Reinforcment Learning Implementations

I have implemented various reinforcement learning algorithms, both within the Reinforcement Learning class at UMass Lowell, and on my own. These algorithms include Q-Learning, SARSA, Actor-Critic with Elgibility Traces, and Deep Q-Learning. I have tested these algorithms in various environments within the Gymnasium Library, a maintained fork of OpenAI’s Gym library. These environments range from simple discrete state and action environments such as Cliff Walking, Frozen Lake, and Taxi, to continous state space and discrete action space environments like Mountain Car, Cart Pole, and Lunar Lander.