\n", + "| total_timesteps | 163038 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.41 |\n", + "| n_updates | 4710 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14832 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1042 |\n", + "| total_timesteps | 163062 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.9 |\n", + "| n_updates | 4711 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14836 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1042 |\n", + "| total_timesteps | 163098 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.54 |\n", + "| n_updates | 4712 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14840 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1042 |\n", + "| total_timesteps | 163140 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.21 |\n", + "| n_updates | 4714 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14844 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1042 |\n", + "| total_timesteps | 163158 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.65 |\n", + "| n_updates | 4715 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14848 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1043 |\n", + "| total_timesteps | 163200 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.45 |\n", + "| n_updates | 4716 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14852 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1043 |\n", + "| total_timesteps | 163260 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 4719 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14856 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1044 |\n", + "| total_timesteps | 163302 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 4721 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14860 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1045 |\n", + "| total_timesteps | 163428 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.62 |\n", + "| n_updates | 4726 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14864 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1045 |\n", + "| total_timesteps | 163470 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.04 |\n", + "| n_updates | 4728 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14868 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1045 |\n", + "| total_timesteps | 163506 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.89 |\n", + "| n_updates | 4729 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14872 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1046 |\n", + "| total_timesteps | 163548 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.66 |\n", + "| n_updates | 4731 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14876 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1046 |\n", + "| total_timesteps | 163584 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.02 |\n", + "| n_updates | 4732 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14880 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1046 |\n", + "| total_timesteps | 163626 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.61 |\n", + "| n_updates | 4734 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14884 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1046 |\n", + "| total_timesteps | 163656 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.2 |\n", + "| n_updates | 4735 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14888 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1047 |\n", + "| total_timesteps | 163674 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 4736 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14892 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1047 |\n", + "| total_timesteps | 163710 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.8 |\n", + "| n_updates | 4738 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14896 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1047 |\n", + "| total_timesteps | 163752 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.24 |\n", + "| n_updates | 4739 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14900 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1048 |\n", + "| total_timesteps | 163848 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.18 |\n", + "| n_updates | 4743 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14904 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1049 |\n", + "| total_timesteps | 163932 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.87 |\n", + "| n_updates | 4747 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14908 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1049 |\n", + "| total_timesteps | 163968 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 4748 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14912 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1049 |\n", + "| total_timesteps | 163998 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.1 |\n", + "| n_updates | 4750 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14916 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1050 |\n", + "| total_timesteps | 164040 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.96 |\n", + "| n_updates | 4751 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14920 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1050 |\n", + "| total_timesteps | 164076 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.62 |\n", + "| n_updates | 4753 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14924 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1050 |\n", + "| total_timesteps | 164118 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.69 |\n", + "| n_updates | 4755 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14928 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1051 |\n", + "| total_timesteps | 164196 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.99 |\n", + "| n_updates | 4758 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14932 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1051 |\n", + "| total_timesteps | 164232 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.9 |\n", + "| n_updates | 4759 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14936 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1051 |\n", + "| total_timesteps | 164256 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.29 |\n", + "| n_updates | 4760 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14940 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1052 |\n", + "| total_timesteps | 164298 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.87 |\n", + "| n_updates | 4762 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14944 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1052 |\n", + "| total_timesteps | 164322 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.06 |\n", + "| n_updates | 4763 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14948 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1052 |\n", + "| total_timesteps | 164358 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.21 |\n", + "| n_updates | 4765 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14952 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1053 |\n", + "| total_timesteps | 164400 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.37 |\n", + "| n_updates | 4766 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14956 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1053 |\n", + "| total_timesteps | 164436 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.68 |\n", + "| n_updates | 4768 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14960 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1053 |\n", + "| total_timesteps | 164472 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.76 |\n", + "| n_updates | 4769 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14964 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1054 |\n", + "| total_timesteps | 164526 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.42 |\n", + "| n_updates | 4772 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14968 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1054 |\n", + "| total_timesteps | 164616 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.61 |\n", + "| n_updates | 4775 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14972 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1055 |\n", + "| total_timesteps | 164670 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.56 |\n", + "| n_updates | 4778 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14976 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1055 |\n", + "| total_timesteps | 164700 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.81 |\n", + "| n_updates | 4779 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14980 |\n", + "| fps | 156 |\n", + "| time_elapsed | 1055 |\n", + "| total_timesteps | 164730 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.04 |\n", + "| n_updates | 4780 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14984 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1056 |\n", + "| total_timesteps | 164754 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.52 |\n", + "| n_updates | 4781 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14988 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1056 |\n", + "| total_timesteps | 164790 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 4783 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14992 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1056 |\n", + "| total_timesteps | 164814 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 4784 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 14996 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1056 |\n", + "| total_timesteps | 164832 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15000 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1057 |\n", + "| total_timesteps | 164862 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.65 |\n", + "| n_updates | 4786 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15004 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1057 |\n", + "| total_timesteps | 164928 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.24 |\n", + "| n_updates | 4788 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15008 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1057 |\n", + "| total_timesteps | 164958 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.23 |\n", + "| n_updates | 4790 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15012 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1058 |\n", + "| total_timesteps | 164982 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.6 |\n", + "| n_updates | 4791 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15016 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1058 |\n", + "| total_timesteps | 165018 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.83 |\n", + "| n_updates | 4792 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15020 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1058 |\n", + "| total_timesteps | 165036 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.24 |\n", + "| n_updates | 4793 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15024 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1058 |\n", + "| total_timesteps | 165066 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.5 |\n", + "| n_updates | 4794 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15028 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1059 |\n", + "| total_timesteps | 165084 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.7 |\n", + "| n_updates | 4795 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15032 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1059 |\n", + "| total_timesteps | 165108 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.29 |\n", + "| n_updates | 4796 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15036 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1059 |\n", + "| total_timesteps | 165138 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.93 |\n", + "| n_updates | 4797 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15040 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1059 |\n", + "| total_timesteps | 165180 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.65 |\n", + "| n_updates | 4799 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15044 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1060 |\n", + "| total_timesteps | 165312 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2 |\n", + "| n_updates | 4804 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15048 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1061 |\n", + "| total_timesteps | 165348 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.59 |\n", + "| n_updates | 4806 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15052 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1061 |\n", + "| total_timesteps | 165390 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.35 |\n", + "| n_updates | 4808 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15056 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1061 |\n", + "| total_timesteps | 165414 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.1 |\n", + "| n_updates | 4809 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15060 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1062 |\n", + "| total_timesteps | 165456 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.11 |\n", + "| n_updates | 4810 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15064 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1062 |\n", + "| total_timesteps | 165498 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.39 |\n", + "| n_updates | 4812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15068 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1062 |\n", + "| total_timesteps | 165540 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 4814 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15072 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1063 |\n", + "| total_timesteps | 165624 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.07 |\n", + "| n_updates | 4817 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15076 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1064 |\n", + "| total_timesteps | 165702 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.27 |\n", + "| n_updates | 4821 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15080 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1064 |\n", + "| total_timesteps | 165750 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.56 |\n", + "| n_updates | 4823 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15084 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1064 |\n", + "| total_timesteps | 165798 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.48 |\n", + "| n_updates | 4825 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15088 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1065 |\n", + "| total_timesteps | 165834 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.88 |\n", + "| n_updates | 4826 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15092 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1065 |\n", + "| total_timesteps | 165882 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.21 |\n", + "| n_updates | 4828 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15096 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1066 |\n", + "| total_timesteps | 165936 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.65 |\n", + "| n_updates | 4830 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15100 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1066 |\n", + "| total_timesteps | 165978 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.62 |\n", + "| n_updates | 4832 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15104 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1066 |\n", + "| total_timesteps | 166032 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.45 |\n", + "| n_updates | 4834 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15108 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1067 |\n", + "| total_timesteps | 166080 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.44 |\n", + "| n_updates | 4836 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15112 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1067 |\n", + "| total_timesteps | 166122 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.17 |\n", + "| n_updates | 4838 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15116 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1068 |\n", + "| total_timesteps | 166212 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.84 |\n", + "| n_updates | 4842 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15120 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1068 |\n", + "| total_timesteps | 166284 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 4845 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15124 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1069 |\n", + "| total_timesteps | 166344 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 4847 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15128 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1069 |\n", + "| total_timesteps | 166398 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 4850 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15132 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1070 |\n", + "| total_timesteps | 166440 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.29 |\n", + "| n_updates | 4851 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15136 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1070 |\n", + "| total_timesteps | 166470 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.98 |\n", + "| n_updates | 4853 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15140 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1070 |\n", + "| total_timesteps | 166506 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.18 |\n", + "| n_updates | 4854 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15144 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1070 |\n", + "| total_timesteps | 166536 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.34 |\n", + "| n_updates | 4855 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15148 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1071 |\n", + "| total_timesteps | 166566 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.9 |\n", + "| n_updates | 4857 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15152 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1071 |\n", + "| total_timesteps | 166638 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.21 |\n", + "| n_updates | 4860 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15156 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1072 |\n", + "| total_timesteps | 166668 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.46 |\n", + "| n_updates | 4861 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15160 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1072 |\n", + "| total_timesteps | 166686 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.64 |\n", + "| n_updates | 4862 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15164 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1072 |\n", + "| total_timesteps | 166740 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.71 |\n", + "| n_updates | 4864 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15168 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1072 |\n", + "| total_timesteps | 166770 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.92 |\n", + "| n_updates | 4865 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15172 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1073 |\n", + "| total_timesteps | 166800 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.52 |\n", + "| n_updates | 4866 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15176 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1073 |\n", + "| total_timesteps | 166818 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.68 |\n", + "| n_updates | 4867 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15180 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1073 |\n", + "| total_timesteps | 166848 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.16 |\n", + "| n_updates | 4868 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15184 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1073 |\n", + "| total_timesteps | 166878 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.92 |\n", + "| n_updates | 4870 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15188 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1074 |\n", + "| total_timesteps | 166908 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.18 |\n", + "| n_updates | 4871 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15192 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1074 |\n", + "| total_timesteps | 166920 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15196 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1074 |\n", + "| total_timesteps | 166956 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.51 |\n", + "| n_updates | 4873 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15200 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1075 |\n", + "| total_timesteps | 167010 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.84 |\n", + "| n_updates | 4875 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15204 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1075 |\n", + "| total_timesteps | 167040 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.92 |\n", + "| n_updates | 4876 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15208 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1075 |\n", + "| total_timesteps | 167058 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.93 |\n", + "| n_updates | 4877 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15212 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1075 |\n", + "| total_timesteps | 167082 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.21 |\n", + "| n_updates | 4878 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15216 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1076 |\n", + "| total_timesteps | 167142 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 4881 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15220 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1076 |\n", + "| total_timesteps | 167172 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.17 |\n", + "| n_updates | 4882 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15224 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1076 |\n", + "| total_timesteps | 167214 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.18 |\n", + "| n_updates | 4884 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15228 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1077 |\n", + "| total_timesteps | 167268 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.39 |\n", + "| n_updates | 4886 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15232 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1077 |\n", + "| total_timesteps | 167298 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.89 |\n", + "| n_updates | 4887 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15236 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1077 |\n", + "| total_timesteps | 167340 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.91 |\n", + "| n_updates | 4889 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15240 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1078 |\n", + "| total_timesteps | 167376 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.48 |\n", + "| n_updates | 4890 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15244 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1078 |\n", + "| total_timesteps | 167418 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.68 |\n", + "| n_updates | 4892 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15248 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1079 |\n", + "| total_timesteps | 167496 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.44 |\n", + "| n_updates | 4895 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15252 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1079 |\n", + "| total_timesteps | 167556 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.12 |\n", + "| n_updates | 4898 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15256 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1079 |\n", + "| total_timesteps | 167610 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 4900 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15260 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1080 |\n", + "| total_timesteps | 167670 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.33 |\n", + "| n_updates | 4903 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15264 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1080 |\n", + "| total_timesteps | 167694 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.65 |\n", + "| n_updates | 4904 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15268 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1081 |\n", + "| total_timesteps | 167724 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.18 |\n", + "| n_updates | 4905 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15272 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1081 |\n", + "| total_timesteps | 167808 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.46 |\n", + "| n_updates | 4908 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15276 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1082 |\n", + "| total_timesteps | 167892 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.9 |\n", + "| n_updates | 4912 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15280 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1082 |\n", + "| total_timesteps | 167916 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.09 |\n", + "| n_updates | 4913 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15284 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1082 |\n", + "| total_timesteps | 167946 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.04 |\n", + "| n_updates | 4914 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15288 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1083 |\n", + "| total_timesteps | 167982 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.42 |\n", + "| n_updates | 4916 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15292 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1083 |\n", + "| total_timesteps | 168018 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.94 |\n", + "| n_updates | 4917 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15296 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1083 |\n", + "| total_timesteps | 168078 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 4920 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15300 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1084 |\n", + "| total_timesteps | 168120 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 4921 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15304 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1084 |\n", + "| total_timesteps | 168174 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 4924 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15308 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1085 |\n", + "| total_timesteps | 168210 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.58 |\n", + "| n_updates | 4925 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15312 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1085 |\n", + "| total_timesteps | 168240 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.99 |\n", + "| n_updates | 4926 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15316 |\n", + "| fps | 155 |\n", + "| time_elapsed | 1085 |\n", + "| total_timesteps | 168264 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.62 |\n", + "| n_updates | 4927 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15320 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1085 |\n", + "| total_timesteps | 168294 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.27 |\n", + "| n_updates | 4929 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15324 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1086 |\n", + "| total_timesteps | 168330 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 4930 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15328 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1086 |\n", + "| total_timesteps | 168366 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.98 |\n", + "| n_updates | 4932 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15332 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1086 |\n", + "| total_timesteps | 168408 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.26 |\n", + "| n_updates | 4933 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15336 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1087 |\n", + "| total_timesteps | 168486 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.71 |\n", + "| n_updates | 4937 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15340 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1087 |\n", + "| total_timesteps | 168534 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.47 |\n", + "| n_updates | 4939 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15344 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1088 |\n", + "| total_timesteps | 168570 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.5 |\n", + "| n_updates | 4940 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15348 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1088 |\n", + "| total_timesteps | 168612 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.22 |\n", + "| n_updates | 4942 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15352 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1088 |\n", + "| total_timesteps | 168654 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.06 |\n", + "| n_updates | 4944 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15356 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1089 |\n", + "| total_timesteps | 168702 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.27 |\n", + "| n_updates | 4946 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15360 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1089 |\n", + "| total_timesteps | 168744 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.12 |\n", + "| n_updates | 4947 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15364 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1089 |\n", + "| total_timesteps | 168780 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.05 |\n", + "| n_updates | 4949 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15368 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1090 |\n", + "| total_timesteps | 168816 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.06 |\n", + "| n_updates | 4950 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15372 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1090 |\n", + "| total_timesteps | 168858 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.84 |\n", + "| n_updates | 4952 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15376 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1090 |\n", + "| total_timesteps | 168906 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.65 |\n", + "| n_updates | 4954 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15380 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1091 |\n", + "| total_timesteps | 168954 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.71 |\n", + "| n_updates | 4956 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15384 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1091 |\n", + "| total_timesteps | 168990 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.45 |\n", + "| n_updates | 4958 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15388 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1091 |\n", + "| total_timesteps | 169032 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 4959 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15392 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1092 |\n", + "| total_timesteps | 169050 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.07 |\n", + "| n_updates | 4960 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15396 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1092 |\n", + "| total_timesteps | 169092 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.32 |\n", + "| n_updates | 4962 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15400 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1092 |\n", + "| total_timesteps | 169140 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.06 |\n", + "| n_updates | 4964 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15404 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1093 |\n", + "| total_timesteps | 169176 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.19 |\n", + "| n_updates | 4965 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15408 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1093 |\n", + "| total_timesteps | 169188 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.83 |\n", + "| n_updates | 4966 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15412 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1093 |\n", + "| total_timesteps | 169218 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.73 |\n", + "| n_updates | 4967 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15416 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1093 |\n", + "| total_timesteps | 169254 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.17 |\n", + "| n_updates | 4969 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15420 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1094 |\n", + "| total_timesteps | 169290 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.41 |\n", + "| n_updates | 4970 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15424 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1094 |\n", + "| total_timesteps | 169314 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.98 |\n", + "| n_updates | 4971 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15428 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1094 |\n", + "| total_timesteps | 169350 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.15 |\n", + "| n_updates | 4973 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15432 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1094 |\n", + "| total_timesteps | 169380 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.44 |\n", + "| n_updates | 4974 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15436 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1095 |\n", + "| total_timesteps | 169410 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.16 |\n", + "| n_updates | 4975 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15440 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1095 |\n", + "| total_timesteps | 169440 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.92 |\n", + "| n_updates | 4976 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15444 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1095 |\n", + "| total_timesteps | 169470 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.13 |\n", + "| n_updates | 4978 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15448 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1096 |\n", + "| total_timesteps | 169524 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.75 |\n", + "| n_updates | 4980 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15452 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1096 |\n", + "| total_timesteps | 169572 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.48 |\n", + "| n_updates | 4982 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15456 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1097 |\n", + "| total_timesteps | 169638 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.4 |\n", + "| n_updates | 4985 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15460 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1097 |\n", + "| total_timesteps | 169680 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.96 |\n", + "| n_updates | 4986 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15464 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1097 |\n", + "| total_timesteps | 169734 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.01 |\n", + "| n_updates | 4989 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15468 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1098 |\n", + "| total_timesteps | 169782 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.4 |\n", + "| n_updates | 4991 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15472 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1098 |\n", + "| total_timesteps | 169836 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.3 |\n", + "| n_updates | 4993 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15476 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1099 |\n", + "| total_timesteps | 169878 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.17 |\n", + "| n_updates | 4995 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15480 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1099 |\n", + "| total_timesteps | 169914 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.88 |\n", + "| n_updates | 4996 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15484 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1099 |\n", + "| total_timesteps | 169950 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.98 |\n", + "| n_updates | 4998 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15488 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1099 |\n", + "| total_timesteps | 169986 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.4 |\n", + "| n_updates | 4999 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15492 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1100 |\n", + "| total_timesteps | 170082 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.26 |\n", + "| n_updates | 5003 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15496 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1101 |\n", + "| total_timesteps | 170148 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 5006 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 279 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15500 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1101 |\n", + "| total_timesteps | 170184 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.45 |\n", + "| n_updates | 5007 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15504 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1101 |\n", + "| total_timesteps | 170226 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.05 |\n", + "| n_updates | 5009 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15508 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1102 |\n", + "| total_timesteps | 170238 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.36 |\n", + "| n_updates | 5010 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15512 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1103 |\n", + "| total_timesteps | 170358 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.69 |\n", + "| n_updates | 5015 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15516 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1103 |\n", + "| total_timesteps | 170412 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.92 |\n", + "| n_updates | 5017 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15520 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1103 |\n", + "| total_timesteps | 170454 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.89 |\n", + "| n_updates | 5019 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15524 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1104 |\n", + "| total_timesteps | 170490 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.15 |\n", + "| n_updates | 5020 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15528 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1104 |\n", + "| total_timesteps | 170544 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.79 |\n", + "| n_updates | 5022 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15532 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1104 |\n", + "| total_timesteps | 170586 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.81 |\n", + "| n_updates | 5024 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15536 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1105 |\n", + "| total_timesteps | 170628 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 5026 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15540 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1105 |\n", + "| total_timesteps | 170670 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.59 |\n", + "| n_updates | 5028 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15544 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1105 |\n", + "| total_timesteps | 170706 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.93 |\n", + "| n_updates | 5029 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15548 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1106 |\n", + "| total_timesteps | 170742 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.33 |\n", + "| n_updates | 5031 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15552 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1106 |\n", + "| total_timesteps | 170784 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.43 |\n", + "| n_updates | 5032 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15556 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1107 |\n", + "| total_timesteps | 170850 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.39 |\n", + "| n_updates | 5035 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15560 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1107 |\n", + "| total_timesteps | 170892 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.59 |\n", + "| n_updates | 5037 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15564 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1107 |\n", + "| total_timesteps | 170928 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 5038 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15568 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1108 |\n", + "| total_timesteps | 170970 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.59 |\n", + "| n_updates | 5040 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15572 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1108 |\n", + "| total_timesteps | 171012 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.4 |\n", + "| n_updates | 5042 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15576 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1108 |\n", + "| total_timesteps | 171048 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.36 |\n", + "| n_updates | 5043 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15580 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1109 |\n", + "| total_timesteps | 171084 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.79 |\n", + "| n_updates | 5045 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15584 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1109 |\n", + "| total_timesteps | 171120 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.33 |\n", + "| n_updates | 5046 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15588 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1110 |\n", + "| total_timesteps | 171216 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.61 |\n", + "| n_updates | 5050 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15592 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1110 |\n", + "| total_timesteps | 171288 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.47 |\n", + "| n_updates | 5053 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15596 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1110 |\n", + "| total_timesteps | 171318 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.64 |\n", + "| n_updates | 5055 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15600 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1111 |\n", + "| total_timesteps | 171366 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.55 |\n", + "| n_updates | 5057 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15604 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1112 |\n", + "| total_timesteps | 171438 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.79 |\n", + "| n_updates | 5060 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15608 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1112 |\n", + "| total_timesteps | 171492 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.67 |\n", + "| n_updates | 5062 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15612 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1112 |\n", + "| total_timesteps | 171552 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.34 |\n", + "| n_updates | 5064 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15616 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1113 |\n", + "| total_timesteps | 171636 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.29 |\n", + "| n_updates | 5068 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15620 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1113 |\n", + "| total_timesteps | 171696 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.83 |\n", + "| n_updates | 5070 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15624 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1114 |\n", + "| total_timesteps | 171726 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.7 |\n", + "| n_updates | 5072 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15628 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1114 |\n", + "| total_timesteps | 171756 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.57 |\n", + "| n_updates | 5073 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15632 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1114 |\n", + "| total_timesteps | 171786 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.95 |\n", + "| n_updates | 5074 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15636 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1115 |\n", + "| total_timesteps | 171852 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.41 |\n", + "| n_updates | 5077 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15640 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1115 |\n", + "| total_timesteps | 171912 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.81 |\n", + "| n_updates | 5079 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15644 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1116 |\n", + "| total_timesteps | 171990 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.49 |\n", + "| n_updates | 5083 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15648 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1116 |\n", + "| total_timesteps | 172026 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.34 |\n", + "| n_updates | 5084 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15652 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1117 |\n", + "| total_timesteps | 172068 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 5086 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15656 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1117 |\n", + "| total_timesteps | 172092 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.04 |\n", + "| n_updates | 5087 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15660 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1117 |\n", + "| total_timesteps | 172128 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 5088 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15664 |\n", + "| fps | 154 |\n", + "| time_elapsed | 1117 |\n", + "| total_timesteps | 172164 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 5090 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15668 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1118 |\n", + "| total_timesteps | 172200 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.83 |\n", + "| n_updates | 5091 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15672 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1118 |\n", + "| total_timesteps | 172260 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 5094 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15676 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1118 |\n", + "| total_timesteps | 172284 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.08 |\n", + "| n_updates | 5095 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15680 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1119 |\n", + "| total_timesteps | 172326 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.84 |\n", + "| n_updates | 5097 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15684 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1119 |\n", + "| total_timesteps | 172368 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.21 |\n", + "| n_updates | 5098 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15688 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1120 |\n", + "| total_timesteps | 172446 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.6 |\n", + "| n_updates | 5102 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15692 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1120 |\n", + "| total_timesteps | 172482 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.44 |\n", + "| n_updates | 5103 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15696 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1120 |\n", + "| total_timesteps | 172512 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.72 |\n", + "| n_updates | 5104 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15700 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1121 |\n", + "| total_timesteps | 172536 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.5 |\n", + "| n_updates | 5105 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15704 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1121 |\n", + "| total_timesteps | 172578 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.53 |\n", + "| n_updates | 5107 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15708 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1121 |\n", + "| total_timesteps | 172650 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.86 |\n", + "| n_updates | 5110 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15712 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1122 |\n", + "| total_timesteps | 172704 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.88 |\n", + "| n_updates | 5112 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15716 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1122 |\n", + "| total_timesteps | 172734 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.32 |\n", + "| n_updates | 5114 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15720 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1123 |\n", + "| total_timesteps | 172806 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.68 |\n", + "| n_updates | 5117 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15724 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1123 |\n", + "| total_timesteps | 172872 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.12 |\n", + "| n_updates | 5119 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15728 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1124 |\n", + "| total_timesteps | 172908 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.21 |\n", + "| n_updates | 5121 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15732 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1124 |\n", + "| total_timesteps | 172932 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.85 |\n", + "| n_updates | 5122 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15736 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1124 |\n", + "| total_timesteps | 172956 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.36 |\n", + "| n_updates | 5123 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15740 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1124 |\n", + "| total_timesteps | 172986 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.66 |\n", + "| n_updates | 5124 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15744 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1125 |\n", + "| total_timesteps | 173034 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.92 |\n", + "| n_updates | 5126 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15748 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1125 |\n", + "| total_timesteps | 173082 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.18 |\n", + "| n_updates | 5128 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15752 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1126 |\n", + "| total_timesteps | 173136 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.62 |\n", + "| n_updates | 5130 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15756 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1126 |\n", + "| total_timesteps | 173172 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.22 |\n", + "| n_updates | 5132 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15760 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1126 |\n", + "| total_timesteps | 173238 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.87 |\n", + "| n_updates | 5135 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15764 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1127 |\n", + "| total_timesteps | 173286 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.61 |\n", + "| n_updates | 5137 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15768 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1127 |\n", + "| total_timesteps | 173340 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.89 |\n", + "| n_updates | 5139 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15772 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1127 |\n", + "| total_timesteps | 173364 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.01 |\n", + "| n_updates | 5140 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15776 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1128 |\n", + "| total_timesteps | 173400 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.94 |\n", + "| n_updates | 5141 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15780 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1128 |\n", + "| total_timesteps | 173436 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.29 |\n", + "| n_updates | 5143 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15784 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1128 |\n", + "| total_timesteps | 173478 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.47 |\n", + "| n_updates | 5145 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15788 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1129 |\n", + "| total_timesteps | 173568 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.43 |\n", + "| n_updates | 5148 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15792 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1130 |\n", + "| total_timesteps | 173658 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.66 |\n", + "| n_updates | 5152 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15796 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1130 |\n", + "| total_timesteps | 173694 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.62 |\n", + "| n_updates | 5154 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15800 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1131 |\n", + "| total_timesteps | 173772 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.84 |\n", + "| n_updates | 5157 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15804 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1131 |\n", + "| total_timesteps | 173838 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.57 |\n", + "| n_updates | 5160 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15808 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1132 |\n", + "| total_timesteps | 173892 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.16 |\n", + "| n_updates | 5162 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15812 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1132 |\n", + "| total_timesteps | 173934 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.48 |\n", + "| n_updates | 5164 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15816 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1132 |\n", + "| total_timesteps | 173964 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.54 |\n", + "| n_updates | 5165 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15820 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1133 |\n", + "| total_timesteps | 174000 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.26 |\n", + "| n_updates | 5166 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15824 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1133 |\n", + "| total_timesteps | 174030 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 5168 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15828 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1133 |\n", + "| total_timesteps | 174060 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.1 |\n", + "| n_updates | 5169 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15832 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1134 |\n", + "| total_timesteps | 174114 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.68 |\n", + "| n_updates | 5171 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15836 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1134 |\n", + "| total_timesteps | 174174 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.59 |\n", + "| n_updates | 5174 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15840 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1134 |\n", + "| total_timesteps | 174216 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.53 |\n", + "| n_updates | 5175 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15844 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1135 |\n", + "| total_timesteps | 174246 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.37 |\n", + "| n_updates | 5177 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15848 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1135 |\n", + "| total_timesteps | 174282 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.31 |\n", + "| n_updates | 5178 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15852 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1136 |\n", + "| total_timesteps | 174342 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.77 |\n", + "| n_updates | 5181 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15856 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1136 |\n", + "| total_timesteps | 174390 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.11 |\n", + "| n_updates | 5183 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15860 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1137 |\n", + "| total_timesteps | 174420 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.58 |\n", + "| n_updates | 5184 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15864 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1137 |\n", + "| total_timesteps | 174462 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.09 |\n", + "| n_updates | 5186 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15868 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1137 |\n", + "| total_timesteps | 174504 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 5187 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15872 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1138 |\n", + "| total_timesteps | 174582 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.47 |\n", + "| n_updates | 5191 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15876 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1138 |\n", + "| total_timesteps | 174618 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 5192 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15880 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1139 |\n", + "| total_timesteps | 174672 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.39 |\n", + "| n_updates | 5194 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15884 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1139 |\n", + "| total_timesteps | 174696 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.35 |\n", + "| n_updates | 5195 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15888 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1139 |\n", + "| total_timesteps | 174720 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.25 |\n", + "| n_updates | 5196 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15892 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1140 |\n", + "| total_timesteps | 174816 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.23 |\n", + "| n_updates | 5200 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15896 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1141 |\n", + "| total_timesteps | 174870 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.63 |\n", + "| n_updates | 5203 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15900 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1141 |\n", + "| total_timesteps | 174912 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 5204 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15904 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1141 |\n", + "| total_timesteps | 174930 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.04 |\n", + "| n_updates | 5205 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15908 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1142 |\n", + "| total_timesteps | 174960 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.2 |\n", + "| n_updates | 5206 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15912 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1142 |\n", + "| total_timesteps | 174996 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.99 |\n", + "| n_updates | 5208 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15916 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1143 |\n", + "| total_timesteps | 175056 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 5210 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15920 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1143 |\n", + "| total_timesteps | 175122 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.29 |\n", + "| n_updates | 5213 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15924 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1144 |\n", + "| total_timesteps | 175158 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.25 |\n", + "| n_updates | 5215 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15928 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1144 |\n", + "| total_timesteps | 175188 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 5216 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15932 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1144 |\n", + "| total_timesteps | 175206 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 5217 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15936 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1145 |\n", + "| total_timesteps | 175284 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.35 |\n", + "| n_updates | 5220 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15940 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1145 |\n", + "| total_timesteps | 175314 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 5221 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15944 |\n", + "| fps | 153 |\n", + "| time_elapsed | 1145 |\n", + "| total_timesteps | 175338 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.21 |\n", + "| n_updates | 5222 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15948 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1146 |\n", + "| total_timesteps | 175380 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.7 |\n", + "| n_updates | 5224 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15952 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1146 |\n", + "| total_timesteps | 175410 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.27 |\n", + "| n_updates | 5225 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15956 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1147 |\n", + "| total_timesteps | 175446 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.61 |\n", + "| n_updates | 5227 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15960 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1147 |\n", + "| total_timesteps | 175482 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.53 |\n", + "| n_updates | 5228 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 304 |\n", + "| ep_rew_mean | 2.09 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15964 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1147 |\n", + "| total_timesteps | 175506 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 5229 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15968 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1147 |\n", + "| total_timesteps | 175536 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.4 |\n", + "| n_updates | 5230 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15972 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1148 |\n", + "| total_timesteps | 175572 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 5232 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15976 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1148 |\n", + "| total_timesteps | 175584 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15980 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1148 |\n", + "| total_timesteps | 175620 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 5234 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15984 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1149 |\n", + "| total_timesteps | 175674 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.27 |\n", + "| n_updates | 5236 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15988 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1149 |\n", + "| total_timesteps | 175710 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.94 |\n", + "| n_updates | 5238 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15992 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1150 |\n", + "| total_timesteps | 175746 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.12 |\n", + "| n_updates | 5239 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 15996 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1150 |\n", + "| total_timesteps | 175800 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.7 |\n", + "| n_updates | 5241 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16000 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1151 |\n", + "| total_timesteps | 175830 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.58 |\n", + "| n_updates | 5243 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16004 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1151 |\n", + "| total_timesteps | 175872 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.17 |\n", + "| n_updates | 5244 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16008 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1151 |\n", + "| total_timesteps | 175908 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.82 |\n", + "| n_updates | 5246 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16012 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1151 |\n", + "| total_timesteps | 175938 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 5247 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16016 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1152 |\n", + "| total_timesteps | 176004 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.79 |\n", + "| n_updates | 5250 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16020 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1152 |\n", + "| total_timesteps | 176010 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16024 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1153 |\n", + "| total_timesteps | 176052 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.97 |\n", + "| n_updates | 5252 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16028 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1153 |\n", + "| total_timesteps | 176082 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.17 |\n", + "| n_updates | 5253 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16032 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1153 |\n", + "| total_timesteps | 176106 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.64 |\n", + "| n_updates | 5254 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16036 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1154 |\n", + "| total_timesteps | 176142 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.14 |\n", + "| n_updates | 5256 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16040 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1154 |\n", + "| total_timesteps | 176178 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.74 |\n", + "| n_updates | 5257 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16044 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1154 |\n", + "| total_timesteps | 176208 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.48 |\n", + "| n_updates | 5258 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16048 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1155 |\n", + "| total_timesteps | 176250 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.03 |\n", + "| n_updates | 5260 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16052 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1155 |\n", + "| total_timesteps | 176274 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.3 |\n", + "| n_updates | 5261 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16056 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1155 |\n", + "| total_timesteps | 176310 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.2 |\n", + "| n_updates | 5263 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16060 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1156 |\n", + "| total_timesteps | 176346 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.04 |\n", + "| n_updates | 5264 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16064 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1156 |\n", + "| total_timesteps | 176382 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.6 |\n", + "| n_updates | 5266 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16068 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1157 |\n", + "| total_timesteps | 176442 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.67 |\n", + "| n_updates | 5268 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 289 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16072 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1157 |\n", + "| total_timesteps | 176472 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.17 |\n", + "| n_updates | 5269 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16076 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1157 |\n", + "| total_timesteps | 176508 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.65 |\n", + "| n_updates | 5271 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16080 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1157 |\n", + "| total_timesteps | 176538 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.07 |\n", + "| n_updates | 5272 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16084 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1158 |\n", + "| total_timesteps | 176556 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.37 |\n", + "| n_updates | 5273 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16088 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1158 |\n", + "| total_timesteps | 176598 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.83 |\n", + "| n_updates | 5275 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16092 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1158 |\n", + "| total_timesteps | 176634 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 5276 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16096 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1159 |\n", + "| total_timesteps | 176652 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.13 |\n", + "| n_updates | 5277 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16100 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1159 |\n", + "| total_timesteps | 176676 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.63 |\n", + "| n_updates | 5278 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16104 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1159 |\n", + "| total_timesteps | 176724 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.73 |\n", + "| n_updates | 5280 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16108 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1160 |\n", + "| total_timesteps | 176766 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.88 |\n", + "| n_updates | 5282 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16112 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1160 |\n", + "| total_timesteps | 176796 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.02 |\n", + "| n_updates | 5283 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16116 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1160 |\n", + "| total_timesteps | 176814 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.27 |\n", + "| n_updates | 5284 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.85 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16120 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1160 |\n", + "| total_timesteps | 176844 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.33 |\n", + "| n_updates | 5285 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16124 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1161 |\n", + "| total_timesteps | 176874 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.6 |\n", + "| n_updates | 5286 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16128 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1161 |\n", + "| total_timesteps | 176910 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.23 |\n", + "| n_updates | 5288 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16132 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1161 |\n", + "| total_timesteps | 176928 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16136 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1162 |\n", + "| total_timesteps | 176958 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.51 |\n", + "| n_updates | 5290 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16140 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1162 |\n", + "| total_timesteps | 177012 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 5292 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16144 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1162 |\n", + "| total_timesteps | 177048 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 5293 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16148 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1163 |\n", + "| total_timesteps | 177072 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.35 |\n", + "| n_updates | 5294 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16152 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1163 |\n", + "| total_timesteps | 177090 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.21 |\n", + "| n_updates | 5295 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16156 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1163 |\n", + "| total_timesteps | 177126 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.74 |\n", + "| n_updates | 5297 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16160 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1164 |\n", + "| total_timesteps | 177156 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.58 |\n", + "| n_updates | 5298 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16164 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1164 |\n", + "| total_timesteps | 177192 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.63 |\n", + "| n_updates | 5299 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16168 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1164 |\n", + "| total_timesteps | 177222 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.6 |\n", + "| n_updates | 5301 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16172 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1165 |\n", + "| total_timesteps | 177264 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.48 |\n", + "| n_updates | 5302 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16176 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1165 |\n", + "| total_timesteps | 177306 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 5304 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16180 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1165 |\n", + "| total_timesteps | 177318 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.45 |\n", + "| n_updates | 5305 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16184 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1166 |\n", + "| total_timesteps | 177360 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.03 |\n", + "| n_updates | 5306 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16188 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1166 |\n", + "| total_timesteps | 177402 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.92 |\n", + "| n_updates | 5308 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16192 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1166 |\n", + "| total_timesteps | 177432 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.81 |\n", + "| n_updates | 5309 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16196 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1167 |\n", + "| total_timesteps | 177474 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.19 |\n", + "| n_updates | 5311 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16200 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1167 |\n", + "| total_timesteps | 177510 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.77 |\n", + "| n_updates | 5313 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16204 |\n", + "| fps | 152 |\n", + "| time_elapsed | 1167 |\n", + "| total_timesteps | 177534 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.86 |\n", + "| n_updates | 5314 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16208 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1168 |\n", + "| total_timesteps | 177570 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.03 |\n", + "| n_updates | 5315 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16212 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1168 |\n", + "| total_timesteps | 177618 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.38 |\n", + "| n_updates | 5317 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16216 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1169 |\n", + "| total_timesteps | 177660 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 5319 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16220 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1169 |\n", + "| total_timesteps | 177732 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.81 |\n", + "| n_updates | 5322 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16224 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1170 |\n", + "| total_timesteps | 177774 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.99 |\n", + "| n_updates | 5324 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16228 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1170 |\n", + "| total_timesteps | 177822 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 5326 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16232 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1171 |\n", + "| total_timesteps | 177870 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 5328 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16236 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1171 |\n", + "| total_timesteps | 177900 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.21 |\n", + "| n_updates | 5329 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16240 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1171 |\n", + "| total_timesteps | 177942 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.51 |\n", + "| n_updates | 5331 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16244 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1172 |\n", + "| total_timesteps | 177996 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.74 |\n", + "| n_updates | 5333 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16248 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1172 |\n", + "| total_timesteps | 178038 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.18 |\n", + "| n_updates | 5335 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16252 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1173 |\n", + "| total_timesteps | 178098 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.27 |\n", + "| n_updates | 5337 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16256 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1174 |\n", + "| total_timesteps | 178152 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.17 |\n", + "| n_updates | 5339 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16260 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1174 |\n", + "| total_timesteps | 178200 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.19 |\n", + "| n_updates | 5341 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16264 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1174 |\n", + "| total_timesteps | 178242 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.98 |\n", + "| n_updates | 5343 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16268 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1175 |\n", + "| total_timesteps | 178278 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.16 |\n", + "| n_updates | 5345 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16272 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1175 |\n", + "| total_timesteps | 178314 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.24 |\n", + "| n_updates | 5346 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16276 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1176 |\n", + "| total_timesteps | 178350 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.11 |\n", + "| n_updates | 5348 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16280 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1176 |\n", + "| total_timesteps | 178380 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 5349 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16284 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1176 |\n", + "| total_timesteps | 178422 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.36 |\n", + "| n_updates | 5351 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16288 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1176 |\n", + "| total_timesteps | 178446 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.7 |\n", + "| n_updates | 5352 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16292 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1177 |\n", + "| total_timesteps | 178488 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.21 |\n", + "| n_updates | 5353 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16296 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1178 |\n", + "| total_timesteps | 178608 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.3 |\n", + "| n_updates | 5358 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16300 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1178 |\n", + "| total_timesteps | 178644 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.82 |\n", + "| n_updates | 5360 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16304 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1179 |\n", + "| total_timesteps | 178680 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.57 |\n", + "| n_updates | 5361 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16308 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1179 |\n", + "| total_timesteps | 178704 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.05 |\n", + "| n_updates | 5362 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16312 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1179 |\n", + "| total_timesteps | 178746 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.71 |\n", + "| n_updates | 5364 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16316 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1180 |\n", + "| total_timesteps | 178824 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.73 |\n", + "| n_updates | 5367 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16320 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1180 |\n", + "| total_timesteps | 178872 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.29 |\n", + "| n_updates | 5369 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16324 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1181 |\n", + "| total_timesteps | 178896 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.03 |\n", + "| n_updates | 5370 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16328 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1181 |\n", + "| total_timesteps | 178926 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.11 |\n", + "| n_updates | 5372 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16332 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1181 |\n", + "| total_timesteps | 178956 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.51 |\n", + "| n_updates | 5373 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16336 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1182 |\n", + "| total_timesteps | 179022 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.99 |\n", + "| n_updates | 5376 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16340 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1182 |\n", + "| total_timesteps | 179064 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 5377 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16344 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1183 |\n", + "| total_timesteps | 179112 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 5379 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16348 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1183 |\n", + "| total_timesteps | 179124 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.11 |\n", + "| n_updates | 5380 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16352 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1183 |\n", + "| total_timesteps | 179154 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.78 |\n", + "| n_updates | 5381 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16356 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1184 |\n", + "| total_timesteps | 179214 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.12 |\n", + "| n_updates | 5384 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16360 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1184 |\n", + "| total_timesteps | 179244 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.19 |\n", + "| n_updates | 5385 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16364 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1185 |\n", + "| total_timesteps | 179286 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.07 |\n", + "| n_updates | 5387 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16368 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1185 |\n", + "| total_timesteps | 179310 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.86 |\n", + "| n_updates | 5388 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16372 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1185 |\n", + "| total_timesteps | 179346 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.2 |\n", + "| n_updates | 5389 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16376 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1186 |\n", + "| total_timesteps | 179382 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.1 |\n", + "| n_updates | 5391 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16380 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1187 |\n", + "| total_timesteps | 179484 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.11 |\n", + "| n_updates | 5395 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16384 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1187 |\n", + "| total_timesteps | 179556 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.66 |\n", + "| n_updates | 5398 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16388 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1187 |\n", + "| total_timesteps | 179580 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.45 |\n", + "| n_updates | 5399 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16392 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1188 |\n", + "| total_timesteps | 179616 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.28 |\n", + "| n_updates | 5400 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16396 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1188 |\n", + "| total_timesteps | 179658 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.1 |\n", + "| n_updates | 5402 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16400 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1189 |\n", + "| total_timesteps | 179748 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.1 |\n", + "| n_updates | 5406 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16404 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1189 |\n", + "| total_timesteps | 179802 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.61 |\n", + "| n_updates | 5408 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16408 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1190 |\n", + "| total_timesteps | 179844 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 5410 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16412 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1190 |\n", + "| total_timesteps | 179886 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 5412 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16416 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1190 |\n", + "| total_timesteps | 179928 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.52 |\n", + "| n_updates | 5413 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16420 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1191 |\n", + "| total_timesteps | 179970 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.77 |\n", + "| n_updates | 5415 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16424 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1191 |\n", + "| total_timesteps | 180018 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 8.88 |\n", + "| n_updates | 5417 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16428 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1192 |\n", + "| total_timesteps | 180066 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.98 |\n", + "| n_updates | 5419 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16432 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1192 |\n", + "| total_timesteps | 180108 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.93 |\n", + "| n_updates | 5421 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16436 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1192 |\n", + "| total_timesteps | 180144 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.71 |\n", + "| n_updates | 5422 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16440 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1193 |\n", + "| total_timesteps | 180186 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 5424 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16444 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1193 |\n", + "| total_timesteps | 180228 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.03 |\n", + "| n_updates | 5426 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16448 |\n", + "| fps | 151 |\n", + "| time_elapsed | 1193 |\n", + "| total_timesteps | 180288 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.76 |\n", + "| n_updates | 5428 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16452 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1194 |\n", + "| total_timesteps | 180342 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2 |\n", + "| n_updates | 5431 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16456 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1194 |\n", + "| total_timesteps | 180366 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.35 |\n", + "| n_updates | 5432 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16460 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1194 |\n", + "| total_timesteps | 180402 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.79 |\n", + "| n_updates | 5433 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16464 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1195 |\n", + "| total_timesteps | 180468 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.58 |\n", + "| n_updates | 5436 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16468 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1195 |\n", + "| total_timesteps | 180510 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.59 |\n", + "| n_updates | 5438 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16472 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1196 |\n", + "| total_timesteps | 180564 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.77 |\n", + "| n_updates | 5440 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16476 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1196 |\n", + "| total_timesteps | 180600 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.35 |\n", + "| n_updates | 5441 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16480 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1196 |\n", + "| total_timesteps | 180642 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 8.32 |\n", + "| n_updates | 5443 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16484 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1197 |\n", + "| total_timesteps | 180678 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.89 |\n", + "| n_updates | 5445 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16488 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1197 |\n", + "| total_timesteps | 180702 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.9 |\n", + "| n_updates | 5446 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16492 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1197 |\n", + "| total_timesteps | 180738 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.72 |\n", + "| n_updates | 5447 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16496 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1197 |\n", + "| total_timesteps | 180786 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.9 |\n", + "| n_updates | 5449 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16500 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1198 |\n", + "| total_timesteps | 180834 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.61 |\n", + "| n_updates | 5451 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16504 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1198 |\n", + "| total_timesteps | 180876 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.6 |\n", + "| n_updates | 5453 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16508 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1199 |\n", + "| total_timesteps | 180918 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.77 |\n", + "| n_updates | 5455 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16512 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1199 |\n", + "| total_timesteps | 180954 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.19 |\n", + "| n_updates | 5456 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16516 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1199 |\n", + "| total_timesteps | 180996 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.75 |\n", + "| n_updates | 5458 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16520 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1200 |\n", + "| total_timesteps | 181086 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.05 |\n", + "| n_updates | 5462 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16524 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1201 |\n", + "| total_timesteps | 181164 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.3 |\n", + "| n_updates | 5465 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16528 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1201 |\n", + "| total_timesteps | 181194 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.84 |\n", + "| n_updates | 5466 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16532 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1201 |\n", + "| total_timesteps | 181230 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.77 |\n", + "| n_updates | 5468 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16536 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1201 |\n", + "| total_timesteps | 181272 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 8.21 |\n", + "| n_updates | 5469 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16540 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1202 |\n", + "| total_timesteps | 181308 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.45 |\n", + "| n_updates | 5471 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16544 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1202 |\n", + "| total_timesteps | 181350 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.26 |\n", + "| n_updates | 5473 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16548 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1202 |\n", + "| total_timesteps | 181380 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.41 |\n", + "| n_updates | 5474 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16552 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1202 |\n", + "| total_timesteps | 181416 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.38 |\n", + "| n_updates | 5475 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16556 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1203 |\n", + "| total_timesteps | 181464 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.41 |\n", + "| n_updates | 5477 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16560 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1203 |\n", + "| total_timesteps | 181500 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 5479 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16564 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1203 |\n", + "| total_timesteps | 181536 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.68 |\n", + "| n_updates | 5480 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16568 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1204 |\n", + "| total_timesteps | 181566 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.43 |\n", + "| n_updates | 5482 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16572 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1204 |\n", + "| total_timesteps | 181626 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.48 |\n", + "| n_updates | 5484 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16576 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1205 |\n", + "| total_timesteps | 181692 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.33 |\n", + "| n_updates | 5487 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16580 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1205 |\n", + "| total_timesteps | 181728 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.53 |\n", + "| n_updates | 5488 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16584 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1205 |\n", + "| total_timesteps | 181788 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.44 |\n", + "| n_updates | 5491 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16588 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1206 |\n", + "| total_timesteps | 181896 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.69 |\n", + "| n_updates | 5495 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16592 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1207 |\n", + "| total_timesteps | 181932 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.37 |\n", + "| n_updates | 5497 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 277 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16596 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1207 |\n", + "| total_timesteps | 181962 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.76 |\n", + "| n_updates | 5498 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16600 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1207 |\n", + "| total_timesteps | 182010 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 5500 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.69 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16604 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1208 |\n", + "| total_timesteps | 182088 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.14 |\n", + "| n_updates | 5503 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.74 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16608 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1208 |\n", + "| total_timesteps | 182130 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.81 |\n", + "| n_updates | 5505 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16612 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1208 |\n", + "| total_timesteps | 182172 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.93 |\n", + "| n_updates | 5507 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16616 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1209 |\n", + "| total_timesteps | 182208 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.15 |\n", + "| n_updates | 5508 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16620 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1209 |\n", + "| total_timesteps | 182232 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.14 |\n", + "| n_updates | 5509 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16624 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1209 |\n", + "| total_timesteps | 182274 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.5 |\n", + "| n_updates | 5511 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16628 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1210 |\n", + "| total_timesteps | 182346 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.26 |\n", + "| n_updates | 5514 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16632 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1210 |\n", + "| total_timesteps | 182364 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.93 |\n", + "| n_updates | 5515 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16636 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1210 |\n", + "| total_timesteps | 182406 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.43 |\n", + "| n_updates | 5517 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16640 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1211 |\n", + "| total_timesteps | 182436 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.09 |\n", + "| n_updates | 5518 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16644 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1211 |\n", + "| total_timesteps | 182466 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.43 |\n", + "| n_updates | 5519 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16648 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1211 |\n", + "| total_timesteps | 182490 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.82 |\n", + "| n_updates | 5520 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16652 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1212 |\n", + "| total_timesteps | 182544 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 5522 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16656 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1212 |\n", + "| total_timesteps | 182580 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.6 |\n", + "| n_updates | 5524 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16660 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1212 |\n", + "| total_timesteps | 182616 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.18 |\n", + "| n_updates | 5525 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.87 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16664 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1212 |\n", + "| total_timesteps | 182646 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.31 |\n", + "| n_updates | 5527 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16668 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1213 |\n", + "| total_timesteps | 182682 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.11 |\n", + "| n_updates | 5528 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16672 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1213 |\n", + "| total_timesteps | 182700 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.12 |\n", + "| n_updates | 5529 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16676 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1213 |\n", + "| total_timesteps | 182748 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.54 |\n", + "| n_updates | 5531 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16680 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1214 |\n", + "| total_timesteps | 182778 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.39 |\n", + "| n_updates | 5532 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16684 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1214 |\n", + "| total_timesteps | 182808 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.98 |\n", + "| n_updates | 5533 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16688 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1214 |\n", + "| total_timesteps | 182856 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 5535 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16692 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1215 |\n", + "| total_timesteps | 182910 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.35 |\n", + "| n_updates | 5538 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16696 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1216 |\n", + "| total_timesteps | 183054 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.73 |\n", + "| n_updates | 5544 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16700 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1216 |\n", + "| total_timesteps | 183084 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.87 |\n", + "| n_updates | 5545 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16704 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1216 |\n", + "| total_timesteps | 183114 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.05 |\n", + "| n_updates | 5546 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16708 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1217 |\n", + "| total_timesteps | 183210 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.45 |\n", + "| n_updates | 5550 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16712 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1217 |\n", + "| total_timesteps | 183270 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.28 |\n", + "| n_updates | 5553 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16716 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1218 |\n", + "| total_timesteps | 183378 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.81 |\n", + "| n_updates | 5557 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16720 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1219 |\n", + "| total_timesteps | 183414 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.83 |\n", + "| n_updates | 5559 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16724 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1219 |\n", + "| total_timesteps | 183444 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.21 |\n", + "| n_updates | 5560 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16728 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1219 |\n", + "| total_timesteps | 183474 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.39 |\n", + "| n_updates | 5561 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16732 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1219 |\n", + "| total_timesteps | 183516 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.07 |\n", + "| n_updates | 5563 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16736 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1220 |\n", + "| total_timesteps | 183546 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.84 |\n", + "| n_updates | 5564 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16740 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1220 |\n", + "| total_timesteps | 183576 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.29 |\n", + "| n_updates | 5565 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16744 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1220 |\n", + "| total_timesteps | 183606 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.26 |\n", + "| n_updates | 5567 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16748 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1220 |\n", + "| total_timesteps | 183642 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.11 |\n", + "| n_updates | 5568 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16752 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1221 |\n", + "| total_timesteps | 183702 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.41 |\n", + "| n_updates | 5571 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16756 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1221 |\n", + "| total_timesteps | 183732 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.81 |\n", + "| n_updates | 5572 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16760 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1221 |\n", + "| total_timesteps | 183756 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.78 |\n", + "| n_updates | 5573 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16764 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1222 |\n", + "| total_timesteps | 183792 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.1 |\n", + "| n_updates | 5574 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16768 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1222 |\n", + "| total_timesteps | 183816 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.3 |\n", + "| n_updates | 5575 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16772 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1222 |\n", + "| total_timesteps | 183846 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.22 |\n", + "| n_updates | 5577 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16776 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1223 |\n", + "| total_timesteps | 183936 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.49 |\n", + "| n_updates | 5580 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16780 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1223 |\n", + "| total_timesteps | 183996 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.47 |\n", + "| n_updates | 5583 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16784 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1223 |\n", + "| total_timesteps | 184026 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.37 |\n", + "| n_updates | 5584 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16788 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1224 |\n", + "| total_timesteps | 184056 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.99 |\n", + "| n_updates | 5585 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16792 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1224 |\n", + "| total_timesteps | 184092 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.7 |\n", + "| n_updates | 5587 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16796 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1225 |\n", + "| total_timesteps | 184182 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.17 |\n", + "| n_updates | 5591 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16800 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1225 |\n", + "| total_timesteps | 184230 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 5593 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16804 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1226 |\n", + "| total_timesteps | 184278 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.04 |\n", + "| n_updates | 5595 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16808 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1226 |\n", + "| total_timesteps | 184320 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.75 |\n", + "| n_updates | 5596 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16812 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1226 |\n", + "| total_timesteps | 184356 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.07 |\n", + "| n_updates | 5598 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16816 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1226 |\n", + "| total_timesteps | 184392 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.04 |\n", + "| n_updates | 5599 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16820 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1227 |\n", + "| total_timesteps | 184434 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.18 |\n", + "| n_updates | 5601 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16824 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1227 |\n", + "| total_timesteps | 184524 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.72 |\n", + "| n_updates | 5605 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16828 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1228 |\n", + "| total_timesteps | 184596 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.37 |\n", + "| n_updates | 5608 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16832 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1228 |\n", + "| total_timesteps | 184656 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.11 |\n", + "| n_updates | 5610 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16836 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1229 |\n", + "| total_timesteps | 184692 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.65 |\n", + "| n_updates | 5612 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16840 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1229 |\n", + "| total_timesteps | 184722 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 5613 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16844 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1229 |\n", + "| total_timesteps | 184740 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.24 |\n", + "| n_updates | 5614 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16848 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1229 |\n", + "| total_timesteps | 184770 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.7 |\n", + "| n_updates | 5615 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16852 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1230 |\n", + "| total_timesteps | 184806 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.29 |\n", + "| n_updates | 5617 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16856 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1230 |\n", + "| total_timesteps | 184842 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.67 |\n", + "| n_updates | 5618 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16860 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1230 |\n", + "| total_timesteps | 184866 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 5619 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16864 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1231 |\n", + "| total_timesteps | 184908 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.15 |\n", + "| n_updates | 5621 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16868 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1231 |\n", + "| total_timesteps | 184944 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.04 |\n", + "| n_updates | 5622 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16872 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1231 |\n", + "| total_timesteps | 184986 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.02 |\n", + "| n_updates | 5624 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16876 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1232 |\n", + "| total_timesteps | 185064 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.89 |\n", + "| n_updates | 5627 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16880 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1232 |\n", + "| total_timesteps | 185100 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.24 |\n", + "| n_updates | 5629 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16884 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1232 |\n", + "| total_timesteps | 185124 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 5630 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16888 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1233 |\n", + "| total_timesteps | 185166 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.2 |\n", + "| n_updates | 5632 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16892 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1233 |\n", + "| total_timesteps | 185202 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 5633 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16896 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1233 |\n", + "| total_timesteps | 185232 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.49 |\n", + "| n_updates | 5634 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16900 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1233 |\n", + "| total_timesteps | 185250 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.9 |\n", + "| n_updates | 5635 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16904 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1234 |\n", + "| total_timesteps | 185280 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.03 |\n", + "| n_updates | 5636 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16908 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1234 |\n", + "| total_timesteps | 185334 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 5639 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16912 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1234 |\n", + "| total_timesteps | 185364 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.48 |\n", + "| n_updates | 5640 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16916 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1235 |\n", + "| total_timesteps | 185406 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.04 |\n", + "| n_updates | 5642 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16920 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1235 |\n", + "| total_timesteps | 185424 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16924 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1235 |\n", + "| total_timesteps | 185448 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 5643 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16928 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1235 |\n", + "| total_timesteps | 185478 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.93 |\n", + "| n_updates | 5645 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16932 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1236 |\n", + "| total_timesteps | 185520 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.26 |\n", + "| n_updates | 5646 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16936 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1236 |\n", + "| total_timesteps | 185562 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.73 |\n", + "| n_updates | 5648 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16940 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1236 |\n", + "| total_timesteps | 185616 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.55 |\n", + "| n_updates | 5650 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16944 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1237 |\n", + "| total_timesteps | 185652 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.59 |\n", + "| n_updates | 5652 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.9 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16948 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1237 |\n", + "| total_timesteps | 185694 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.06 |\n", + "| n_updates | 5654 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16952 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1237 |\n", + "| total_timesteps | 185742 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.14 |\n", + "| n_updates | 5656 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16956 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1238 |\n", + "| total_timesteps | 185784 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.59 |\n", + "| n_updates | 5657 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16960 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1238 |\n", + "| total_timesteps | 185832 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.01 |\n", + "| n_updates | 5659 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16964 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1238 |\n", + "| total_timesteps | 185868 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.92 |\n", + "| n_updates | 5661 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16968 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1239 |\n", + "| total_timesteps | 185904 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.6 |\n", + "| n_updates | 5662 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.94 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16972 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1239 |\n", + "| total_timesteps | 185934 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.45 |\n", + "| n_updates | 5664 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16976 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1239 |\n", + "| total_timesteps | 185958 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.66 |\n", + "| n_updates | 5665 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16980 |\n", + "| fps | 150 |\n", + "| time_elapsed | 1239 |\n", + "| total_timesteps | 186000 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.8 |\n", + "| n_updates | 5666 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16984 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1240 |\n", + "| total_timesteps | 186054 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.09 |\n", + "| n_updates | 5669 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16988 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1240 |\n", + "| total_timesteps | 186084 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.47 |\n", + "| n_updates | 5670 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16992 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1240 |\n", + "| total_timesteps | 186102 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.34 |\n", + "| n_updates | 5671 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 16996 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1241 |\n", + "| total_timesteps | 186138 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.05 |\n", + "| n_updates | 5672 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17000 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1241 |\n", + "| total_timesteps | 186198 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.1 |\n", + "| n_updates | 5675 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17004 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1241 |\n", + "| total_timesteps | 186240 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.98 |\n", + "| n_updates | 5676 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17008 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1242 |\n", + "| total_timesteps | 186270 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.6 |\n", + "| n_updates | 5678 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17012 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1242 |\n", + "| total_timesteps | 186300 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.16 |\n", + "| n_updates | 5679 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17016 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1243 |\n", + "| total_timesteps | 186372 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.34 |\n", + "| n_updates | 5682 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17020 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1243 |\n", + "| total_timesteps | 186402 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.1 |\n", + "| n_updates | 5683 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17024 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1243 |\n", + "| total_timesteps | 186438 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.4 |\n", + "| n_updates | 5685 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17028 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1243 |\n", + "| total_timesteps | 186468 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.16 |\n", + "| n_updates | 5686 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17032 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1244 |\n", + "| total_timesteps | 186498 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.17 |\n", + "| n_updates | 5687 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17036 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1244 |\n", + "| total_timesteps | 186522 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.25 |\n", + "| n_updates | 5688 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.96 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17040 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1244 |\n", + "| total_timesteps | 186552 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 5689 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17044 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1244 |\n", + "| total_timesteps | 186600 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.1 |\n", + "| n_updates | 5691 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.93 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17048 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1245 |\n", + "| total_timesteps | 186642 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.82 |\n", + "| n_updates | 5693 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17052 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1245 |\n", + "| total_timesteps | 186684 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.73 |\n", + "| n_updates | 5695 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17056 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1245 |\n", + "| total_timesteps | 186720 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 5696 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17060 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1246 |\n", + "| total_timesteps | 186738 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.6 |\n", + "| n_updates | 5697 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17064 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1246 |\n", + "| total_timesteps | 186768 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.76 |\n", + "| n_updates | 5698 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17068 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1246 |\n", + "| total_timesteps | 186798 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.46 |\n", + "| n_updates | 5700 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17072 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1246 |\n", + "| total_timesteps | 186828 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.01 |\n", + "| n_updates | 5701 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17076 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1247 |\n", + "| total_timesteps | 186858 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.89 |\n", + "| n_updates | 5702 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17080 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1247 |\n", + "| total_timesteps | 186900 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.11 |\n", + "| n_updates | 5704 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17084 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1247 |\n", + "| total_timesteps | 186942 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.33 |\n", + "| n_updates | 5706 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17088 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1248 |\n", + "| total_timesteps | 186972 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.41 |\n", + "| n_updates | 5707 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17092 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1248 |\n", + "| total_timesteps | 187026 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.12 |\n", + "| n_updates | 5709 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.86 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17096 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1248 |\n", + "| total_timesteps | 187080 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.4 |\n", + "| n_updates | 5711 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17100 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1249 |\n", + "| total_timesteps | 187122 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.57 |\n", + "| n_updates | 5713 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17104 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1249 |\n", + "| total_timesteps | 187158 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.95 |\n", + "| n_updates | 5715 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17108 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1250 |\n", + "| total_timesteps | 187212 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.56 |\n", + "| n_updates | 5717 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17112 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1250 |\n", + "| total_timesteps | 187266 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.43 |\n", + "| n_updates | 5719 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17116 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1250 |\n", + "| total_timesteps | 187290 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.69 |\n", + "| n_updates | 5720 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17120 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1251 |\n", + "| total_timesteps | 187356 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.72 |\n", + "| n_updates | 5723 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17124 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1251 |\n", + "| total_timesteps | 187392 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.59 |\n", + "| n_updates | 5724 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17128 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1251 |\n", + "| total_timesteps | 187422 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.88 |\n", + "| n_updates | 5726 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17132 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1252 |\n", + "| total_timesteps | 187446 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.89 |\n", + "| n_updates | 5727 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17136 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1252 |\n", + "| total_timesteps | 187470 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.54 |\n", + "| n_updates | 5728 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17140 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1252 |\n", + "| total_timesteps | 187494 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.69 |\n", + "| n_updates | 5729 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17144 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1252 |\n", + "| total_timesteps | 187524 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.33 |\n", + "| n_updates | 5730 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17148 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1252 |\n", + "| total_timesteps | 187554 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.68 |\n", + "| n_updates | 5731 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17152 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1253 |\n", + "| total_timesteps | 187602 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.16 |\n", + "| n_updates | 5733 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17156 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1253 |\n", + "| total_timesteps | 187632 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.28 |\n", + "| n_updates | 5734 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.77 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17160 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1253 |\n", + "| total_timesteps | 187662 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.42 |\n", + "| n_updates | 5736 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17164 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1254 |\n", + "| total_timesteps | 187692 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.67 |\n", + "| n_updates | 5737 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17168 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1254 |\n", + "| total_timesteps | 187722 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.49 |\n", + "| n_updates | 5738 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17172 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1254 |\n", + "| total_timesteps | 187752 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.63 |\n", + "| n_updates | 5739 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17176 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1254 |\n", + "| total_timesteps | 187776 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.04 |\n", + "| n_updates | 5740 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17180 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1255 |\n", + "| total_timesteps | 187800 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.94 |\n", + "| n_updates | 5741 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17184 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1255 |\n", + "| total_timesteps | 187824 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.35 |\n", + "| n_updates | 5742 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 270 |\n", + "| ep_rew_mean | 1.75 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17188 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1255 |\n", + "| total_timesteps | 187866 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.55 |\n", + "| n_updates | 5744 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17192 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1256 |\n", + "| total_timesteps | 187932 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.22 |\n", + "| n_updates | 5747 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.71 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17196 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1256 |\n", + "| total_timesteps | 187986 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.27 |\n", + "| n_updates | 5749 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17200 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1257 |\n", + "| total_timesteps | 188046 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.52 |\n", + "| n_updates | 5752 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 269 |\n", + "| ep_rew_mean | 1.72 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17204 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1257 |\n", + "| total_timesteps | 188112 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.5 |\n", + "| n_updates | 5754 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17208 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1258 |\n", + "| total_timesteps | 188178 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.1 |\n", + "| n_updates | 5757 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17212 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1258 |\n", + "| total_timesteps | 188220 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.04 |\n", + "| n_updates | 5759 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17216 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1258 |\n", + "| total_timesteps | 188262 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.76 |\n", + "| n_updates | 5761 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 267 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17220 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1259 |\n", + "| total_timesteps | 188292 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.05 |\n", + "| n_updates | 5762 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17224 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1259 |\n", + "| total_timesteps | 188334 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.75 |\n", + "| n_updates | 5764 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17228 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1259 |\n", + "| total_timesteps | 188400 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.11 |\n", + "| n_updates | 5766 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17232 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1260 |\n", + "| total_timesteps | 188436 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.27 |\n", + "| n_updates | 5768 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17236 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1260 |\n", + "| total_timesteps | 188460 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.1 |\n", + "| n_updates | 5769 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17240 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1260 |\n", + "| total_timesteps | 188490 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.63 |\n", + "| n_updates | 5770 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17244 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1260 |\n", + "| total_timesteps | 188508 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.14 |\n", + "| n_updates | 5771 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17248 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1261 |\n", + "| total_timesteps | 188532 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.87 |\n", + "| n_updates | 5772 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17252 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1261 |\n", + "| total_timesteps | 188568 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 5773 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17256 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1261 |\n", + "| total_timesteps | 188604 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.33 |\n", + "| n_updates | 5775 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17260 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1261 |\n", + "| total_timesteps | 188628 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.62 |\n", + "| n_updates | 5776 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17264 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1262 |\n", + "| total_timesteps | 188652 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.99 |\n", + "| n_updates | 5777 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17268 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1262 |\n", + "| total_timesteps | 188682 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.47 |\n", + "| n_updates | 5778 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17272 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1262 |\n", + "| total_timesteps | 188694 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.14 |\n", + "| n_updates | 5779 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17276 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1262 |\n", + "| total_timesteps | 188724 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.36 |\n", + "| n_updates | 5780 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17280 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1262 |\n", + "| total_timesteps | 188748 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.03 |\n", + "| n_updates | 5781 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17284 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1263 |\n", + "| total_timesteps | 188862 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.87 |\n", + "| n_updates | 5786 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17288 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1264 |\n", + "| total_timesteps | 188916 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.78 |\n", + "| n_updates | 5788 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17292 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1264 |\n", + "| total_timesteps | 188952 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.76 |\n", + "| n_updates | 5789 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17296 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1264 |\n", + "| total_timesteps | 188982 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.26 |\n", + "| n_updates | 5791 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17300 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1265 |\n", + "| total_timesteps | 189024 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.87 |\n", + "| n_updates | 5792 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17304 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1265 |\n", + "| total_timesteps | 189084 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.5 |\n", + "| n_updates | 5795 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17308 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1265 |\n", + "| total_timesteps | 189132 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.64 |\n", + "| n_updates | 5797 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17312 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1266 |\n", + "| total_timesteps | 189162 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.21 |\n", + "| n_updates | 5798 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17316 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1266 |\n", + "| total_timesteps | 189234 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.53 |\n", + "| n_updates | 5801 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17320 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1267 |\n", + "| total_timesteps | 189300 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.92 |\n", + "| n_updates | 5804 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.59 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17324 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1267 |\n", + "| total_timesteps | 189330 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.99 |\n", + "| n_updates | 5805 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17328 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1267 |\n", + "| total_timesteps | 189348 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.06 |\n", + "| n_updates | 5806 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17332 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1267 |\n", + "| total_timesteps | 189378 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.62 |\n", + "| n_updates | 5807 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17336 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1268 |\n", + "| total_timesteps | 189414 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 5809 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 261 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17340 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1268 |\n", + "| total_timesteps | 189474 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.67 |\n", + "| n_updates | 5811 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17344 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1268 |\n", + "| total_timesteps | 189504 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.03 |\n", + "| n_updates | 5812 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17348 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1269 |\n", + "| total_timesteps | 189522 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.51 |\n", + "| n_updates | 5813 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17352 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1269 |\n", + "| total_timesteps | 189558 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.72 |\n", + "| n_updates | 5815 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17356 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1269 |\n", + "| total_timesteps | 189618 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.59 |\n", + "| n_updates | 5817 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17360 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1270 |\n", + "| total_timesteps | 189672 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.44 |\n", + "| n_updates | 5819 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17364 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1270 |\n", + "| total_timesteps | 189702 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.84 |\n", + "| n_updates | 5821 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17368 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1270 |\n", + "| total_timesteps | 189720 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17372 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1270 |\n", + "| total_timesteps | 189744 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.32 |\n", + "| n_updates | 5822 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17376 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1271 |\n", + "| total_timesteps | 189774 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.48 |\n", + "| n_updates | 5824 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17380 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1271 |\n", + "| total_timesteps | 189828 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.09 |\n", + "| n_updates | 5826 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17384 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1271 |\n", + "| total_timesteps | 189864 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.54 |\n", + "| n_updates | 5827 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17388 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1272 |\n", + "| total_timesteps | 189894 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.11 |\n", + "| n_updates | 5829 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.58 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17392 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1272 |\n", + "| total_timesteps | 189924 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.19 |\n", + "| n_updates | 5830 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17396 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1272 |\n", + "| total_timesteps | 189960 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.38 |\n", + "| n_updates | 5831 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17400 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1273 |\n", + "| total_timesteps | 189990 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.31 |\n", + "| n_updates | 5833 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17404 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1273 |\n", + "| total_timesteps | 190020 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.07 |\n", + "| n_updates | 5834 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17408 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1273 |\n", + "| total_timesteps | 190050 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 5835 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17412 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1273 |\n", + "| total_timesteps | 190086 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.99 |\n", + "| n_updates | 5837 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17416 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1274 |\n", + "| total_timesteps | 190122 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.13 |\n", + "| n_updates | 5838 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17420 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1274 |\n", + "| total_timesteps | 190158 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.9 |\n", + "| n_updates | 5840 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17424 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1274 |\n", + "| total_timesteps | 190200 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.36 |\n", + "| n_updates | 5841 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17428 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1275 |\n", + "| total_timesteps | 190248 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.92 |\n", + "| n_updates | 5843 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17432 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1275 |\n", + "| total_timesteps | 190260 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 5844 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17436 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1275 |\n", + "| total_timesteps | 190290 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.21 |\n", + "| n_updates | 5845 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17440 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1276 |\n", + "| total_timesteps | 190332 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.77 |\n", + "| n_updates | 5847 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17444 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1276 |\n", + "| total_timesteps | 190374 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 5849 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17448 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1276 |\n", + "| total_timesteps | 190416 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.48 |\n", + "| n_updates | 5850 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17452 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1276 |\n", + "| total_timesteps | 190446 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.83 |\n", + "| n_updates | 5852 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17456 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1277 |\n", + "| total_timesteps | 190482 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.53 |\n", + "| n_updates | 5853 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17460 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1277 |\n", + "| total_timesteps | 190524 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.86 |\n", + "| n_updates | 5855 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17464 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1277 |\n", + "| total_timesteps | 190536 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17468 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1278 |\n", + "| total_timesteps | 190614 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.43 |\n", + "| n_updates | 5859 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17472 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1278 |\n", + "| total_timesteps | 190632 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17476 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1278 |\n", + "| total_timesteps | 190668 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 5861 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17480 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1279 |\n", + "| total_timesteps | 190698 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 5862 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17484 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1279 |\n", + "| total_timesteps | 190746 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 5864 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17488 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1279 |\n", + "| total_timesteps | 190788 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.43 |\n", + "| n_updates | 5866 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17492 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1279 |\n", + "| total_timesteps | 190812 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.78 |\n", + "| n_updates | 5867 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17496 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1280 |\n", + "| total_timesteps | 190848 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.06 |\n", + "| n_updates | 5868 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 258 |\n", + "| ep_rew_mean | 1.49 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17500 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1280 |\n", + "| total_timesteps | 190878 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.17 |\n", + "| n_updates | 5870 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17504 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1280 |\n", + "| total_timesteps | 190920 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 5871 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 256 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17508 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1281 |\n", + "| total_timesteps | 190962 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.39 |\n", + "| n_updates | 5873 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 256 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17512 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1281 |\n", + "| total_timesteps | 191004 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.54 |\n", + "| n_updates | 5875 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 255 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17516 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1281 |\n", + "| total_timesteps | 191040 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.15 |\n", + "| n_updates | 5876 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 256 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17520 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1282 |\n", + "| total_timesteps | 191058 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.85 |\n", + "| n_updates | 5877 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 255 |\n", + "| ep_rew_mean | 1.43 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17524 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1282 |\n", + "| total_timesteps | 191082 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.68 |\n", + "| n_updates | 5878 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 255 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17528 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1282 |\n", + "| total_timesteps | 191118 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 5880 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 255 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17532 |\n", + "| fps | 149 |\n", + "| time_elapsed | 1282 |\n", + "| total_timesteps | 191166 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.76 |\n", + "| n_updates | 5882 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 255 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17536 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1283 |\n", + "| total_timesteps | 191238 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 5885 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 255 |\n", + "| ep_rew_mean | 1.44 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17540 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1283 |\n", + "| total_timesteps | 191292 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.04 |\n", + "| n_updates | 5887 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17544 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1284 |\n", + "| total_timesteps | 191316 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.33 |\n", + "| n_updates | 5888 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.47 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17548 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1284 |\n", + "| total_timesteps | 191346 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.29 |\n", + "| n_updates | 5889 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 256 |\n", + "| ep_rew_mean | 1.45 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17552 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1284 |\n", + "| total_timesteps | 191400 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.65 |\n", + "| n_updates | 5891 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17556 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1285 |\n", + "| total_timesteps | 191466 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.86 |\n", + "| n_updates | 5894 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17560 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1285 |\n", + "| total_timesteps | 191526 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.42 |\n", + "| n_updates | 5897 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17564 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1286 |\n", + "| total_timesteps | 191580 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.48 |\n", + "| n_updates | 5899 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 257 |\n", + "| ep_rew_mean | 1.46 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17568 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1286 |\n", + "| total_timesteps | 191622 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.42 |\n", + "| n_updates | 5901 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 259 |\n", + "| ep_rew_mean | 1.48 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17572 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1286 |\n", + "| total_timesteps | 191652 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 5902 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 260 |\n", + "| ep_rew_mean | 1.5 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17576 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1287 |\n", + "| total_timesteps | 191688 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.31 |\n", + "| n_updates | 5903 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17580 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1287 |\n", + "| total_timesteps | 191736 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.15 |\n", + "| n_updates | 5905 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17584 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1287 |\n", + "| total_timesteps | 191778 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.64 |\n", + "| n_updates | 5907 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 262 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17588 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1288 |\n", + "| total_timesteps | 191814 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.27 |\n", + "| n_updates | 5909 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17592 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1288 |\n", + "| total_timesteps | 191832 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17596 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1288 |\n", + "| total_timesteps | 191874 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.06 |\n", + "| n_updates | 5911 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17600 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1288 |\n", + "| total_timesteps | 191916 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.14 |\n", + "| n_updates | 5913 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17604 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1289 |\n", + "| total_timesteps | 191982 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.83 |\n", + "| n_updates | 5916 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17608 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1289 |\n", + "| total_timesteps | 192024 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.31 |\n", + "| n_updates | 5917 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17612 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1290 |\n", + "| total_timesteps | 192060 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.4 |\n", + "| n_updates | 5919 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 263 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17616 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1290 |\n", + "| total_timesteps | 192120 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.93 |\n", + "| n_updates | 5921 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17620 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1291 |\n", + "| total_timesteps | 192180 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.82 |\n", + "| n_updates | 5924 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.57 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17624 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1291 |\n", + "| total_timesteps | 192216 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.98 |\n", + "| n_updates | 5925 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17628 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1291 |\n", + "| total_timesteps | 192246 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.72 |\n", + "| n_updates | 5927 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17632 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1291 |\n", + "| total_timesteps | 192282 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.34 |\n", + "| n_updates | 5928 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17636 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1292 |\n", + "| total_timesteps | 192318 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.53 |\n", + "| n_updates | 5930 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.55 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17640 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1292 |\n", + "| total_timesteps | 192360 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.98 |\n", + "| n_updates | 5931 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.52 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17644 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1292 |\n", + "| total_timesteps | 192420 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.15 |\n", + "| n_updates | 5934 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 264 |\n", + "| ep_rew_mean | 1.51 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17648 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1293 |\n", + "| total_timesteps | 192510 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.35 |\n", + "| n_updates | 5938 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 265 |\n", + "| ep_rew_mean | 1.53 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17652 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1294 |\n", + "| total_timesteps | 192582 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.95 |\n", + "| n_updates | 5941 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 266 |\n", + "| ep_rew_mean | 1.54 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17656 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1294 |\n", + "| total_timesteps | 192594 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17660 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1294 |\n", + "| total_timesteps | 192630 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.37 |\n", + "| n_updates | 5943 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17664 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1294 |\n", + "| total_timesteps | 192672 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.42 |\n", + "| n_updates | 5944 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17668 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1295 |\n", + "| total_timesteps | 192750 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.55 |\n", + "| n_updates | 5948 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17672 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1296 |\n", + "| total_timesteps | 192804 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.86 |\n", + "| n_updates | 5950 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17676 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1296 |\n", + "| total_timesteps | 192852 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.16 |\n", + "| n_updates | 5952 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 268 |\n", + "| ep_rew_mean | 1.56 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17680 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1296 |\n", + "| total_timesteps | 192888 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.33 |\n", + "| n_updates | 5953 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 271 |\n", + "| ep_rew_mean | 1.6 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17684 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1297 |\n", + "| total_timesteps | 192948 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.56 |\n", + "| n_updates | 5956 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17688 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1297 |\n", + "| total_timesteps | 192984 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.36 |\n", + "| n_updates | 5957 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17692 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1297 |\n", + "| total_timesteps | 193026 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.2 |\n", + "| n_updates | 5959 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.63 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17696 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1298 |\n", + "| total_timesteps | 193080 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.8 |\n", + "| n_updates | 5961 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17700 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1298 |\n", + "| total_timesteps | 193152 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.41 |\n", + "| n_updates | 5964 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.66 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17704 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1299 |\n", + "| total_timesteps | 193212 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.4 |\n", + "| n_updates | 5967 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17708 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1299 |\n", + "| total_timesteps | 193278 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.34 |\n", + "| n_updates | 5970 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17712 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1300 |\n", + "| total_timesteps | 193320 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.61 |\n", + "| n_updates | 5971 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17716 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1300 |\n", + "| total_timesteps | 193350 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.21 |\n", + "| n_updates | 5973 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17720 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1300 |\n", + "| total_timesteps | 193386 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.63 |\n", + "| n_updates | 5974 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.68 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17724 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1300 |\n", + "| total_timesteps | 193410 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.58 |\n", + "| n_updates | 5975 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17728 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1301 |\n", + "| total_timesteps | 193452 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.09 |\n", + "| n_updates | 5977 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17732 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1301 |\n", + "| total_timesteps | 193482 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.77 |\n", + "| n_updates | 5978 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.61 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17736 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1301 |\n", + "| total_timesteps | 193554 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.02 |\n", + "| n_updates | 5981 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17740 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1302 |\n", + "| total_timesteps | 193596 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 5983 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17744 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1302 |\n", + "| total_timesteps | 193632 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.51 |\n", + "| n_updates | 5984 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17748 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1302 |\n", + "| total_timesteps | 193668 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.94 |\n", + "| n_updates | 5986 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 272 |\n", + "| ep_rew_mean | 1.62 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17752 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1303 |\n", + "| total_timesteps | 193704 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.89 |\n", + "| n_updates | 5987 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 273 |\n", + "| ep_rew_mean | 1.64 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17756 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1303 |\n", + "| total_timesteps | 193758 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.46 |\n", + "| n_updates | 5990 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 274 |\n", + "| ep_rew_mean | 1.65 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17760 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1304 |\n", + "| total_timesteps | 193818 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.27 |\n", + "| n_updates | 5992 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 275 |\n", + "| ep_rew_mean | 1.67 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17764 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1304 |\n", + "| total_timesteps | 193914 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.96 |\n", + "| n_updates | 5996 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 276 |\n", + "| ep_rew_mean | 1.7 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17768 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1305 |\n", + "| total_timesteps | 193956 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.12 |\n", + "| n_updates | 5998 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17772 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1305 |\n", + "| total_timesteps | 193992 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.76 |\n", + "| n_updates | 5999 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17776 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1305 |\n", + "| total_timesteps | 194022 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.84 |\n", + "| n_updates | 6001 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 278 |\n", + "| ep_rew_mean | 1.73 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17780 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1306 |\n", + "| total_timesteps | 194058 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.92 |\n", + "| n_updates | 6002 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17784 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1307 |\n", + "| total_timesteps | 194184 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.29 |\n", + "| n_updates | 6007 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17788 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1307 |\n", + "| total_timesteps | 194232 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.54 |\n", + "| n_updates | 6009 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17792 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1307 |\n", + "| total_timesteps | 194274 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.44 |\n", + "| n_updates | 6011 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 280 |\n", + "| ep_rew_mean | 1.76 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17796 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1308 |\n", + "| total_timesteps | 194328 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.79 |\n", + "| n_updates | 6013 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 281 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17800 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1308 |\n", + "| total_timesteps | 194370 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.83 |\n", + "| n_updates | 6015 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17804 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1308 |\n", + "| total_timesteps | 194418 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.07 |\n", + "| n_updates | 6017 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17808 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1309 |\n", + "| total_timesteps | 194514 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.42 |\n", + "| n_updates | 6021 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17812 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1310 |\n", + "| total_timesteps | 194568 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.74 |\n", + "| n_updates | 6023 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17816 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1310 |\n", + "| total_timesteps | 194598 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.39 |\n", + "| n_updates | 6025 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17820 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1310 |\n", + "| total_timesteps | 194652 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.06 |\n", + "| n_updates | 6027 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17824 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1311 |\n", + "| total_timesteps | 194700 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.77 |\n", + "| n_updates | 6029 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17828 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1311 |\n", + "| total_timesteps | 194742 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.25 |\n", + "| n_updates | 6031 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17832 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1311 |\n", + "| total_timesteps | 194766 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.51 |\n", + "| n_updates | 6032 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 282 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17836 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1311 |\n", + "| total_timesteps | 194790 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.68 |\n", + "| n_updates | 6033 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 283 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17840 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1312 |\n", + "| total_timesteps | 194814 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.33 |\n", + "| n_updates | 6034 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17844 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1312 |\n", + "| total_timesteps | 194862 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.68 |\n", + "| n_updates | 6036 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17848 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1312 |\n", + "| total_timesteps | 194922 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.08 |\n", + "| n_updates | 6038 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17852 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1313 |\n", + "| total_timesteps | 194970 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.81 |\n", + "| n_updates | 6040 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17856 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1313 |\n", + "| total_timesteps | 195030 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.64 |\n", + "| n_updates | 6043 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17860 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1314 |\n", + "| total_timesteps | 195084 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.97 |\n", + "| n_updates | 6045 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17864 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1314 |\n", + "| total_timesteps | 195126 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.02 |\n", + "| n_updates | 6047 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17868 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1314 |\n", + "| total_timesteps | 195156 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.48 |\n", + "| n_updates | 6048 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.83 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17872 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1315 |\n", + "| total_timesteps | 195180 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.74 |\n", + "| n_updates | 6049 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17876 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1315 |\n", + "| total_timesteps | 195210 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.16 |\n", + "| n_updates | 6050 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17880 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1315 |\n", + "| total_timesteps | 195246 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.56 |\n", + "| n_updates | 6052 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17884 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1316 |\n", + "| total_timesteps | 195306 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.88 |\n", + "| n_updates | 6054 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.81 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17888 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1316 |\n", + "| total_timesteps | 195342 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.18 |\n", + "| n_updates | 6056 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17892 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1316 |\n", + "| total_timesteps | 195378 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.15 |\n", + "| n_updates | 6057 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17896 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1317 |\n", + "| total_timesteps | 195420 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.69 |\n", + "| n_updates | 6059 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 284 |\n", + "| ep_rew_mean | 1.78 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17900 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1317 |\n", + "| total_timesteps | 195450 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.64 |\n", + "| n_updates | 6060 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17904 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1317 |\n", + "| total_timesteps | 195486 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.32 |\n", + "| n_updates | 6062 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 285 |\n", + "| ep_rew_mean | 1.79 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17908 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1317 |\n", + "| total_timesteps | 195516 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.67 |\n", + "| n_updates | 6063 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17912 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1318 |\n", + "| total_timesteps | 195534 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.12 |\n", + "| n_updates | 6064 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17916 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1318 |\n", + "| total_timesteps | 195576 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.63 |\n", + "| n_updates | 6065 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17920 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1318 |\n", + "| total_timesteps | 195630 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.35 |\n", + "| n_updates | 6068 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 286 |\n", + "| ep_rew_mean | 1.8 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17924 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1319 |\n", + "| total_timesteps | 195672 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.7 |\n", + "| n_updates | 6069 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17928 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1319 |\n", + "| total_timesteps | 195714 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.34 |\n", + "| n_updates | 6071 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17932 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1320 |\n", + "| total_timesteps | 195792 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.5 |\n", + "| n_updates | 6074 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17936 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1320 |\n", + "| total_timesteps | 195828 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.83 |\n", + "| n_updates | 6076 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 287 |\n", + "| ep_rew_mean | 1.82 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17940 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1320 |\n", + "| total_timesteps | 195864 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.62 |\n", + "| n_updates | 6077 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17944 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1321 |\n", + "| total_timesteps | 195900 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.33 |\n", + "| n_updates | 6079 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 288 |\n", + "| ep_rew_mean | 1.84 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17948 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1321 |\n", + "| total_timesteps | 195966 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.84 |\n", + "| n_updates | 6082 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 290 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17952 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1322 |\n", + "| total_timesteps | 196062 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.21 |\n", + "| n_updates | 6086 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 291 |\n", + "| ep_rew_mean | 1.88 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17956 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1322 |\n", + "| total_timesteps | 196116 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.28 |\n", + "| n_updates | 6088 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17960 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1323 |\n", + "| total_timesteps | 196158 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.47 |\n", + "| n_updates | 6090 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 292 |\n", + "| ep_rew_mean | 1.89 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17964 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1323 |\n", + "| total_timesteps | 196188 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.13 |\n", + "| n_updates | 6091 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.91 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17968 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1323 |\n", + "| total_timesteps | 196230 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.54 |\n", + "| n_updates | 6093 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 293 |\n", + "| ep_rew_mean | 1.92 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17972 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1324 |\n", + "| total_timesteps | 196302 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.33 |\n", + "| n_updates | 6096 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.95 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17976 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1324 |\n", + "| total_timesteps | 196368 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.76 |\n", + "| n_updates | 6098 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17980 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1325 |\n", + "| total_timesteps | 196416 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.79 |\n", + "| n_updates | 6100 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17984 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1325 |\n", + "| total_timesteps | 196458 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.81 |\n", + "| n_updates | 6102 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17988 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1325 |\n", + "| total_timesteps | 196512 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.05 |\n", + "| n_updates | 6104 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17992 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1326 |\n", + "| total_timesteps | 196554 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 6106 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 17996 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1326 |\n", + "| total_timesteps | 196584 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.68 |\n", + "| n_updates | 6107 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18000 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1326 |\n", + "| total_timesteps | 196620 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.83 |\n", + "| n_updates | 6109 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18004 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1327 |\n", + "| total_timesteps | 196656 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.81 |\n", + "| n_updates | 6110 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18008 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1327 |\n", + "| total_timesteps | 196698 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.43 |\n", + "| n_updates | 6112 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18012 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1327 |\n", + "| total_timesteps | 196746 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.4 |\n", + "| n_updates | 6114 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18016 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1328 |\n", + "| total_timesteps | 196788 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.09 |\n", + "| n_updates | 6116 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18020 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1328 |\n", + "| total_timesteps | 196830 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.75 |\n", + "| n_updates | 6118 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18024 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1328 |\n", + "| total_timesteps | 196866 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.71 |\n", + "| n_updates | 6119 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18028 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1329 |\n", + "| total_timesteps | 196914 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.03 |\n", + "| n_updates | 6121 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18032 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1329 |\n", + "| total_timesteps | 197010 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.52 |\n", + "| n_updates | 6125 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18036 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1330 |\n", + "| total_timesteps | 197052 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.91 |\n", + "| n_updates | 6127 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18040 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1330 |\n", + "| total_timesteps | 197100 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.31 |\n", + "| n_updates | 6129 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18044 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1330 |\n", + "| total_timesteps | 197136 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.4 |\n", + "| n_updates | 6130 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18048 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1331 |\n", + "| total_timesteps | 197166 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.57 |\n", + "| n_updates | 6132 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18052 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1331 |\n", + "| total_timesteps | 197184 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18056 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1331 |\n", + "| total_timesteps | 197232 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.92 |\n", + "| n_updates | 6134 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18060 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1332 |\n", + "| total_timesteps | 197268 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.5 |\n", + "| n_updates | 6136 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18064 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1332 |\n", + "| total_timesteps | 197298 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.28 |\n", + "| n_updates | 6137 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18068 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1332 |\n", + "| total_timesteps | 197352 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.39 |\n", + "| n_updates | 6139 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18072 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1332 |\n", + "| total_timesteps | 197382 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.17 |\n", + "| n_updates | 6141 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18076 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1333 |\n", + "| total_timesteps | 197478 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.92 |\n", + "| n_updates | 6145 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18080 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1334 |\n", + "| total_timesteps | 197532 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.68 |\n", + "| n_updates | 6147 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18084 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1334 |\n", + "| total_timesteps | 197568 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.35 |\n", + "| n_updates | 6148 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18088 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1334 |\n", + "| total_timesteps | 197640 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.17 |\n", + "| n_updates | 6151 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18092 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1335 |\n", + "| total_timesteps | 197700 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.36 |\n", + "| n_updates | 6154 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18096 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1335 |\n", + "| total_timesteps | 197742 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.04 |\n", + "| n_updates | 6156 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18100 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1336 |\n", + "| total_timesteps | 197772 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.22 |\n", + "| n_updates | 6157 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.07 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18104 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1336 |\n", + "| total_timesteps | 197814 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.76 |\n", + "| n_updates | 6159 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18108 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1336 |\n", + "| total_timesteps | 197886 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.48 |\n", + "| n_updates | 6162 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18112 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1337 |\n", + "| total_timesteps | 197922 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.81 |\n", + "| n_updates | 6163 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18116 |\n", + "| fps | 148 |\n", + "| time_elapsed | 1337 |\n", + "| total_timesteps | 197946 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.24 |\n", + "| n_updates | 6164 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18120 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1338 |\n", + "| total_timesteps | 198018 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.65 |\n", + "| n_updates | 6167 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18124 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1338 |\n", + "| total_timesteps | 198066 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.37 |\n", + "| n_updates | 6169 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18128 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1338 |\n", + "| total_timesteps | 198108 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.29 |\n", + "| n_updates | 6171 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18132 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1339 |\n", + "| total_timesteps | 198162 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.44 |\n", + "| n_updates | 6173 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18136 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1339 |\n", + "| total_timesteps | 198186 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.23 |\n", + "| n_updates | 6174 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18140 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1339 |\n", + "| total_timesteps | 198222 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.57 |\n", + "| n_updates | 6176 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 303 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18144 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1339 |\n", + "| total_timesteps | 198240 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 302 |\n", + "| ep_rew_mean | 2.12 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18148 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1340 |\n", + "| total_timesteps | 198276 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.58 |\n", + "| n_updates | 6178 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 301 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18152 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1340 |\n", + "| total_timesteps | 198312 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.61 |\n", + "| n_updates | 6179 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18156 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1340 |\n", + "| total_timesteps | 198342 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.28 |\n", + "| n_updates | 6181 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18160 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1341 |\n", + "| total_timesteps | 198390 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.64 |\n", + "| n_updates | 6183 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18164 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1341 |\n", + "| total_timesteps | 198462 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7 |\n", + "| n_updates | 6186 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 299 |\n", + "| ep_rew_mean | 2.08 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18168 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1342 |\n", + "| total_timesteps | 198522 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.14 |\n", + "| n_updates | 6188 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 298 |\n", + "| ep_rew_mean | 2.06 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18172 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1342 |\n", + "| total_timesteps | 198540 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.08 |\n", + "| n_updates | 6189 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18176 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1342 |\n", + "| total_timesteps | 198624 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.53 |\n", + "| n_updates | 6192 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18180 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1343 |\n", + "| total_timesteps | 198666 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.48 |\n", + "| n_updates | 6194 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18184 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1343 |\n", + "| total_timesteps | 198702 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.08 |\n", + "| n_updates | 6196 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18188 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1343 |\n", + "| total_timesteps | 198744 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.68 |\n", + "| n_updates | 6197 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.1 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18192 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1344 |\n", + "| total_timesteps | 198786 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.25 |\n", + "| n_updates | 6199 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 300 |\n", + "| ep_rew_mean | 2.11 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18196 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1344 |\n", + "| total_timesteps | 198816 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.11 |\n", + "| n_updates | 6200 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.05 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18200 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1344 |\n", + "| total_timesteps | 198858 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.62 |\n", + "| n_updates | 6202 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.04 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18204 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1345 |\n", + "| total_timesteps | 198900 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.84 |\n", + "| n_updates | 6204 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18208 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1345 |\n", + "| total_timesteps | 198912 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18212 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1345 |\n", + "| total_timesteps | 198948 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 6.95 |\n", + "| n_updates | 6206 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18216 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1345 |\n", + "| total_timesteps | 198978 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.61 |\n", + "| n_updates | 6207 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18220 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1346 |\n", + "| total_timesteps | 199014 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.2 |\n", + "| n_updates | 6209 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2.01 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18224 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1346 |\n", + "| total_timesteps | 199062 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.95 |\n", + "| n_updates | 6211 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18228 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1346 |\n", + "| total_timesteps | 199128 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.25 |\n", + "| n_updates | 6213 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 2 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18232 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1347 |\n", + "| total_timesteps | 199164 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.92 |\n", + "| n_updates | 6215 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18236 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1347 |\n", + "| total_timesteps | 199200 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.5 |\n", + "| n_updates | 6216 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18240 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1347 |\n", + "| total_timesteps | 199236 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.39 |\n", + "| n_updates | 6218 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18244 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1348 |\n", + "| total_timesteps | 199290 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.03 |\n", + "| n_updates | 6220 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18248 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1348 |\n", + "| total_timesteps | 199356 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.89 |\n", + "| n_updates | 6223 |\n", + "----------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18252 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1349 |\n", + "| total_timesteps | 199446 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.37 |\n", + "| n_updates | 6227 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 297 |\n", + "| ep_rew_mean | 2.03 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18256 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1350 |\n", + "| total_timesteps | 199494 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.87 |\n", + "| n_updates | 6229 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18260 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1350 |\n", + "| total_timesteps | 199536 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 1.88 |\n", + "| n_updates | 6230 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18264 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1350 |\n", + "| total_timesteps | 199572 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.8 |\n", + "| n_updates | 6232 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18268 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1350 |\n", + "| total_timesteps | 199614 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.43 |\n", + "| n_updates | 6234 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 296 |\n", + "| ep_rew_mean | 2.02 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18272 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1351 |\n", + "| total_timesteps | 199656 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.98 |\n", + "| n_updates | 6235 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 294 |\n", + "| ep_rew_mean | 1.98 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18276 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1351 |\n", + "| total_timesteps | 199698 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.53 |\n", + "| n_updates | 6237 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.99 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18280 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1351 |\n", + "| total_timesteps | 199734 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 4.69 |\n", + "| n_updates | 6239 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18284 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1352 |\n", + "| total_timesteps | 199776 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.63 |\n", + "| n_updates | 6240 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18288 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1352 |\n", + "| total_timesteps | 199812 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 7.02 |\n", + "| n_updates | 6242 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18292 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1353 |\n", + "| total_timesteps | 199908 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 3.92 |\n", + "| n_updates | 6246 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18296 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1353 |\n", + "| total_timesteps | 199968 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 2.47 |\n", + "| n_updates | 6248 |\n", + "----------------------------------\n", + "----------------------------------\n", + "| rollout/ | |\n", + "| ep_len_mean | 295 |\n", + "| ep_rew_mean | 1.97 |\n", + "| exploration_rate | 0.01 |\n", + "| time/ | |\n", + "| episodes | 18300 |\n", + "| fps | 147 |\n", + "| time_elapsed | 1354 |\n", + "| total_timesteps | 200004 |\n", + "| train/ | |\n", + "| learning_rate | 5e-05 |\n", + "| loss | 5.12 |\n", + "| n_updates | 6250 |\n", + "----------------------------------\n" + ] + } + ], + "source": [ + "train_experiment(algo_list, env_name, 200000, models_records)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.0" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/2b_Breakout-v0-recurrent_Evaluate.ipynb b/2b_Breakout-v0-recurrent_Evaluate.ipynb new file mode 100644 index 0000000..4d960d3 --- /dev/null +++ b/2b_Breakout-v0-recurrent_Evaluate.ipynb @@ -0,0 +1,261 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "7d1fa20c", + "metadata": {}, + "outputs": [], + "source": [ + "import os, sys\n", + "import gc\n", + "import matplotlib.pyplot as plt\n", + "import numpy as np" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "83d1313d", + "metadata": {}, + "outputs": [], + "source": [ + "sys.path.append('../')\n", + "import torch" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "c8c767df", + "metadata": {}, + "outputs": [], + "source": [ + "from get_algos import get_all_algos , run_experiment ,call_paths, plot_mean" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "c9fc3531", + "metadata": {}, + "outputs": [], + "source": [ + "import gym\n", + "from gym.wrappers import Monitor\n", + "from sb3_contrib import QRDQN ,RecurrentPPO, TRPO \n", + "from stable_baselines3.common.vec_env import VecFrameStack\n", + "from stable_baselines3.common.evaluation import evaluate_policy\n", + "from stable_baselines3.common.env_util import make_atari_env" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "5f7370b2", + "metadata": {}, + "outputs": [], + "source": [ + "env_name='Breakout-v0'" + ] + }, + { + "cell_type": "markdown", + "id": "54c5cdd5", + "metadata": {}, + "source": [ + "### 2. Evaluation\n", + "
      \n", + "
    1. Create the environment
    2. \n", + "
    3. For each algorithm:
    4. \n", + "
      1. Load the model
      2. \n", + "
      3. Evaluate the model for 5 sample iterations
      4. \n", + "
      5. Output the score for each algo and each iteration
      6. \n", + "
      7. Assess stability of the model based on the variance / standard deviation
      8. \n", + "
      \n", + "
    5. Plot the corresponding scores
    6. \n", + "
    " + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "65fae03b", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['QRDQN', 'RecurrentPPO', 'TRPO']\n" + ] + } + ], + "source": [ + "env_recurrent_type={'Discrete':['MaskablePPO', 'QRDQN', 'RecurrentPPO', 'TRPO'],'Box':['ARS', 'RecurrentPPO', 'TQC', 'TRPO'], \n", + " 'MultiDiscrete':['MaskablePPO', 'RecurrentPPO', 'TRPO'],'MultiBinary':['MaskablePPO', 'RecurrentPPO', 'TRPO']}\n", + "def get_algo_recurrent(env):\n", + " act_space=str(type(env.action_space)).split('.')[3].split(\"'\")[0]\n", + " return env_recurrent_type[act_space]\n", + "\n", + "algo_list=get_algo_recurrent(gym.make(env_name))\n", + "algo_list.remove('MaskablePPO') if 'MaskablePPO' in algo_list else algo_list\n", + "print(algo_list)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "52178f03", + "metadata": {}, + "outputs": [], + "source": [ + "def evaluate_experiment(algo_list, env_name,n_steps=200000,n_episodes=100):\n", + " rewards_mean={}\n", + " rewards_std={}\n", + " for algo_name in reversed(algo_list):\n", + " if algo_name =='QRDQN' or 'TRPO':\n", + " device='cpu'\n", + " else:\n", + " device='cuda' #GPU was unable to load the entire experience relay so moved to virtual memory on disk\n", + " policy='CnnLstmPolicy' if algo_name=='RecurrentPPO' else 'CnnPolicy' \n", + " env=make_atari_env(env_name,n_envs=6)\n", + " env=VecFrameStack(env, n_stack=6)\n", + " print('******* Evaluating', algo_name,' *******')\n", + " log_path, render_path, model_path=call_paths(algo_name,env_name,n_steps)\n", + " model_name=env_name+\"_\"+algo_name+\"_model\"\n", + " model=eval(algo_name).load(os.path.join(model_path,model_name),env,device=device)\n", + " mean_rew, mean_std=evaluate_policy(model,env, n_eval_episodes=n_episodes)\n", + " rewards_mean[algo_name]=mean_rew\n", + " rewards_std[algo_name]=mean_std\n", + " print('Mean rewards for ',n_episodes, ' episodes of ',algo_name,' is ',mean_rew,'\\n')\n", + " del model\n", + " env.close()\n", + " return rewards_mean,rewards_std" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "66a2bd41", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "******* Evaluating TRPO *******\n", + "Wrapping the env in a VecTransposeImage.\n", + "Mean rewards for 100 episodes of TRPO is 2.06 \n", + "\n", + "******* Evaluating RecurrentPPO *******\n", + "Wrapping the env in a VecTransposeImage.\n", + "Mean rewards for 100 episodes of RecurrentPPO is 4.39 \n", + "\n", + "******* Evaluating QRDQN *******\n", + "Wrapping the env in a VecTransposeImage.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "E:\\Anaconda\\envs\\ai_gym\\lib\\site-packages\\stable_baselines3\\common\\buffers.py:229: UserWarning: This system does not have apparently enough memory to store the complete replay buffer 84.69GB > 10.70GB\n", + " \"This system does not have apparently enough memory to store the complete \"\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Mean rewards for 100 episodes of QRDQN is 2.12 \n", + "\n" + ] + } + ], + "source": [ + "rewards=evaluate_experiment(algo_list, env_name)" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "0a4d7aa0", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
    " + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plot_mean(rewards[0],'mean rewards')" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "46b5aa97", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
    " + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plot_mean(rewards[1],'std deviation')" + ] + }, + { + "cell_type": "markdown", + "id": "719d552f", + "metadata": {}, + "source": [ + "Hence, we see that:\n", + "
    1. RecurrentPPO has the highest rewards (2.1x TRPO and 2x QRDQN)
    2. \n", + "
    3. It also has the highest std deviation (1.8x TRPO and 2X QRDQN)
    4. \n", + "
    5. Similarly, A2C has 9% higher reward than PPO but 1.3X its std deviation
    6. \n", + " \n", + "Given that ReccurrentPPO seems to be the highest rewards we will use it for the next set of 5,000,000 steps" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.0" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/2c_Breakout-v0-recurrent_Test.ipynb b/2c_Breakout-v0-recurrent_Test.ipynb new file mode 100644 index 0000000..ce99ab4 --- /dev/null +++ b/2c_Breakout-v0-recurrent_Test.ipynb @@ -0,0 +1,245 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "7d1fa20c", + "metadata": {}, + "outputs": [], + "source": [ + "import os, sys\n", + "import gc\n", + "import matplotlib.pyplot as plt\n", + "import numpy as np" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "759b713c", + "metadata": {}, + "outputs": [], + "source": [ + "sys.path.append('../')\n", + "import torch" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "c8c767df", + "metadata": {}, + "outputs": [], + "source": [ + "from get_algos import get_all_algos , run_experiment ,call_paths, plot_mean" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "c9fc3531", + "metadata": {}, + "outputs": [], + "source": [ + "import gym\n", + "from sb3_contrib import QRDQN ,RecurrentPPO, TRPO\n", + "from stable_baselines3.common.vec_env import VecFrameStack,VecVideoRecorder\n", + "from stable_baselines3.common.evaluation import evaluate_policy\n", + "from stable_baselines3.common.env_util import make_atari_env\n", + "from stable_baselines3.common.monitor import Monitor" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "ed55ba4d", + "metadata": {}, + "outputs": [], + "source": [ + "env_name='Breakout-v0'" + ] + }, + { + "cell_type": "markdown", + "id": "54c5cdd5", + "metadata": {}, + "source": [ + "### 1. Test\n", + "
        \n", + "
      1. Create the environment
      2. \n", + "
      3. For each algorithm:
      4. \n", + "
        1. Load the model
        2. \n", + "
        3. Evaluate the model for 5 sample iterations
        4. \n", + "
        5. Output the score for each algo and each iteration
        6. \n", + "
        7. Render the video and store it
        8. \n", + "
        \n", + "
      " + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "65fae03b", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['QRDQN', 'RecurrentPPO', 'TRPO']\n" + ] + } + ], + "source": [ + "env_recurrent_type={'Discrete':['MaskablePPO', 'QRDQN', 'RecurrentPPO', 'TRPO'],'Box':['ARS', 'RecurrentPPO', 'TQC', 'TRPO'], \n", + " 'MultiDiscrete':['MaskablePPO', 'RecurrentPPO', 'TRPO'],'MultiBinary':['MaskablePPO', 'RecurrentPPO', 'TRPO']}\n", + "def get_algo_recurrent(env):\n", + " act_space=str(type(env.action_space)).split('.')[3].split(\"'\")[0]\n", + " return env_recurrent_type[act_space]\n", + "\n", + "algo_list=get_algo_recurrent(gym.make(env_name))\n", + "algo_list.remove('MaskablePPO') if 'MaskablePPO' in algo_list else algo_list\n", + "print(algo_list)" + ] + }, + { + "cell_type": "markdown", + "id": "7e8fab60", + "metadata": {}, + "source": [ + "### 3. Testing" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "972110da", + "metadata": {}, + "outputs": [], + "source": [ + "def testing_model(algo_list, env_name,n_steps,vid_length):\n", + " total_rewards={}\n", + " for algo_name in reversed(algo_list):\n", + " algo_rewards=[]\n", + " if algo_name =='QRDQN' or 'TRPO':\n", + " device='cpu'\n", + " else:\n", + " device='cuda' #GPU was unable to load the entire experience relay so moved to virtual memory on disk\n", + " policy='CnnLstmPolicy' if algo_name=='RecurrentPPO' else 'CnnPolicy'\n", + " log_path, render_path, model_path=call_paths(algo_name,env_name,n_steps)\n", + " env=VecVideoRecorder(VecFrameStack(make_atari_env(env_name,monitor_dir=render_path),n_stack=6),render_path,record_video_trigger=lambda step: step == 0,video_length=vid_length)\n", + " model_name=env_name+\"_\"+algo_name+\"_model\"\n", + " model=eval(algo_name).load(os.path.join(model_path, model_name),env,device=device)\n", + " for i in range(5):\n", + " state=env.reset()\n", + " epi_rewards=0\n", + " while True:\n", + " action,_=model.predict(state)\n", + " state,reward,done,_=env.step(action)\n", + " epi_rewards+=reward[0]\n", + " env.render()\n", + " if done:\n", + " algo_rewards.append(epi_rewards)\n", + " break\n", + " total_rewards[algo_name]=algo_rewards\n", + " del model\n", + " env.close()\n", + " return total_rewards" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "2f2d2d60", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Wrapping the env in a VecTransposeImage.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "E:\\Anaconda\\envs\\ai_gym\\lib\\site-packages\\gym\\envs\\atari\\environment.py:269: UserWarning: \u001b[33mWARN: We strongly suggest supplying `render_mode` when constructing your environment, e.g., gym.make(ID, render_mode='human'). Using `render_mode` provides access to proper scaling, audio support, and proper framerates.\u001b[0m\n", + " \"We strongly suggest supplying `render_mode` when \"\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Wrapping the env in a VecTransposeImage.\n", + "Wrapping the env in a VecTransposeImage.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "E:\\Anaconda\\envs\\ai_gym\\lib\\site-packages\\stable_baselines3\\common\\buffers.py:229: UserWarning: This system does not have apparently enough memory to store the complete replay buffer 84.69GB > 10.47GB\n", + " \"This system does not have apparently enough memory to store the complete \"\n" + ] + } + ], + "source": [ + "test=total_rewards=testing_model(algo_list, env_name,n_steps=200000,vid_length=1000)" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "63f6b45f", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'TRPO': [0.0, 0.0, 0.0, 0.0, 0.0],\n", + " 'RecurrentPPO': [0.0, 5.0, 0.0, 0.0, 0.0],\n", + " 'QRDQN': [0.0, 0.0, 2.0, 1.0, 0.0]}" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "test" + ] + }, + { + "cell_type": "markdown", + "id": "870561de", + "metadata": {}, + "source": [ + "We see that RecurrentPPO seems to consistently provide rewards with the highest average reward. Hence, we will use RecurrentPPO as the algorithm for subsequent training of 5,000,000 steps" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.0" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/3a_Breakout-v0_final_train.ipynb b/3a_Breakout-v0_final_train.ipynb new file mode 100644 index 0000000..68509c4 --- /dev/null +++ b/3a_Breakout-v0_final_train.ipynb @@ -0,0 +1,340 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "7d1fa20c", + "metadata": {}, + "outputs": [], + "source": [ + "import os, sys\n", + "import gc\n", + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "98159a81", + "metadata": {}, + "outputs": [], + "source": [ + "sys.path.append('../')\n", + "import torch" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "c8c767df", + "metadata": {}, + "outputs": [], + "source": [ + "from get_algos import get_all_algos , run_experiment ,create_paths" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "c9fc3531", + "metadata": {}, + "outputs": [], + "source": [ + "import gym\n", + "from sb3_contrib import RecurrentPPO\n", + "from stable_baselines3 import PPO\n", + "from stable_baselines3.common.vec_env import VecFrameStack\n", + "from stable_baselines3.common.evaluation import evaluate_policy\n", + "from stable_baselines3.common.env_util import make_atari_env" + ] + }, + { + "cell_type": "markdown", + "id": "e1d33e3c", + "metadata": {}, + "source": [ + "### 1. Explore breakout environment\n", + "
        \n", + "
      • Explore the environment
      • \n", + "
      " + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "1aad3196", + "metadata": {}, + "outputs": [], + "source": [ + "env_name='Breakout-v0'\n", + "env=gym.make(env_name)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "df2cd276", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Action space: Discrete(4)\n", + "Observation space shape: Box([[[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " ...\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]\n", + "\n", + " [[0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]\n", + " ...\n", + " [0 0 0]\n", + " [0 0 0]\n", + " [0 0 0]]], [[[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " ...\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]\n", + "\n", + " [[255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]\n", + " ...\n", + " [255 255 255]\n", + " [255 255 255]\n", + " [255 255 255]]], (210, 160, 3), uint8)\n", + "Action space shape: ()\n", + "Observation space shape: (210, 160, 3)\n" + ] + } + ], + "source": [ + "print('Action space: ',env.action_space)\n", + "print('Observation space shape: ',env.observation_space)\n", + "print('Action space shape: ',env.action_space.shape)\n", + "print('Observation space shape: ',env.observation_space.shape)" + ] + }, + { + "cell_type": "markdown", + "id": "a195559a", + "metadata": {}, + "source": [ + "#Taking a look at how breakout looks and simulate random actions\n", + "env.reset()\n", + "rewards_all=[]\n", + "for epi in range(50):\n", + " state=env.reset()\n", + " rewards=0\n", + " while True:\n", + " action=env.action_space.sample()\n", + " state,reward,done,_=env.step(action)\n", + " env.render()\n", + " rewards+=reward\n", + " if done:\n", + " rewards_all.append(rewards)\n", + " if (epi+1)%5==0:\n", + " print('Episode: ',epi+1,' Reward: ',rewards)\n", + " break \n", + "env.close()\n", + "print('Average rewards for random action Breakout-v0 is: ',sum(rewards_all)/len(rewards_all))" + ] + }, + { + "cell_type": "markdown", + "id": "54c5cdd5", + "metadata": {}, + "source": [ + "### 2. Training\n", + "
        \n", + "
      1. Make the atari env using make_atari_env
      2. \n", + "
      3. Parallelize the learning using VecFrameStack
      4. \n", + "
      5. Create train function for all appropriate algos
      6. \n", + "
      7. Train
      8. \n", + "
      9. Store model
      10. \n", + "
      " + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "00e701da", + "metadata": {}, + "outputs": [], + "source": [ + "def train_breakout(algo_name, env_name,n_steps,device='cuda'):\n", + " policy='CnnLstmPolicy' if algo_name=='RecurrentPPO' else 'CnnPolicy'\n", + " log_path, render_path, model_path=create_paths(algo_name,env_name,n_steps)\n", + " env=make_atari_env(env_name,n_envs=6)\n", + " env=VecFrameStack(env, n_stack=6)\n", + " model=eval(algo_name)(policy,env, tensorboard_log=log_path,device=device)\n", + " model.learn(n_steps)\n", + " model.save(os.path.join(model_path,env_name+\"_\"+algo_name+\"_\"+\"model\"))\n", + " del model\n", + " env.close()\n", + "\n", + " return log_path, render_path, model_path" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "65fae03b", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['PPO', 'RecurrentPPO']\n" + ] + } + ], + "source": [ + "algo_list=['PPO','RecurrentPPO']\n", + "print(algo_list)" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "ebcf18c9", + "metadata": {}, + "outputs": [], + "source": [ + "models_records={}\n", + "n_steps=5000000" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "52178f03", + "metadata": {}, + "outputs": [], + "source": [ + "def train_experiment(algo_list, env_name,n_steps):\n", + " for algo in reversed(algo_list):\n", + " print('******* Training ',algo,' *******')\n", + " log_path, render_path, model_path=train_breakout(algo, env_name,n_steps)\n", + " gc.collect()\n", + " torch.cuda.empty_cache()" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "0a4d7aa0", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "******* Training RecurrentPPO *******\n", + "******* Training PPO *******\n" + ] + } + ], + "source": [ + "train_experiment(algo_list, env_name,n_steps)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.0" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/3b_Breakout-v0-final_Evaluate.ipynb b/3b_Breakout-v0-final_Evaluate.ipynb new file mode 100644 index 0000000..72a2981 --- /dev/null +++ b/3b_Breakout-v0-final_Evaluate.ipynb @@ -0,0 +1,213 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "7d1fa20c", + "metadata": {}, + "outputs": [], + "source": [ + "import os, sys\n", + "import gc\n", + "import matplotlib.pyplot as plt\n", + "import numpy as np" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "bb837082", + "metadata": {}, + "outputs": [], + "source": [ + "sys.path.append('../')\n", + "import torch" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "c8c767df", + "metadata": {}, + "outputs": [], + "source": [ + "from get_algos import get_all_algos , run_experiment ,call_paths, plot_mean" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "c9fc3531", + "metadata": {}, + "outputs": [], + "source": [ + "import gym\n", + "from gym.wrappers import Monitor\n", + "from sb3_contrib import RecurrentPPO\n", + "from stable_baselines3 import PPO\n", + "from stable_baselines3.common.vec_env import VecFrameStack\n", + "from stable_baselines3.common.evaluation import evaluate_policy\n", + "from stable_baselines3.common.env_util import make_atari_env" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "5f7370b2", + "metadata": {}, + "outputs": [], + "source": [ + "env_name='Breakout-v0'" + ] + }, + { + "cell_type": "markdown", + "id": "54c5cdd5", + "metadata": {}, + "source": [ + "### 2. Evaluation\n", + "
        \n", + "
      1. Create the environment
      2. \n", + "
      3. For each algorithm:
      4. \n", + "
        1. Load the model
        2. \n", + "
        3. Evaluate the model for 5 sample iterations
        4. \n", + "
        5. Output the score for each algo and each iteration
        6. \n", + "
        7. Assess stability of the model based on the variance / standard deviation
        8. \n", + "
        \n", + "
      5. Plot the corresponding scores
      6. \n", + "
      " + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "65fae03b", + "metadata": {}, + "outputs": [], + "source": [ + "algo_list=['PPO','RecurrentPPO']" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "52178f03", + "metadata": {}, + "outputs": [], + "source": [ + "def evaluate_experiment(algo_list, env_name,n_steps=200000,n_episodes=100):\n", + " rewards_mean={}\n", + " rewards_std={}\n", + " for algo_name in reversed(algo_list):\n", + " if algo_name =='QRDQN' or 'TRPO':\n", + " device='cpu'\n", + " else:\n", + " device='cuda' #GPU was unable to load the entire experience relay so moved to virtual memory on disk\n", + " policy='CnnLstmPolicy' if algo_name=='RecurrentPPO' else 'CnnPolicy' \n", + " env=make_atari_env(env_name,n_envs=6)\n", + " env=VecFrameStack(env, n_stack=6)\n", + " print('******* Evaluating', algo_name,' *******')\n", + " log_path, render_path, model_path=call_paths(algo_name,env_name,n_steps)\n", + " model_name=env_name+\"_\"+algo_name+\"_model\"\n", + " model=eval(algo_name).load(os.path.join(model_path,model_name),env,device=device)\n", + " mean_rew, mean_std=evaluate_policy(model,env, n_eval_episodes=n_episodes)\n", + " rewards_mean[algo_name]=mean_rew\n", + " rewards_std[algo_name]=mean_std\n", + " print('Mean rewards for ',n_episodes, ' episodes of ',algo_name,' is ',mean_rew,'\\n')\n", + " del model\n", + " env.close()\n", + " return rewards_mean,rewards_std" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "66a2bd41", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "******* Evaluating RecurrentPPO *******\n", + "Mean rewards for 100 episodes of RecurrentPPO is 3.46 \n", + "\n", + "******* Evaluating PPO *******\n", + "Mean rewards for 100 episodes of PPO is 12.41 \n", + "\n" + ] + } + ], + "source": [ + "rewards=evaluate_experiment(algo_list, env_name,n_steps=5000000)" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "0a4d7aa0", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
      " + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plot_mean(rewards[0],'mean rewards')" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "46b5aa97", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
      " + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plot_mean(rewards[1],'std deviation')" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.0" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/3c_Breakout-v0-final_Test.ipynb b/3c_Breakout-v0-final_Test.ipynb new file mode 100644 index 0000000..3fdca8e --- /dev/null +++ b/3c_Breakout-v0-final_Test.ipynb @@ -0,0 +1,194 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "7d1fa20c", + "metadata": {}, + "outputs": [], + "source": [ + "import os, sys\n", + "import gc\n", + "import matplotlib.pyplot as plt\n", + "import numpy as np" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "db524d19", + "metadata": {}, + "outputs": [], + "source": [ + "sys.path.append('../')\n", + "import torch" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "c8c767df", + "metadata": {}, + "outputs": [], + "source": [ + "from get_algos import get_all_algos , run_experiment ,call_paths, plot_mean" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "c9fc3531", + "metadata": {}, + "outputs": [], + "source": [ + "import gym\n", + "from sb3_contrib import RecurrentPPO\n", + "from gym.wrappers.monitor import Monitor\n", + "from stable_baselines3 import PPO\n", + "from stable_baselines3.common.vec_env import VecFrameStack,VecVideoRecorder\n", + "from stable_baselines3.common.evaluation import evaluate_policy\n", + "from stable_baselines3.common.env_util import make_atari_env" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "ed55ba4d", + "metadata": {}, + "outputs": [], + "source": [ + "env_name='Breakout-v0'" + ] + }, + { + "cell_type": "markdown", + "id": "54c5cdd5", + "metadata": {}, + "source": [ + "### 1. Test\n", + "
        \n", + "
      1. Create the environment
      2. \n", + "
      3. For each algorithm:
      4. \n", + "
        1. Load the model
        2. \n", + "
        3. Evaluate the model for 5 sample iterations
        4. \n", + "
        5. Output the score for each algo and each iteration
        6. \n", + "
        7. Render the video and store it
        8. \n", + "
        \n", + "
      " + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "65fae03b", + "metadata": {}, + "outputs": [], + "source": [ + "algo_list=['PPO','RecurrentPPO']" + ] + }, + { + "cell_type": "markdown", + "id": "7e8fab60", + "metadata": {}, + "source": [ + "### 3. Testing" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "972110da", + "metadata": {}, + "outputs": [], + "source": [ + "def testing_model(algo_list, env_name,n_steps,vid_length):\n", + " total_rewards={}\n", + " for algo_name in reversed(algo_list):\n", + " algo_rewards=[]\n", + " if algo_name =='QRDQN' or 'TRPO':\n", + " device='cpu'\n", + " else:\n", + " device='cuda' #GPU was unable to load the entire experience relay so moved to virtual memory on disk\n", + " policy='CnnLstmPolicy' if algo_name=='RecurrentPPO' else 'CnnPolicy'\n", + " log_path, render_path, model_path=call_paths(algo_name,env_name,n_steps)\n", + " env=VecVideoRecorder(VecFrameStack(make_atari_env(env_name,monitor_dir=render_path),n_stack=6),render_path,record_video_trigger=lambda step: step == 0,video_length=vid_length)\n", + " model_name=env_name+\"_\"+algo_name+\"_model\"\n", + " model=eval(algo_name).load(os.path.join(model_path, model_name),env,device=device)\n", + " for i in range(5):\n", + " state=env.reset()\n", + " epi_rewards=0\n", + " while True:\n", + " action,_=model.predict(state)\n", + " state,reward,done,_=env.step(action)\n", + " epi_rewards+=reward[0]\n", + " env.render()\n", + " if done:\n", + " algo_rewards.append(epi_rewards)\n", + " break\n", + " total_rewards[algo_name]=algo_rewards\n", + " del model\n", + " env.close()\n", + " return total_rewards" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "86523f39", + "metadata": {}, + "outputs": [], + "source": [ + "total_rewards=testing_model(algo_list, env_name,n_steps=5000000,vid_length=1000)" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "4f3794bb", + "metadata": {}, + "outputs": [], + "source": [ + "rand_env_reward={}\n", + "for algo in reversed(algo_list):\n", + " render_path_random=os.path.join(env_name,algo+'_'+'5000000','render','random')\n", + " env=Monitor(gym.make(env_name),directory=render_path_random,force=True)\n", + " total_rewards=[]\n", + " for i in range(5):\n", + " epi_rewards=0\n", + " env.reset()\n", + " while True:\n", + " action=env.action_space.sample()\n", + " _,rewards,done,_=env.step(action)\n", + " epi_rewards+=rewards\n", + " env.render()\n", + " if done:\n", + " total_rewards.append(epi_rewards)\n", + " break\n", + " env.close()\n", + " rand_env_reward[algo]=total_rewards " + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.0" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/A2C_200000/README.md b/A2C_200000/README.md new file mode 100644 index 0000000..461df4e --- /dev/null +++ b/A2C_200000/README.md @@ -0,0 +1,17 @@ +# A2C with 200000 steps + +## Reference +[Asynchronous Methods for Deep Reinforcement Learning](https://arxiv.org/abs/1602.01783) + +## Parameters +Default parameters as per [Stable Baselines](https://stable-baselines3.readthedocs.io/en/master/modules/a2c.html) + +## Performance logs +![Trained model](logs/tensorboard.png) + +## Renders +1. Random
      +![Random agent](render/random.gif) + +2. Modelled
      +![Modelled agent](render/Modelled.gif) diff --git a/A2C_200000/logs/A2C_1/events.out.tfevents.1660743213.Merlin.10876.1 b/A2C_200000/logs/A2C_1/events.out.tfevents.1660743213.Merlin.10876.1 new file mode 100644 index 0000000..6d69efc Binary files /dev/null and b/A2C_200000/logs/A2C_1/events.out.tfevents.1660743213.Merlin.10876.1 differ diff --git a/A2C_200000/logs/tensorboard.png b/A2C_200000/logs/tensorboard.png new file mode 100644 index 0000000..707b4f9 Binary files /dev/null and b/A2C_200000/logs/tensorboard.png differ diff --git a/A2C_200000/models/Breakout-v0_A2C_model.zip b/A2C_200000/models/Breakout-v0_A2C_model.zip new file mode 100644 index 0000000..477994c Binary files /dev/null and b/A2C_200000/models/Breakout-v0_A2C_model.zip differ diff --git a/A2C_200000/render/Modelled.gif b/A2C_200000/render/Modelled.gif new file mode 100644 index 0000000..27ca4be Binary files /dev/null and b/A2C_200000/render/Modelled.gif differ diff --git a/A2C_200000/render/Modelled.mp4 b/A2C_200000/render/Modelled.mp4 new file mode 100644 index 0000000..a9f5382 Binary files /dev/null and b/A2C_200000/render/Modelled.mp4 differ diff --git a/A2C_200000/render/random.gif b/A2C_200000/render/random.gif new file mode 100644 index 0000000..d3ee619 Binary files /dev/null and b/A2C_200000/render/random.gif differ diff --git a/A2C_200000/render/random.mp4 b/A2C_200000/render/random.mp4 new file mode 100644 index 0000000..c8f0ecb Binary files /dev/null and b/A2C_200000/render/random.mp4 differ diff --git a/A2C_5000000/README.md b/A2C_5000000/README.md new file mode 100644 index 0000000..9eb4b05 --- /dev/null +++ b/A2C_5000000/README.md @@ -0,0 +1,17 @@ +# A2C with 5M steps + +## Reference +[Asynchronous Methods for Deep Reinforcement Learning](https://arxiv.org/abs/1602.01783) + +## Parameters +Default parameters as per [Stable Baselines](https://stable-baselines3.readthedocs.io/en/master/modules/a2c.html) + +## Performance logs +![Trained model](logs/Tensorboard.png) + +## Renders +1. Random
      +![Random agent](render/random.gif) + +2. Modelled
      +![Modelled agent](render/Modelled.gif) diff --git a/A2C_5000000/logs/A2C_1/events.out.tfevents.1661183280.Merlin.3528.0 b/A2C_5000000/logs/A2C_1/events.out.tfevents.1661183280.Merlin.3528.0 new file mode 100644 index 0000000..ed3f709 Binary files /dev/null and b/A2C_5000000/logs/A2C_1/events.out.tfevents.1661183280.Merlin.3528.0 differ diff --git a/A2C_5000000/logs/Tensorboard.png b/A2C_5000000/logs/Tensorboard.png new file mode 100644 index 0000000..a994cfb Binary files /dev/null and b/A2C_5000000/logs/Tensorboard.png differ diff --git a/A2C_5000000/models/Breakout-v0_A2C_model.zip b/A2C_5000000/models/Breakout-v0_A2C_model.zip new file mode 100644 index 0000000..861159c Binary files /dev/null and b/A2C_5000000/models/Breakout-v0_A2C_model.zip differ diff --git a/A2C_5000000/render/Modelled.gif b/A2C_5000000/render/Modelled.gif new file mode 100644 index 0000000..7fa0e94 Binary files /dev/null and b/A2C_5000000/render/Modelled.gif differ diff --git a/A2C_5000000/render/Modelled.mp4 b/A2C_5000000/render/Modelled.mp4 new file mode 100644 index 0000000..731b218 Binary files /dev/null and b/A2C_5000000/render/Modelled.mp4 differ diff --git a/A2C_5000000/render/random.gif b/A2C_5000000/render/random.gif new file mode 100644 index 0000000..d3ee619 Binary files /dev/null and b/A2C_5000000/render/random.gif differ diff --git a/A2C_5000000/render/random.mp4 b/A2C_5000000/render/random.mp4 new file mode 100644 index 0000000..c8f0ecb Binary files /dev/null and b/A2C_5000000/render/random.mp4 differ diff --git a/DQN_200000/Readme.md b/DQN_200000/Readme.md new file mode 100644 index 0000000..910cf37 --- /dev/null +++ b/DQN_200000/Readme.md @@ -0,0 +1,17 @@ +# DQN with 20000 steps + +## Reference +[Playing Atari with Deep Reinforcement Learning](https://arxiv.org/abs/1312.5602) + +## Parameters +Default parameters as per [Stable Baselines](https://stable-baselines3.readthedocs.io/en/master/modules/dqn.html) + +## Performance logs +![Trained model](logs/tensorboard.png) + +## Renders +1. Random
      +![Random agent](render/random.gif) + +2. Modelled
      +![Modelled agent](render/Modelled.gif) diff --git a/DQN_200000/logs/DQN_1/events.out.tfevents.1660739886.Merlin.10876.0 b/DQN_200000/logs/DQN_1/events.out.tfevents.1660739886.Merlin.10876.0 new file mode 100644 index 0000000..7f1fdc8 Binary files /dev/null and b/DQN_200000/logs/DQN_1/events.out.tfevents.1660739886.Merlin.10876.0 differ diff --git a/DQN_200000/logs/tensorboard.png b/DQN_200000/logs/tensorboard.png new file mode 100644 index 0000000..d3f84b2 Binary files /dev/null and b/DQN_200000/logs/tensorboard.png differ diff --git a/DQN_200000/models/Breakout-v0_DQN_model.zip b/DQN_200000/models/Breakout-v0_DQN_model.zip new file mode 100644 index 0000000..81c91ed Binary files /dev/null and b/DQN_200000/models/Breakout-v0_DQN_model.zip differ diff --git a/DQN_200000/render/Modelled.gif b/DQN_200000/render/Modelled.gif new file mode 100644 index 0000000..65e5452 Binary files /dev/null and b/DQN_200000/render/Modelled.gif differ diff --git a/DQN_200000/render/Modelled.mp4 b/DQN_200000/render/Modelled.mp4 new file mode 100644 index 0000000..4d41ae5 Binary files /dev/null and b/DQN_200000/render/Modelled.mp4 differ diff --git a/DQN_200000/render/random.gif b/DQN_200000/render/random.gif new file mode 100644 index 0000000..d3ee619 Binary files /dev/null and b/DQN_200000/render/random.gif differ diff --git a/DQN_200000/render/random.mp4 b/DQN_200000/render/random.mp4 new file mode 100644 index 0000000..c8f0ecb Binary files /dev/null and b/DQN_200000/render/random.mp4 differ diff --git a/DQN_5000000/Readme.md b/DQN_5000000/Readme.md new file mode 100644 index 0000000..0d3d406 --- /dev/null +++ b/DQN_5000000/Readme.md @@ -0,0 +1,18 @@ +# DQN with 5M steps + +## Reference +[Playing Atari with Deep Reinforcement Learning](https://arxiv.org/abs/1312.5602) + +## Parameters +Default parameters as per [Stable Baselines](https://stable-baselines3.readthedocs.io/en/master/modules/dqn.html)\ +buffer_relay parameter set to 39500 instead of 1M to allow for limitations in graphics card memory + +## Performance logs +![Trained model](logs/TensorBoard.png) + +## Renders +1. Random
      +![Random agent](render/random.gif) + +2. Modelled
      +![Modelled agent](render/Modelled.gif) diff --git a/DQN_5000000/logs/DQN_1/events.out.tfevents.1661141567.Merlin.10252.0 b/DQN_5000000/logs/DQN_1/events.out.tfevents.1661141567.Merlin.10252.0 new file mode 100644 index 0000000..030e0e4 Binary files /dev/null and b/DQN_5000000/logs/DQN_1/events.out.tfevents.1661141567.Merlin.10252.0 differ diff --git a/DQN_5000000/logs/TensorBoard.png b/DQN_5000000/logs/TensorBoard.png new file mode 100644 index 0000000..c2e69a6 Binary files /dev/null and b/DQN_5000000/logs/TensorBoard.png differ diff --git a/DQN_5000000/models/Breakout-v0_DQN_model.zip b/DQN_5000000/models/Breakout-v0_DQN_model.zip new file mode 100644 index 0000000..00c2c5f Binary files /dev/null and b/DQN_5000000/models/Breakout-v0_DQN_model.zip differ diff --git a/DQN_5000000/render/Modelled.gif b/DQN_5000000/render/Modelled.gif new file mode 100644 index 0000000..5c5dd5e Binary files /dev/null and b/DQN_5000000/render/Modelled.gif differ diff --git a/DQN_5000000/render/Modelled.mp4 b/DQN_5000000/render/Modelled.mp4 new file mode 100644 index 0000000..84cd61b Binary files /dev/null and b/DQN_5000000/render/Modelled.mp4 differ diff --git a/DQN_5000000/render/random.gif b/DQN_5000000/render/random.gif new file mode 100644 index 0000000..d3ee619 Binary files /dev/null and b/DQN_5000000/render/random.gif differ diff --git a/DQN_5000000/render/random.mp4 b/DQN_5000000/render/random.mp4 new file mode 100644 index 0000000..c8f0ecb Binary files /dev/null and b/DQN_5000000/render/random.mp4 differ diff --git a/Evaluation_across_models.png b/Evaluation_across_models.png new file mode 100644 index 0000000..5f893be Binary files /dev/null and b/Evaluation_across_models.png differ diff --git a/PPO_200000/Readme.md b/PPO_200000/Readme.md new file mode 100644 index 0000000..6c8a31e --- /dev/null +++ b/PPO_200000/Readme.md @@ -0,0 +1,17 @@ +# PPO with 20000 steps + +## Reference +[Proximal Policy Optimization Algorithms](https://arxiv.org/abs/1312.5602) + +## Parameters +Default parameters as per [Stable Baselines](https://stable-baselines3.readthedocs.io/en/master/modules/ppo.html) + +## Performance logs +![Trained model](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/PPO_200000/logs/tensorboard.png) + +## Renders +1. Random
      +![Random agent](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/PPO_200000/render/random.gif) + +2. Modelled
      +![Modelled agent](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/PPO_200000/render/Modelled.gif) diff --git a/PPO_200000/logs/PPO_1/events.out.tfevents.1660744801.Merlin.10876.2 b/PPO_200000/logs/PPO_1/events.out.tfevents.1660744801.Merlin.10876.2 new file mode 100644 index 0000000..824d8ad Binary files /dev/null and b/PPO_200000/logs/PPO_1/events.out.tfevents.1660744801.Merlin.10876.2 differ diff --git a/PPO_200000/logs/tensorboard.png b/PPO_200000/logs/tensorboard.png new file mode 100644 index 0000000..8506b79 Binary files /dev/null and b/PPO_200000/logs/tensorboard.png differ diff --git a/PPO_200000/models/Breakout-v0_PPO_model.zip b/PPO_200000/models/Breakout-v0_PPO_model.zip new file mode 100644 index 0000000..3c5e6b9 Binary files /dev/null and b/PPO_200000/models/Breakout-v0_PPO_model.zip differ diff --git a/PPO_200000/render/Modelled.gif b/PPO_200000/render/Modelled.gif new file mode 100644 index 0000000..39cbc68 Binary files /dev/null and b/PPO_200000/render/Modelled.gif differ diff --git a/PPO_200000/render/Modelled.mp4 b/PPO_200000/render/Modelled.mp4 new file mode 100644 index 0000000..71c64fb Binary files /dev/null and b/PPO_200000/render/Modelled.mp4 differ diff --git a/PPO_200000/render/random.gif b/PPO_200000/render/random.gif new file mode 100644 index 0000000..d3ee619 Binary files /dev/null and b/PPO_200000/render/random.gif differ diff --git a/PPO_200000/render/random.mp4 b/PPO_200000/render/random.mp4 new file mode 100644 index 0000000..c8f0ecb Binary files /dev/null and b/PPO_200000/render/random.mp4 differ diff --git a/PPO_5000000/Readme.md b/PPO_5000000/Readme.md new file mode 100644 index 0000000..4b15ddd --- /dev/null +++ b/PPO_5000000/Readme.md @@ -0,0 +1,17 @@ +# PPO with 5M steps + +## Reference +[Proximal Policy Optimization Algorithms](https://arxiv.org/abs/1312.5602) + +## Parameters +Default parameters as per [Stable Baselines](https://stable-baselines3.readthedocs.io/en/master/modules/ppo.html) + +## Performance logs +![Trained model](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/DQN_5000000/logs/TensorBoard.png) + +## Renders +1. Random
      +![Random agent](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/PPO_5000000/render/random.gif) + +2. Modelled
      +![Modelled agent](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/PPO_5000000/render/Modelled.gif) diff --git a/PPO_5000000/logs/PPO_1/events.out.tfevents.1661014405.Merlin.4132.1 b/PPO_5000000/logs/PPO_1/events.out.tfevents.1661014405.Merlin.4132.1 new file mode 100644 index 0000000..3293423 Binary files /dev/null and b/PPO_5000000/logs/PPO_1/events.out.tfevents.1661014405.Merlin.4132.1 differ diff --git a/PPO_5000000/logs/PPO_2/events.out.tfevents.1661207207.Merlin.12196.0 b/PPO_5000000/logs/PPO_2/events.out.tfevents.1661207207.Merlin.12196.0 new file mode 100644 index 0000000..a12a521 Binary files /dev/null and b/PPO_5000000/logs/PPO_2/events.out.tfevents.1661207207.Merlin.12196.0 differ diff --git a/PPO_5000000/logs/Tensorboard.png b/PPO_5000000/logs/Tensorboard.png new file mode 100644 index 0000000..6ae48b4 Binary files /dev/null and b/PPO_5000000/logs/Tensorboard.png differ diff --git a/PPO_5000000/models/Breakout-v0_PPO_model.zip b/PPO_5000000/models/Breakout-v0_PPO_model.zip new file mode 100644 index 0000000..84de66f Binary files /dev/null and b/PPO_5000000/models/Breakout-v0_PPO_model.zip differ diff --git a/PPO_5000000/render/Modelled.gif b/PPO_5000000/render/Modelled.gif new file mode 100644 index 0000000..542ba83 Binary files /dev/null and b/PPO_5000000/render/Modelled.gif differ diff --git a/PPO_5000000/render/Modelled.mp4 b/PPO_5000000/render/Modelled.mp4 new file mode 100644 index 0000000..704fa58 Binary files /dev/null and b/PPO_5000000/render/Modelled.mp4 differ diff --git a/PPO_5000000/render/random.gif b/PPO_5000000/render/random.gif new file mode 100644 index 0000000..d3ee619 Binary files /dev/null and b/PPO_5000000/render/random.gif differ diff --git a/PPO_5000000/render/random.mp4 b/PPO_5000000/render/random.mp4 new file mode 100644 index 0000000..c8f0ecb Binary files /dev/null and b/PPO_5000000/render/random.mp4 differ diff --git a/QRDQN_200000/Readme.md b/QRDQN_200000/Readme.md new file mode 100644 index 0000000..e6878ea --- /dev/null +++ b/QRDQN_200000/Readme.md @@ -0,0 +1,17 @@ +# QR-DQN with 200K steps + +## Reference +[A Distributional Perspective on Reinforcement Learning](https://arxiv.org/abs/1707.06887) + +## Parameters +Default parameters as per [Stable Baselines](https://sb3-contrib.readthedocs.io/en/master/modules/qrdqn.html) + +## Performance logs +![Trained model](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/QRDQN_200000/logs/Tensorboard.png) + +## Renders +1. Random
      +![Random agent](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/QRDQN_200000/render/random.gif) + +2. Modelled
      +![Modelled agent](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/QRDQN_200000/render/Modelled.gif) diff --git a/QRDQN_200000/logs/QRDQN_1/events.out.tfevents.1660914872.Merlin.3580.0 b/QRDQN_200000/logs/QRDQN_1/events.out.tfevents.1660914872.Merlin.3580.0 new file mode 100644 index 0000000..0bf5472 Binary files /dev/null and b/QRDQN_200000/logs/QRDQN_1/events.out.tfevents.1660914872.Merlin.3580.0 differ diff --git a/QRDQN_200000/logs/Tensorboard.png b/QRDQN_200000/logs/Tensorboard.png new file mode 100644 index 0000000..629eb83 Binary files /dev/null and b/QRDQN_200000/logs/Tensorboard.png differ diff --git a/QRDQN_200000/models/Breakout-v0_QRDQN_model.zip b/QRDQN_200000/models/Breakout-v0_QRDQN_model.zip new file mode 100644 index 0000000..ea52b18 Binary files /dev/null and b/QRDQN_200000/models/Breakout-v0_QRDQN_model.zip differ diff --git a/QRDQN_200000/render/Modelled.gif b/QRDQN_200000/render/Modelled.gif new file mode 100644 index 0000000..1f3addc Binary files /dev/null and b/QRDQN_200000/render/Modelled.gif differ diff --git a/QRDQN_200000/render/Modelled.mp4 b/QRDQN_200000/render/Modelled.mp4 new file mode 100644 index 0000000..6096e65 Binary files /dev/null and b/QRDQN_200000/render/Modelled.mp4 differ diff --git a/QRDQN_200000/render/random.gif b/QRDQN_200000/render/random.gif new file mode 100644 index 0000000..d3ee619 Binary files /dev/null and b/QRDQN_200000/render/random.gif differ diff --git a/QRDQN_200000/render/random.mp4 b/QRDQN_200000/render/random.mp4 new file mode 100644 index 0000000..c8f0ecb Binary files /dev/null and b/QRDQN_200000/render/random.mp4 differ diff --git a/Readme.md b/Readme.md new file mode 100644 index 0000000..2394757 --- /dev/null +++ b/Readme.md @@ -0,0 +1,14 @@ +# Breakout +## Description: +Another famous Atari game. The dynamics are similar to pong: You move a paddle and hit the ball in a brick wall at the top of the screen. Your goal is to destroy the brick wall. You can try to break through the wall and let the ball wreak havoc on the other side, all on its own! You have five lives. Detailed documentation can be found on the AtariAge page. + +## Training steps: +1. Inital exploration across algorithms - 200K +2. Final training for PPO and RecurrentPPO - 5M + +## Results: +### Randomly acting agent: +![Initial](random.gif) + +### Modelled agent +![Trained model](modelled.gif) diff --git a/RecurrentPPO_200000/Readme.md b/RecurrentPPO_200000/Readme.md new file mode 100644 index 0000000..3512195 --- /dev/null +++ b/RecurrentPPO_200000/Readme.md @@ -0,0 +1,17 @@ +# Recurrent PPO with 200K steps + +## Reference +[The 37 Implementation Details of Proximal Policy Optimization](https://iclr-blog-track.github.io/2022/03/25/ppo-implementation-details/) + +## Parameters +Default parameters as per [Stable Baselines](https://sb3-contrib.readthedocs.io/en/master/modules/ppo_recurrent.html) + +## Performance logs +![Trained model](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/RecurrentPPO_200000/logs/Tensorboard.png) + +## Renders +1. Random
      +![Random agent](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/RecurrentPPO_200000/render/random.gif) + +2. Modelled
      +![Modelled agent](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/RecurrentPPO_200000//render/Modelled.gif) diff --git a/RecurrentPPO_200000/logs/RecurrentPPO_1/events.out.tfevents.1660898427.Merlin.14972.1 b/RecurrentPPO_200000/logs/RecurrentPPO_1/events.out.tfevents.1660898427.Merlin.14972.1 new file mode 100644 index 0000000..2157d50 Binary files /dev/null and b/RecurrentPPO_200000/logs/RecurrentPPO_1/events.out.tfevents.1660898427.Merlin.14972.1 differ diff --git a/RecurrentPPO_200000/logs/Tensorboard.png b/RecurrentPPO_200000/logs/Tensorboard.png new file mode 100644 index 0000000..b8bc8f3 Binary files /dev/null and b/RecurrentPPO_200000/logs/Tensorboard.png differ diff --git a/RecurrentPPO_200000/models/Breakout-v0_RecurrentPPO_model.zip b/RecurrentPPO_200000/models/Breakout-v0_RecurrentPPO_model.zip new file mode 100644 index 0000000..27e443f Binary files /dev/null and b/RecurrentPPO_200000/models/Breakout-v0_RecurrentPPO_model.zip differ diff --git a/RecurrentPPO_200000/render/Modelled.gif b/RecurrentPPO_200000/render/Modelled.gif new file mode 100644 index 0000000..b32cfe5 Binary files /dev/null and b/RecurrentPPO_200000/render/Modelled.gif differ diff --git a/RecurrentPPO_200000/render/Modelled.mp4 b/RecurrentPPO_200000/render/Modelled.mp4 new file mode 100644 index 0000000..6a8c775 Binary files /dev/null and b/RecurrentPPO_200000/render/Modelled.mp4 differ diff --git a/RecurrentPPO_200000/render/random.gif b/RecurrentPPO_200000/render/random.gif new file mode 100644 index 0000000..d3ee619 Binary files /dev/null and b/RecurrentPPO_200000/render/random.gif differ diff --git a/RecurrentPPO_200000/render/random.mp4 b/RecurrentPPO_200000/render/random.mp4 new file mode 100644 index 0000000..c8f0ecb Binary files /dev/null and b/RecurrentPPO_200000/render/random.mp4 differ diff --git a/RecurrentPPO_5000000/Readme.md b/RecurrentPPO_5000000/Readme.md new file mode 100644 index 0000000..bb4fd75 --- /dev/null +++ b/RecurrentPPO_5000000/Readme.md @@ -0,0 +1,17 @@ +# Recurrent PPO with 5M steps + +## Reference +[The 37 Implementation Details of Proximal Policy Optimization](https://iclr-blog-track.github.io/2022/03/25/ppo-implementation-details/) + +## Parameters +Default parameters as per [Stable Baselines](https://sb3-contrib.readthedocs.io/en/master/modules/ppo_recurrent.html) + +## Performance logs +![Trained model](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/PPO_5000000/logs/Tensorboard.png) + +## Renders +1. Random
      +![Random agent](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/RecurrentPPO_5000000/render/random.gif) + +2. Modelled
      +![Modelled agent](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/RecurrentPPO_5000000//render/Modelled.gif) diff --git a/RecurrentPPO_5000000/logs/RecurrentPPO_2/events.out.tfevents.1660970876.Merlin.4132.0 b/RecurrentPPO_5000000/logs/RecurrentPPO_2/events.out.tfevents.1660970876.Merlin.4132.0 new file mode 100644 index 0000000..c4e8fef Binary files /dev/null and b/RecurrentPPO_5000000/logs/RecurrentPPO_2/events.out.tfevents.1660970876.Merlin.4132.0 differ diff --git a/RecurrentPPO_5000000/logs/RecurrentPPO_3/events.out.tfevents.1661240879.Merlin.13336.0 b/RecurrentPPO_5000000/logs/RecurrentPPO_3/events.out.tfevents.1661240879.Merlin.13336.0 new file mode 100644 index 0000000..6b819f5 Binary files /dev/null and b/RecurrentPPO_5000000/logs/RecurrentPPO_3/events.out.tfevents.1661240879.Merlin.13336.0 differ diff --git a/RecurrentPPO_5000000/logs/Tensorrboard.png b/RecurrentPPO_5000000/logs/Tensorrboard.png new file mode 100644 index 0000000..7e109fa Binary files /dev/null and b/RecurrentPPO_5000000/logs/Tensorrboard.png differ diff --git a/RecurrentPPO_5000000/models/Breakout-v0_RecurrentPPO_model.zip b/RecurrentPPO_5000000/models/Breakout-v0_RecurrentPPO_model.zip new file mode 100644 index 0000000..c046dda Binary files /dev/null and b/RecurrentPPO_5000000/models/Breakout-v0_RecurrentPPO_model.zip differ diff --git a/RecurrentPPO_5000000/render/Modelled.gif b/RecurrentPPO_5000000/render/Modelled.gif new file mode 100644 index 0000000..8fd99c2 Binary files /dev/null and b/RecurrentPPO_5000000/render/Modelled.gif differ diff --git a/RecurrentPPO_5000000/render/Modelled.mp4 b/RecurrentPPO_5000000/render/Modelled.mp4 new file mode 100644 index 0000000..e2ef2ee Binary files /dev/null and b/RecurrentPPO_5000000/render/Modelled.mp4 differ diff --git a/RecurrentPPO_5000000/render/random.gif b/RecurrentPPO_5000000/render/random.gif new file mode 100644 index 0000000..d3ee619 Binary files /dev/null and b/RecurrentPPO_5000000/render/random.gif differ diff --git a/RecurrentPPO_5000000/render/random.mp4 b/RecurrentPPO_5000000/render/random.mp4 new file mode 100644 index 0000000..c8f0ecb Binary files /dev/null and b/RecurrentPPO_5000000/render/random.mp4 differ diff --git a/TRPO_200000/Readme.md b/TRPO_200000/Readme.md new file mode 100644 index 0000000..9b0fca4 --- /dev/null +++ b/TRPO_200000/Readme.md @@ -0,0 +1,17 @@ +# TRPO with 200K steps + +## Reference +[Trust Region Policy Optimization](https://arxiv.org/abs/1502.05477) + +## Parameters +Default parameters as per [Stable Baselines](https://sb3-contrib.readthedocs.io/en/master/modules/trpo.html) + +## Performance logs +![Trained model](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/TRPO_200000/logs/Tensorboard.png) + +## Renders +1. Random
      +![Random agent](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/TRPO_200000/render/random.gif) + +2. Modelled
      +![Modelled agent](https://github.com/SwamiKannan/Reinforcement-Learning/blob/main/Stable%20baselines/Breakout-v0/TRPO_200000/render/Modelled.gif) diff --git a/TRPO_200000/logs/TRPO_1/events.out.tfevents.1660843948.Merlin.12188.0 b/TRPO_200000/logs/TRPO_1/events.out.tfevents.1660843948.Merlin.12188.0 new file mode 100644 index 0000000..ec31b0c Binary files /dev/null and b/TRPO_200000/logs/TRPO_1/events.out.tfevents.1660843948.Merlin.12188.0 differ diff --git a/TRPO_200000/logs/TRPO_2/events.out.tfevents.1660844011.Merlin.2924.0 b/TRPO_200000/logs/TRPO_2/events.out.tfevents.1660844011.Merlin.2924.0 new file mode 100644 index 0000000..9c16c20 Binary files /dev/null and b/TRPO_200000/logs/TRPO_2/events.out.tfevents.1660844011.Merlin.2924.0 differ diff --git a/TRPO_200000/logs/TRPO_3/events.out.tfevents.1660887582.Merlin.14972.0 b/TRPO_200000/logs/TRPO_3/events.out.tfevents.1660887582.Merlin.14972.0 new file mode 100644 index 0000000..2961bdb Binary files /dev/null and b/TRPO_200000/logs/TRPO_3/events.out.tfevents.1660887582.Merlin.14972.0 differ diff --git a/TRPO_200000/logs/Tensorboard.png b/TRPO_200000/logs/Tensorboard.png new file mode 100644 index 0000000..8fc9e52 Binary files /dev/null and b/TRPO_200000/logs/Tensorboard.png differ diff --git a/TRPO_200000/models/Breakout-v0_TRPO_model.zip b/TRPO_200000/models/Breakout-v0_TRPO_model.zip new file mode 100644 index 0000000..972f065 Binary files /dev/null and b/TRPO_200000/models/Breakout-v0_TRPO_model.zip differ diff --git a/TRPO_200000/render/Modelled.gif b/TRPO_200000/render/Modelled.gif new file mode 100644 index 0000000..eceb727 Binary files /dev/null and b/TRPO_200000/render/Modelled.gif differ diff --git a/TRPO_200000/render/Modelled.mp4 b/TRPO_200000/render/Modelled.mp4 new file mode 100644 index 0000000..484e374 Binary files /dev/null and b/TRPO_200000/render/Modelled.mp4 differ diff --git a/TRPO_200000/render/random.gif b/TRPO_200000/render/random.gif new file mode 100644 index 0000000..d3ee619 Binary files /dev/null and b/TRPO_200000/render/random.gif differ diff --git a/TRPO_200000/render/random.mp4 b/TRPO_200000/render/random.mp4 new file mode 100644 index 0000000..c8f0ecb Binary files /dev/null and b/TRPO_200000/render/random.mp4 differ diff --git a/get_algos.py b/get_algos.py new file mode 100644 index 0000000..232f9a9 --- /dev/null +++ b/get_algos.py @@ -0,0 +1,126 @@ +import os +import gym +from gym.wrappers import Monitor +import matplotlib.pyplot as plt + +env_type={'Discrete':['PPO','A2C', 'DQN'],'Box':['PPO', 'A2C', 'DDPG', 'SAC', 'TD3'],'MultiDiscrete':['PPO','A2C'],'Multibinary':['PPO','A2C']} +def get_applicable_algos(action_type): + ''' + We are going to get all the algorithms that are applicable for the given action_state space. All algos can work independently of the state space type. + link: https://stable-baselines3.readthedocs.io/en/master/modules/a2c.html + Algo Space Action Observation + PPO Discrete Yes Yes + PPO Box Yes Yes + PPO MultiDiscrete Yes Yes + PPO MultiBinary Yes Yes + PPO Dict No Yes + + A2C Discrete Yes Yes + A2C Box Yes Yes + A2C MultiDiscrete Yes Yes + A2C MultiBinary Yes Yes + A2C Dict No Yes + + DDPG Discrete No Yes + DDPG Box Yes Yes + DDPG MultiDiscrete No Yes + DDPG MultiBinary No Yes + DDPG Dict No Yes + + DQN Discrete Yes Yes + DQN Box No Yes + DQN MultiDiscrete No Yes + DQN MultiBinary No Yes + DQN Dict No Yes + + SAC Discrete No Yes + SAC Box Yes Yes + SAC MultiDiscrete No Yes + SAC MultiBinary No Yes + SAC Dict No Yes + + TD3 Discrete No Yes + TD3 Box Yes Yes + TD3 MultiDiscrete No Yes + TD3 MultiBinary No Yes + TD3 Dict No Yes + ''' + return env_type[action_type] + +def run_env(env, episodes, random=True, model=""): + total_rewards=[] + if random: + for _ in range(episodes): + ep_rewards=0 + env.reset() + while True: + action=env.action_space.sample() + next_state, reward,done, info=env.step(action) + ep_rewards+=reward + if done: + total_rewards.append(ep_rewards) + break + else: + if model=="": + print('Please enter the agent model') + + else: + for _ in range(episodes): + ep_rewards=0 + state=env.reset() + while True: + action,_=model.predict(state) + next_state, reward,done, info=env.step(action) + ep_rewards+=reward + state=next_state + if done: + total_rewards.append(ep_rewards) + break + return total_rewards + +def run_experiment(env_name,env,render_path,random=True, episodes=5, model=""): + env=Monitor(gym.make(env_name),render_path,force=True) + if random: + total_rewards=run_env(env, 5) + else: + total_rewards=run_env(env,episodes=episodes, random=False,model=model) + return env, total_rewards + +def create_paths(algo_name,env_name,n_steps): + log_path=os.path.join(env_name, algo_name+"_"+str(n_steps),"logs") + if not os.path.exists(log_path): + os.makedirs(log_path) + render_path=os.path.join(env_name, algo_name+"_"+str(n_steps),"render") + if not os.path.exists(render_path): + os.makedirs(render_path) + model_path=os.path.join(env_name, algo_name+"_"+str(n_steps),"models") + if not os.path.exists(model_path): + os.makedirs(model_path) + return(log_path, render_path, model_path) + +def call_paths(algo_name,env_name,n_steps): + log_path=os.path.join(env_name, algo_name+"_"+str(n_steps),"logs") + render_path=os.path.join(env_name, algo_name+"_"+str(n_steps),"render") + model_path=os.path.join(env_name, algo_name+"_"+str(n_steps),"models") + return(log_path, render_path, model_path) + +def get_action_type_name(env): + action_space_type=str(type(env.action_space)).split('.')[3].split("'")[0] #Parsing the action_space variable to get the exact type - Discrete, Box, etc. + return action_space_type + +def get_all_algos(env): + action_space_type=get_action_type_name(env) + algo_list=get_applicable_algos(action_space_type) + return algo_list + +def addlabels(x,y): + for i in range(len(x)): + plt.text(i,y[i]+0.5,round(y[i],2)) + +def plot_mean(rewards,y_title): + x=list(rewards.keys()) + y=list(rewards.values()) + plt.bar(range(len(x)),y,tick_label=x) + plt.xlabel("Algorithm") + plt.ylabel(y_title) + addlabels(x,y) \ No newline at end of file diff --git a/modelled.gif b/modelled.gif new file mode 100644 index 0000000..dc68c6b Binary files /dev/null and b/modelled.gif differ diff --git a/random.gif b/random.gif new file mode 100644 index 0000000..d3ee619 Binary files /dev/null and b/random.gif differ