Contra-PPO-pytorch
This project offers Python code for training AI agents in the Contra NES game using OpenAI's Proximal Policy Optimization. The algorithm is known for its efficient AI training capabilities, exemplified in OpenAI Five's success. Features include comprehensive training and testing functionalities, a convenient Docker setup, and an exploration of the algorithm's impact in retro gaming scenarios such as Contra, building upon past implementations in other NES titles.
