faisalahmed0 / deep-rl

Some reimplementations of deep RL algorithm and papers I liked

Reinforcement Learning

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

There is also a simple implementation of the conjugate gradient algorithm with some visualization.
References
Reinforcement Learning: An Introduction http://incompleteideas.net/book/the-book-2nd.html
https://github.com/openai/gym
https://spinningup.openai.com/en/latest/