This course provides an overview of reinforcement learning (RL) in the context of robotics. The main purpose is to highlight the particular challenges that arise in the field of robotics, including sim2real transfer, expensive and potentially difficult data collection, and safety constraints. A good understanding of these aspects is crucial for the successful use of RL agents in industrial robotics tasks.
Throughout the course, we will present and discuss research papers on the following topics:
• Goal-Conditioned RL
• Object Manipulation
• Real-World RL
• Optimal Control
• Safe RL
• Multi-Agent RL
For participants who are interested in training a RL agent in simulation, there is also the opportunity to present the results of a small project.
Frequency | Weekday | Time | Format / Place | Period | |
---|---|---|---|---|---|
weekly | Mo | 10-12 | CITEC-1.015 | 07.10.2024-31.01.2025
not on: 10/28/24 / 12/23/24 / 12/30/24 |
am 28.10.2024 im CITEC-Raum 1.204 |
one-time | Mo | CITEC-1.204 | 28.10.2024 |
Module | Course | Requirements | |
---|---|---|---|
39-M-Inf-AI-adv Advanced Artificial Intelligence | Advanced Artificial Intelligence: Seminar 1 | Study requirement
|
Student information |
39-M-Inf-ASE-adv Advanced Autonomous Systems Engineering | Advanced Autonomous Systems Engineering: Seminar 1 | Study requirement
|
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.