Learning materials for Reinforcement learning 2021 by AIDA Lab.
| Lecture | Title | Video | Slides |
|---|---|---|---|
| Lecture 1 | Basics, environments | Link | Link |
| Lecture 2 | Dynamic programming | Link | Link |
| Lecture 3 | Policy gradient | Link | Link |
| Lecture 4 | Actor-critic | Link | Link |
| Lecture 5 | Convergence I | Link | Link |
| Lecture 6 | Convergence II | Link | Link |
| Lecture 7 | Deep RL | Link | Link |
| Lecture 8 | Predictive agents | Link | Link |
| Lecture 9 | Safety | Link | Link |
| Seminar | Topic | Tasks | Materials | Video |
|---|---|---|---|---|
| Seminar 1 | Basics, environments | Link | Link | Link |
| Seminar 2 | Dynamic programming | Link | Link | Link |
| Seminar 3 | Policy gradient | Link | Link | Link |
| Seminar 4 | Actor-critic | Link | Link | Link |
| Seminar 5 | Convergence I | Link | Link | Link |
| Seminar 6 | Convergence II | Link | Link | Link |
| Seminar 7 | Deep RL | Link | Link | Link |
| Seminar 8 | Predictive agents | Link | Link | Link |
| Seminar 9 | Safety | Link | Link | Link |
| Assignment | Description | Roll-out | Due |
|---|---|---|---|
| Assignment 1 | Dynamic programming | 21.09.2021 | 28.09.2021 |
| Assignment 2 | Policy gradient | 30.09.2021 | 07.10.2021 |
| Assignment 3 | Actor-critic | 05.10.2021 | 12.10.2021 |
| Assignment 4 | Deep actor-critic | 12.10.2021 | 19.10.2021 |
| Final project | Topic of choice (needs approval) | Free to start | Presentation at last two slots |