Reinforcement Learning Algorithms for OpenAI Environments

Implemented value-iteration, policy-iteration, and Q-learning agents for grid (Frozen Lake), and non-grid (Forest Management) world environments [Python, OpenAI Gym, MDPToolbox]

Coded Q-Learning from scratch for Cart-Pole, and Frozen Lake environments, and improved performance of the agents by testing different epsilon greedy strategies (exploration/exploitation) [Python]