CS 839: Advanced Topics in Reinforcement Learning

CS 839, Fall 2026, Section 001
Department of Computer Sciences
University of Wisconsin–Madison


Schedule (Subject to Change)

Slides are tentative and will be updated shortly before lecture starts on each day. Slides will also be updated if errors are found — please let me know if you spot one!
Date Topic Assigned Reading Assignments
Thursday, Sept 3 Welcome and Course Overview (Slides) Chapter 1 of "Reinforcement Learning: An Introduction"
Tuesday, Sept 8 Bandits (Slides) Chapters 2 and 3 of "Reinforcement Learning: An Introduction". You may skim 2.5 - 2.9.
Thursday, Sept 10 Markov Decision Processes (Slides)
Tuesday, Sept 15 Dynamic Programming (Slides) Chapters 4 and 5 of "Reinforcement Learning: An Introduction"
Thursday, Sept 17 Monte Carlo Methods (Slides)
Tuesday, Sept 22 Temporal Difference Learning I (Slides) Chapter 6 of "Reinforcement Learning: An Introduction"
Thursday, Sept 24 Temporal Difference Learning II (Slides)
Tuesday, Sept 29 Models and Planning I (Slides) Chapter 8 of "Reinforcement Learning: An Introduction"
Thursday, Oct 1 Models and Planning II (Slides) Final project proposal due at 11:59 PM
Tuesday, Oct 6 Function Approximation I (Slides) Chapter 9 of "Reinforcement Learning: An Introduction" (You may skim 9.5, 9.7, 9.9, and 9.10; 9.7 will be assigned later)
Chapter 11 of "Reinforcement Learning: An Introduction" (Only up to (and including) 11.3)
Thursday, Oct 8 Function Approximation II (Slides) Programming assignment due at 11:59 PM
Tuesday, Oct 13 Deep RL I (Slides) Section 9.7 and 16.5 of "Reinforcement Learning: An Introduction"
Thursday, Oct 15 Deep RL II (Slides)
Tuesday, Oct 20 Policy Gradients I (Slides) Chapter 13 (skip 13.6) of "Reinforcement Learning: An Introduction"
Thursday, Oct 22 Policy Gradients II (Slides) Literature survey due at 11:59 PM
Tuesday, Oct 27 Multi-agent RL (Slides) Multi-agent Reinforcement Learning: Foundations and Modern Approaches (Chapter 1 and 5)
Thursday, Oct 29 Midterm Exam in Class
Tuesday, Nov 3 Abstraction and Hierarchy I (Slides) Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
Thursday, Nov 5 Abstraction and Hierarchy II (Slides)
Tuesday, Nov 10 Learning from Humans: RLHF, Inverse RL, Imitation Learning (Slides) Deep Reinforcement Learning from Human Preferences
Thursday, Nov 12 RL + LLMs (Slides)
Tuesday, Nov 17 Reproducibility and Evaluation (Slides) Empirical Design in Reinforcement Learning
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems (Read all of Sections 1, 2, 4, 6, and 7. Skim Section 5)
Thursday, Nov 19 Offline RL (Slides)
Tuesday, Nov 24 No class (Thanksgiving week)
Thursday, Nov 26 Happy Thanksgiving! (No class)
Tuesday, Dec 1 Applications (Slides) Challenges of Real-World Reinforcement Learning
Thursday, Dec 3 World Models
Tuesday, Dec 8 Project Lightning Talks
FINAL PROJECT REPORTS DUE: December 11 at 11:59 PM
Everything below here is tentative and subject to change.