Introduction to Reinforcement Learning
This page will host materials from CS 4789/5789: Introduction to Reinforcement Learning taught by Sarah Dean at Cornell. See Spring 2022 and Spring 2023 pages for past materials. This course was first taught by Wen Sun in spring 2021.
Schedule
| No. | Date | Topic | Materials |
| 1 | 8/24 | Introduction to RL | Slides |
| 2 | 8/26 | Setting and Estimation | Notes (through section 1.2), Slides |
| 3 | 8/31 | Policy Gradients | Notes (through section 1.3), Slides |
| 4 | 9/2 | Trust Regions | Notes (through section 1.4), Slides |
| 9/7 | |||
| 5 | 9/9 | Policy Optimization Summary | Notes (through section 1.4), Slides |
| 6 | 9/14 | State and Sequences | Notes (through section 2.3), Slides |
| 7 | 9/16 | Policy Evaluation | Notes (through section 2.4), Slides |
| 8 | 9/21 | Review | Slides |
| 9 | 9/23 | Exam 1 | |
| 10 | 9/28 | Optimal Policies in MDPs | Notes (through section 3.1 and section 2.6) |
| 11 | 9/30 | Value Iteration | |
| 12 | 10/5 | Dynamic Programming | |
| 13 | 10/7 | Fitted VI | |
| 10/12 | |||
| 14 | 10/14 | Policy Iteration | |
| 15 | 10/19 | Fitted PI | |
| 16 | 10/21 | Policy Optimization Revisited | |
| 17 | 10/26 | Policy Optimization cont. | |
| 18 | 10/28 | Exam 2 | |
| 19 | 11/2 | Multi-Armed Bandits | |
| 20 | 11/4 | Contextual Bandits | |
| 21 | 11/9 | Receding Horizon Policies | |
| 22 | 11/11 | Receding Horizon Policies cont. | |
| 23 | 11/16 | Imitation Learning | |
| 24 | 11/18 | Guest Lecture | |
| 25 | 11/23 | Inverse RL | |
| 11/25 | |||
| 26 | 11/30 | Specification and Implications | |
| 27 | 12/2 | Case Study |