Skip to content

Latest commit

 

History

History
392 lines (271 loc) · 27.9 KB

README.md

File metadata and controls

392 lines (271 loc) · 27.9 KB
Raw

👉 Setup Python environment for the repo




👉 Unity enviroment Tennis vector game (Project Submission)

✅ Project description

In this environment, two agents control rackets to bounce a ball over a net. If an agent hits the ball over the net, it receives a reward of +0.1. If an agent lets a ball hit the ground or hits the ball out of bounds, it receives a reward of -0.01. Thus, the goal of each agent is to keep the ball in play.

The observation space consists of 8 variables corresponding to the position and velocity of the ball and racket. Each agent receives its own, local observation. Two continuous actions are available, corresponding to movement toward (or away from) the net, and jumping.

The task is episodic, and in order to solve the environment, your agents must get an average score of +0.5 (over 100 consecutive episodes, after taking the maximum over both agents). Specifically,

  • After each episode, we add up the rewards that each agent received (without discounting), to get a score for each agent. This yields 2 (potentially different) scores. We then take the maximum of these 2 scores.
  • This yields a single score for each episode.

The environment is considered solved, when the average (over 100 episodes) of those scores is at least +0.5.

✅ Multi-Agent Deep Deterministic Policy Gradient (MADDPG) solution

  • MADDPG, or Multi-agent DDPG, extends DDPG into a multi-agent policy gradient algorithm where decentralized agents learn a centralized critic based on the observations and actions of all agents. It leads to learned policies that only use local information (i.e. their own observations) at execution time, does not assume a differentiable model of the environment dynamics or any particular structure on the communication method between agents, and is applicable not only to cooperative interaction but to competitive or mixed interaction involving both physical and communicative behavior. The critic is augmented with extra information about the policies of other agents, while the actor only has access to local information. After training is completed, only the local actors are used at execution phase, acting in a decentralized manner.

  • Multi-environments, implemented using the multiprocessing library (check the file ..\python\baselines\baselines\common\vec_env\subproc_vec_env.py), can be used for parallel training here, which can add diversity to the experiences. Additionally, asynchronous stepping may help speed up the training and evalation processes.

  • I’m borrowing the 'brain' concept from Unity environments, so I refer to the control unit of an agent as a 'brain,' for example, the neural networks here. For instance, in the case of 3 environments with 2 agents per environment, a total of 2 agent brains will be created. Each brain processes its own observation and generates an action in each environment independently, controlling 2 agents within each environment, also updating its own neural network sets independently. This means that an agent brain receives 3 observations (one from each environment) and generates 3 corresponding actions for the 3 environments. The 'x, r, a, x_prime' sequences from all the environments will be stored in a single replay buffer D.

✅ setup Python environment

✅ reference

✅ Implementation

  • Instantiate the DeterministicActorCriticNet class to create 4 Networks (2 classes) per agent:
    actor, critic, target actor, target critic
  • Soft updates for target networks, Adam on actor/critic networks
  • Single replay memory for all agents; have to keep observations straight
    Random uniform sampling, storing new memories
  • The MADDPGAgent class to choose actions, do soft updates, save models
  • The Task class to handle list of agents and learn function
  • Utility functions to reshape the observations and actions, etc.

✅ Coding

  • Add the brain name 'TennisBrain' in ..\python\deeprl\component\envs.py function get_return_from_brain_info.

  • An env has 2 agents playing with each other. Refer to this notebook.

  Number of agents: 2
  Size of each action: 2
  There are 2 agents. Each observes a state with length: 24
  The actions for the 2 agents look like:
  [[0.74462557, -0.91233826], 
   [0.30700633,  0.4461334 ]]
  The state for the first agent looks like: 
  [ 0.          0.          0.          0.          0.          0.
    0.          0.          0.          0.          0.          0.
    0.          0.          0.          0.         -6.65278625 -1.5
   -0.          0.          6.83172083  6.         -0.          0.        ]

  • Create class MADDPGAgent(BaseAgent) in file ..\python\deeprl\agent\MADDPG_agent.py.

  • Create train and eval functions in file ..\python\experiments\deeprl_maddpg_continuous.py.

  • In the get_env_fn() function, located in ..\python\deeprl\component\envs.py, for Gym games, the environment class is wrapped using OriginalReturnWrapper(). Inside the wrapper class's step() and reset() method, info['episodic_return'] = self.total_rewards is defined. However, for Unity games, the environment is already instantiated at the same location, so it can't be wrapped with an wrapper class. Instead, we define info['episodic_return'] within classes UnityVecEnv and UnitySubprocVecEnv, which call the get_return_from_brain_info() function where info is actually populated. And for the Tennis game, we add up the rewards that each agent received (without discounting), to get a score for each agent, which yields 2 (potentially different) scores, and we take the maximum of these 2 scores as the episodic return.




👉 AlphaZero




👉 Unity enviroment Reacher-v2 vector game (Project Submission)

✅ setup Python environment

✅ entry points

✅ Result: A DDPG model was trained in one Unity-Reacher-v2 environment with 1 agent (1 robot arm) for 155 episodes, then evaluated in 3 environments (each with 1 agent) parallelly for 150 consecutive episodes and got an average score of 33.92(0.26) (0.26 is the standard deviation of scores in different envs). also the trained model is tested to control 20 agents in 4 envs parallelly and got a score of 34.24(0.10).

  • evaluation with graphics

    Notes:

    • the 4 envs and each its own 1 (or 20) agents above were controlled by one single DDPG model at the same time.
    • observation dimension [num_envs, num_agents (per env), state_size] will be converted to [num_envs*num_agents, state_size] to pass through the neural networks.
    • during training, action dimension will be [mini_batch_size (replay batch), action_size];
      during evaluation, the local network will ouput actions with dimension [num_envs*num_agents, action_size], and it will be converted to [num_envs, num_agents, action_size] to step the envs.

  • train and eval scores

  • monitor train-eval scores with tensorboard

  • DDPG neural networks architecture

  • evaluation result (in 3 envs for 150 consecutive episodes)

  • saved files (check the folder)

    • trained model
    • train log (human readable):
      you can find all the configuration including training hyperparameters, network architecture, train and eval scores, here.
    • tf_log (tensorflow log, will be read by the plot modules)
    • eval log (human readable)

✅ major efforts in coding

  • all the code is integrated with ShangtongZhang's deeprl framework which uses some OpenAI Baselines functionalities.

  • one task can step multiple envs, either with a single process, or with multiple processes. multiple tasks can be stepped synchronously.

  • to enable multiprocessing of Unity environments, the following code has had to be modified.
    in python/unityagents/rpc_communicator.py

    class UnityToExternalServicerImplementation(UnityToExternalServicer):
    # parent_conn, child_conn = Pipe() ## removed by nov05
...
class RpcCommunicator(Communicator):
    def initialize(self, inputs: UnityInput) -> UnityOutput: # type: ignore
        try:
            self.unity_to_external = UnityToExternalServicerImplementation()
            self.unity_to_external.parent_conn, self.unity_to_external.child_conn = Pipe() ## added by nov05

  • Task UML diagram

    Agent UML diagram

  • launch multiple Unity environments parallelly (not used in the project) from an executable file (using Python Subprocess and Multiprocess, without MLAgents)

✅ reference




👉 OpenAI Gym's Atari Pong pixel game




👉 Unity ML-Agents Banana Collectors (Project Submission)

  1. For this toy game, two Deep Q-network methods are tried out. Since the observations (states) are simple (not in pixels), convolutional layers are not in use. And the evaluation results confirm that linear layers are sufficient for solving the problem.
    • Double DQN, with 3 linear layers (hidden dims: 256*64, later tried with 64*64)
    • Dueling DQN, with 2 linear layers + 2 split linear layers (hidden dims: 64*64)

▪️ The Dueling DQN architecture is displayed as below.

Dueling Architecture The green module

▪️ Since both the advantage and the value stream propagate gradients to the last convolutional layer in the backward pass, we rescale the combined gradient entering the last convolutional layer by 1/√2. This simple heuristic mildly increases stability.

        self.layer1 = nn.Linear(state_size, 64)
        self.layer2 = nn.Linear(64, 64)
        self.layer3_adv = nn.Linear(in_features=64, out_features=action_size) ## advantage
        self.layer3_val = nn.Linear(in_features=64, out_features=1) ## state value

    def forward(self, state):
        x = F.relu(self.layer1(state))
        x = F.relu(self.layer2(x))
        adv, val = self.layer3_adv(x), self.layer3_val(x)
        return (val + adv - adv.mean(1).unsqueeze(1).expand(x.size(0), action_size)) / (2**0.5)

▪️ In addition, we clip the gradients to have their norm less than or equal to 10. This clipping is not standard practice in deep RL, but common in recurrent network training (Bengio et al., 2013).

        ## clip the gradients
        nn.utils.clip_grad_norm_(self.qnetwork_local.parameters(), 10.)
        nn.utils.clip_grad_norm_(self.qnetwork_target.parameters(), 10.)
  1. The following picture shows the train and eval scores (rewards) for both architectures. Since it is a toy project, trained models are not formally evaluated. We can roughly see that Dueling DQN slightly performs better with an average score of 17 vs. Double DQN 13 in 10 episodes.

  1. Project artifacts:




👉 Logs

2024-04-10 p2 Unity Reacher v2 submission
2024-03-07 Python code to launch multiple Unity environments parallelly from an executable file
...
2024-02-14 Banana game project submission
2024-02-11 Unity MLAgent Banana env set up
2024-02-10 repo cloned




Deep Reinforcement Learning Nanodegree

Trained Agents

This repository contains material related to Udacity's Deep Reinforcement Learning Nanodegree program.

Table of Contents

Tutorials

The tutorials lead you through implementing various algorithms in reinforcement learning. All of the code is in PyTorch (v0.4) and Python 3.

  • Dynamic Programming: Implement Dynamic Programming algorithms such as Policy Evaluation, Policy Improvement, Policy Iteration, and Value Iteration.
  • Monte Carlo: Implement Monte Carlo methods for prediction and control.
  • Temporal-Difference: Implement Temporal-Difference methods such as Sarsa, Q-Learning, and Expected Sarsa.
  • Discretization: Learn how to discretize continuous state spaces, and solve the Mountain Car environment.
  • Tile Coding: Implement a method for discretizing continuous state spaces that enables better generalization.
  • Deep Q-Network: Explore how to use a Deep Q-Network (DQN) to navigate a space vehicle without crashing.
  • Robotics: Use a C++ API to train reinforcement learning agents from virtual robotic simulation in 3D. (External link)
  • Hill Climbing: Use hill climbing with adaptive noise scaling to balance a pole on a moving cart.
  • Cross-Entropy Method: Use the cross-entropy method to train a car to navigate a steep hill.
  • REINFORCE: Learn how to use Monte Carlo Policy Gradients to solve a classic control task.
  • Proximal Policy Optimization: Explore how to use Proximal Policy Optimization (PPO) to solve a classic reinforcement learning task. (Coming soon!)
  • Deep Deterministic Policy Gradients: Explore how to use Deep Deterministic Policy Gradients (DDPG) with OpenAI Gym environments.
    • Pendulum: Use OpenAI Gym's Pendulum environment.
    • BipedalWalker: Use OpenAI Gym's BipedalWalker environment.
  • Finance: Train an agent to discover optimal trading strategies.

Labs / Projects

The labs and projects can be found below. All of the projects use rich simulation environments from Unity ML-Agents. In the Deep Reinforcement Learning Nanodegree program, you will receive a review of your project. These reviews are meant to give you personalized feedback and to tell you what can be improved in your code.

  • The Taxi Problem: In this lab, you will train a taxi to pick up and drop off passengers.
  • Navigation: In the first project, you will train an agent to collect yellow bananas while avoiding blue bananas.
  • Continuous Control: In the second project, you will train an robotic arm to reach target locations.
  • Collaboration and Competition: In the third project, you will train a pair of agents to play tennis!

Resources

OpenAI Gym Benchmarks

Classic Control

Box2d

Toy Text

Dependencies

To set up your python environment to run the code in this repository, follow the instructions below.

  1. Create (and activate) a new environment with Python 3.6.

    • Linux or Mac:
    conda create --name drlnd python=3.6
source activate drlnd
    • Windows:
    conda create --name drlnd python=3.6 
activate drlnd

  2. If running in Windows, ensure you have the "Build Tools for Visual Studio 2019" installed from this site. This article may also be very helpful. This was confirmed to work in Windows 10 Home.

  3. Follow the instructions in this repository to perform a minimal install of OpenAI gym.

    • Next, install the classic control environment group by following the instructions here.
    • Then, install the box2d environment group by following the instructions here.

  4. Clone the repository (if you haven't already!), and navigate to the python/ folder. Then, install several dependencies.

    git clone https://github.com/udacity/deep-reinforcement-learning.git
cd deep-reinforcement-learning/python
pip install .

  5. Create an IPython kernel for the drlnd environment.

    python -m ipykernel install --user --name drlnd --display-name "drlnd"

  6. Before running code in a notebook, change the kernel to match the drlnd environment by using the drop-down Kernel menu.

Kernel

Want to learn more?

Come learn with us in the Deep Reinforcement Learning Nanodegree program at Udacity!