Master Seminar "Recent Developments in (Quantum) Reinforcement Learning" (SS 2021)
- Contact: Prof. Dr. Matthias Schubert, Dr. Yunpu Ma
- Required: Successful participation in the lectures "Machine Learning" or "Deep Learning and Artificial Intelligence" or "Artificial Intelligence for Games" or equivalent
Please indicate in the central registration form in uni2work in which semesters you had attended these courses.
- Audience: The lecture is directed towards highly motivated Master students in Mediainformatics, Bioinformatics and Informatics as well as Data Science with strong interest in cutting edge research
Though reinforcement learning driven agents achieve impressive results for well-defined environments, they often lack the capability to adapt to dynamic environments or modified or novel tasks. Learning such complex behavior is generally connected with large computational efforts. Recently advances in the area of quantum computing opened up new possibilities for solving complex mathematical problems. Thus, using quantum computing techniques to enable faster training in machine learning is a quickly developing topic. In this seminar, we will cover emerging and advanced topics like meta reinforcement learning, intrinsic rewards and motivation, multi-agent reinforcement learning, novel architectures for reinforcement learning, and quantum reinforcement learning. The participants will prepare reports and give a talk on selected topics in the area.