REINFORCEMENT LEARNING :

DESCRIPTION OF FILES:

1. RL_Frozenlake_Cliffwalker.ipynb : Jupyter notebook with the code for Q-Learning ( off policy TD learning ). The program runs two board games namely Frozen lake and Cliff walker. Environment simulation for Frozen lake has been imported from python library 'gym' while for cliff walker the environment dynamics and simulation has been written down in the notebook. Q-learning algorithm uses epsilon-greedy policy to search through the state space to find maximizing actions.