/Pendulum_PPO

Implementation of Proximal Policy Optimization (PPO) for continuous action space (`Pendulum-v1` from gym) using pytorch.

Primary LanguagePythonMIT LicenseMIT

Pendulum_PPO

Implementation of Proximal Policy Optimization (PPO) for continuous action space (Pendulum-v1 from gym) using pytorch. I got the code working with Gymnasium (instead of OpenAI Gym) and removed the TensorFlow code and testing code.