Introduction to Reinforcement Learning
This page presents lecture materials for CS 4789/5789: Introduction to Reinforcement Learning taught by Sarah Dean at Cornell University in spring 2023. For the most recent materials look here . This course was first taught by Wen Sun in spring 2021.
Schedule
| no. | Date | Topic | Materials |
| 1 | 1/23 | Introduction to RL | Slides |
| 2 | 1/25 | MDPs and Imitation Learning | Slides |
| 3 | 1/30 | MDPs and Bellman Equations | Slides |
| 4 | 2/1 | MDPs and Optimal Policies | Slides |
| 5 | 2/6 | Value Iteration | Slides |
| 6 | 2/8 | Policy Iteration and Dynamic Programming | Slides |
| 7 | 2/13 | Continuous Control | Slides |
| 8 | 2/15 | Optimal Linear Control | Slides |
| 9 | 2/20 | LQR and Local Nonlinear Control | Slides |
| 10 | 2/22 | Iterative LQR & Fundamental Limitations | Slides |
| 2/27 | No lecture - February Break | ||
| 11 | 3/1 | Model-Based Reinforcement Learning | Slides |
| 12 | 3/6 | Approximate Policy Iteration | Slides |
| 13 | 3/8 | Conservative Policy Iteration | Slides |
| 14 | 3/13 | Review | Slides |
| 3/15 | Prelim during lecture time | ||
| 15 | 3/20 | Value-based RL | Slides |
| 16 | 3/22 | Optimization Overview | Slides |
| 17 | 3/27 | Policy Optimization | Slides |
| 18 | 3/29 | Trust Regions and NPG | Slides |
| 4/3 | Spring break | ||
| 4/5 | Spring break | ||
| 19 | 4/10 | Exploration: Multi-Armed Bandits | Slides |
| 20 | 4/12 | Upper Confidence Bound Algorithm | Slides |
| 21 | 4/17 | Contextual Bandits | Slides |
| 22 | 4/19 | Exploration in MDPs | Slides |
| 23 | 4/24 | Interactive Imitation Learning | Slides |
| 24 | 4/26 | Inverse RL | Slides |
| 25 | 5/1 | Case Study: AlphaGo | Slides |
| 26 | 5/3 | Specification & Societal Implications | Slides |
| 27 | 5/8 | Final Review | Slides |