Chapters 17 and 22: Reinforcement Learning and MDPs

Chapter 17: MDPs

• Define an MDP model for the 4x3 grid world. Defines the MDP from scratch (from Reinforcement Learning).
• Value Iteration and Policy Iteration for Russel and Norvig’s 4x3 grid world. This notebook discusses the implementation of the algorithms. (from Reinforcement Learning)
• Connection to Chapter 5 (Adversarial Search): Finding the Optimal Policy to Play Tic-Tac-Toe with Value Iteration implements value iteration to find the optimal policy to play the game.

Chapter 22: Reinforcement Learning (RL)

• Q-Learning for the Cliff Walking Environment (from Reinforcement Learning).
• Connection to Chapter 5 (Adversarial Search): Learning to Play Tic-Tac-Toe with Q-Learning implements a simple table-based Q-learning algorithm to play the game.

More on Reinforcement Learning

More on RL (examples, code, libraries) can be found in the course material Reinforcement Learning: Lecture Material, Simple Python Code Examples and Assignments

License

© 2025-2026 Michael Hahsler. All code and documents in this repository are provided under Creative Commons Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) License.