This project aims to be an example of the implementation of various reinforcement learning concepts using the Gym library in Python.
It specifically
Phase 1: Focuses on the "CartPole" environment provided by Gym.
Phase 2: Takes a look at some algorithms like QLearning and SARSA.
Phase 3: Provides a custom env named CustomMiniGridEnv instead of using Gym environments and applies Tabular QLearning on it.
Phase 4: Makes itself better and better in deeper insights
AmirMahdi Daraei
Helia AkhtarKavian