Cursussyllabus
Link to recordings: RL Course 23-24 (ZIP, 4 GB)
Link to the practical sessions: JupyterLab on Binder (may take several minutes to load)
This course will serve as an introduction to the basic concepts of single agent RL and slowly build up to advanced concepts leading to current state-of-the-art methods and Deep RL.
Examination:
Students will be evaluated based on following criteria:
- Participation to the lectures and practical sessions (except for working students), 10%
- Learning agent project (2nd semester)
- Project defence & report (2nd semester exam period), 90%
Material:
Basic Reinforcement Learning book (this is the structure we will follow in the course):
Reinforcement Learning: An Introduction 2nd edition
Other resources:
- John Schulman’s and Pieter Abeel’s class: Deep Reinforcement Learning, Fall 2015
- Deep Reinforcement Learning and Control, CMU Spring 2017
- David Silver’s class: Reinforcement learning
For neural networks material:
Software:
- The OpenAI Gym will be use as a testbed for learning algorithms (if you do not program your own environment, which is also allowed).
- Experiments will be coded in Python. We recommend installation of the Anaconda framework to get all the scientific computing libraries.
Cursusoverzicht:
| Datum | Details | Inleverdatum |
|---|---|---|