ToyRL¶
Documentation¶
https://ai-glimpse.github.io/toyrl
Installation¶
pip install toyrl
Algorithms¶
- REINFORCE
- SARSA
- DQN & Double DQN
- A2C
- PPO
References¶
- kengz/SLM-Lab: Our implementations are inspired by the book "Foundations of Deep Reinforcement Learning" and the implementation of SLM-Lab.
- vwxyzjn/cleanrl: The main reference for the implementation of the PPO implementation.