Nuts and bolts of reinforcement learning algorithms

Pytorch implementations of RL algorithms.

• Common utilities applicable to all RL algorithms can be found in rlkits.
• Algorithms can be found in rlalgos
• Notes about the algorithms can be found in theory
• Examples can be found in example
• Experiments in Jupyter notebooks can be found in notebooks

To install the package

pip install -e .

Policy gradient methods

• A2C
• TRPO
• PPO
• DDPG

Reference

• andri27-ts/Reinforcement-Learning
• higgsfield/RL-Adventure
• yandexdataschool/Practical_RL
• openai/baselines