Policy Iteration

Lets start our first Model-Based Reinforcement Learning method using Policy Iteration! Please make sure you are comfortable with the Bellman Equation though! Here are some of my previous videos to help: Derive the Bellman Equation https://youtu.be/4YXM7vEuR5c Bellman Optimality Equations https://youtu.be/OmdMnU4BCn0 Timestamps: 00:00:00 - Two Methods to Solve Environment 00:03:35 - Policy Evaluation 00:04:35 - Policy Improvement 00:06:00 - How to use Gymnasium Package 00:17:35 - Implement Deterministic Policy Evaluation 00:26:17 - Implement Deterministic Policy Improvement 00:34:10 - Play Game! 00:35:00 - Convert to Stochastic Environment 00:46:05 - Play Game! 00:48:36 - Recap Socials! X https://twitter.com/data_adventurer Instagram https://www.instagram.com/nixielights/ Linkedin https://www.linkedin.com/in/priyammaz/ 🚀 Github: https://github.com/priyammaz 🌐 Website: https://www.priyammazumdar.com/