Tutorials for reinforcement learning in PyTorch and Gym by implementing a few of the popular algorithms. [IN PROGRESS]

Proximal Policy Optimization(PPO) with Intrinsic Curiosity Module(ICM)

A collection of Reinforcement Learning implementations with PyTorch

Phasic-Policy-Gradient

An implementation from the state-of-the-art family of reinforcement learning algorithms Proximal Policy Optimization using normalized Generalized Advantage Estimation and optional batch mode training. The loss function incorporates an entropy bonus.

Recurrent Policies for Handling Partially Observable Environments

Example TRPO implementation with ReLAx

Example PPO implementation with ReLAx

Modular Implementation of Proximal Policy Optimization (PPO) is a policy gradient reinforcement learning algorithm introduced by OpenAI in 2017. It's designed to be a simpler, more stable, and more sample-efficient alternative to previous policy gradient methods like A3C and TRPO (Trust Region Policy Optimization).