RL_Games_Project

This is a reinforcement learning project that our group did for our English project, our goal is to explore different policy optimizers and their performance in different environments. Colmjr came up with the idea to explore policy optimizers and created the the custom environments and GUIs, and helped to deploy the optimzers across all 3 environments. E-rail made the policy optimizers and wrappers(pettingzoo-->gymnasium to be compatible with sb3)to integrate them into the environment. Nick is in charge of reading the papers for PPO and explain PPO and Q-table in simple terms. Ziven is in charge of explaining the basics of RL to our English class.