/MDP-with-Value-Iteration-and-Policy-Iteration

Value Iteration and Policy Iteration to solve MDPs

Primary LanguageJupyter NotebookMIT LicenseMIT

MDP with Value Iteration and Policy Iteration

Solving MDP is a first step towards Deep Reinforcement Learning. This notebook show you how to implement Value Iteration and Policy Iteration to solve OPENAI GYM FrozenLake Enviorment.