This Repository contains implementation of the core Deep RL algorithms tested in variuos toy problem in open AI gym environment.
These alogrithms are implemented in python using numpy and PyTorch.
Algorithms in this repo are:
- REINFORCE (vanilla policy gradient)
- Policy gradient with state dependent baseline
- Policy gradient with state dependent baseline
References
Reinforcement Learning: An Introduction http://incompleteideas.net/book/the-book-2nd.html
https://github.com/openai/gym
https://spinningup.openai.com/en/latest/