README.md

Reinforcement Learning Box

Discountinued I'm now working on a Pytorch RL library
RLbox provides a framework for rapid experimentation with popular Deep Reinforcement Learning algorithms, it focus on making very easy to implement new ideias, which can be rapidly evaluated using OpenAI Gym.

Installation

git clone https://github.com/apparatusbox/rlbox.git
cd rlbox  
pip install -e .  

How to use

Examples on how to run different agents can be found on the examples folder.

Implemented algorithms

State of the art

• DQN and extensions
  • Double Q-learning
  • Dueling networks
  • N-step learning
  • Soft target update
• PPO
  • Clipped Surrogate Objective
  • Adaptive KL Penalty Coefficient

Classical

• Vanilla Policy Gradient
• REINFORCE
• Actor-Critic

Results

• DQN on BreakoutNoFrameskip-v4
  Episode 0 ---------------- Episode 3500 ----------- Episode 6000 ----------- Episode 7500 ----------- Episode 21500
  
  Mean reward after training: 421 (Averaged over 100 episodes)
  Dark blue: Standard DQN
  Light blue: Double DQN
  

• PPO on Hopper-v1 Video