Reinforcement Learning
- Organized by: Prof. Joschka Boedecker, Gabriel Kalweit, Jasper Hoffmann, Andreas Saelinger
- Lecture: HISinOne number: 11LE13V-1141
- Language: English
- Dates: Friday 14:00-15:30 s.t. (online), first lecture on October 22, 2021
- Lecture recordings, slides, exercises and solutions will be posted on ILIAS
Overview:
The lecture deals with methods of Reinforcement Learning that constitute an important class of machine learning algorithms. Starting with the formalization of problems as Markov decision processes, a variety of Reinforcement Learning methods are introduced and discussed in-depth. The connection to practice-oriented problems is established throughout the lecture based on many examples.
Format:
The course will be online only in the form of a flipped classroom, i.e. we will provide recorded lectures for you to watch and post your questions on, which will then be discussed in a live online meeting via zoom. For the first week, there will be no video to watch since we will do the introduction to the course in an online session (see ILIAS Forum for zoom link and password).