Under development! Caution, this page is currently incomlete and there may be missing files and mistakes in the provided materials.
This repository contains lecture material, simple Python code examples, and assignments for the course CS 5/73XX Reinforcement Learning taught by Michael Hahsler at the Department of Computer Science at SMU.
The code examples cover several chapters of the textbook
Richard S. Sutton, Andrew G. Barto, Reinforcement Learning: An Introduction, 2nd edition, MIT Press, Cambridge, MA, 2018.
Deep Reinforcement Learning (DRL) is based on the review paper
Vincent François-Lavet, Peter Henderson, Riashat Islam, Marc G. Bellemare and Joelle Pineau, An Introduction to Deep Reinforcement Learning, Foundations and Trends in Machine Learning, 11:3-4, pp 219-354. http://dx.doi.org/10.1561/2200000071, 2018.
Studying the material requires
- Python programming skills.
- Knowledge of AI basics (how intelligent agents interact with an environment).
- Knowledge of how to use machine learning techniques including deep learning.
- Basic knowledge of probability and statistics, linear algebra, and calculus.
| Module | Book Chapter | Lecture Slides | Code |
|---|---|---|---|
| 1 | 1: Introduction | PDF, PowerPoint | Code |
| 2 | 3: Finite Markov Decision Processes | PDF, PowerPoint | Code |
| Part I: Tabular Methods | |||
| 3 | 4: Dynamic Programming | PDF, PowerPoint | Code |
| 4 | 5: Monte Carlo Methods | PDF, PowerPoint | Code |
| 5 | 6: Temporal-Difference Learning | PDF, PowerPoint | Code |
| - | 7: n-step Bootstrapping | PDF, PowerPoint | - |
| - | 8: Planning and Learning with Tabular Methods | PDF, PowerPoint | - |
| Part II: Approximate Solution Methods | |||
| 6 | 9-10: Prediction and Control using Approximation | PDF, PowerPoint | Code |
| 7 | 12: Eligibility Traces | PDF, PowerPoint | - |
| 9 | 13: Policy Gradient Methods | PDF, PowerPoint | - |
| Modern Methods | |||
| 10 | DRL: Deep Reinforcement Learning | PDF, PowerPoint | Code |
| 11 | X: Current Applications | - | - |
Introduction to Reinforcement Learning © 2026 Michael Hahsler and others is licensed under CC BY-NC-SA 4.0.