Join our weekly meetings on Thursdays 14:30-16:00 at CITEC-1.015.
The seminar focus is on current approaches to deep reinforcement learning [1] as has been explored widely in the last couple of years in the area of learning decisions in computer games [2]. Further, current work extends these approaches to more real-world problems as grasping in robotics [3]. The seminar will give an introduction to the theoretical background of Deep Reinforcement Learning. It will afterward deal with state of the art methods and research literature presenting those methods [4]. Participants are expected to actively participate in the course by presenting selected articles. The seminar aims at comparing different approaches and providing an overview of current evolving principles and questions.
[1] https://deepmind.com/blog/deep-reinforcement-learning
[2] https://youtu.be/XjsY8-P4WHM?t=48s
[3] https://blog.openai.com/learning-dexterity
[4] https://rebrand.ly/DRL
Frequency | Weekday | Time | Format / Place | Period |
---|
Module | Course | Requirements | |
---|---|---|---|
39-Inf-EGMI Ergänzungsmodul Informatik | vertiefendes Seminar 1 | Ungraded examination
|
Student information |
vertiefendes Seminar 2 | Ungraded examination
|
Student information | |
vertiefendes Seminar 3 | Ungraded examination
|
Student information | |
vertiefendes Seminar 4 | Ungraded examination
|
Student information |
The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.
• regular attendance
• active participation in discussions
• presentation of selected articles,
• writing a report on the presented articles.