Safe learning is an essential asset when deploying machine learning algorithms on real hardware to avoid costly hardware damage. In this webinar, Dr. Dominik Baumann will discuss two recent approaches for safe learning and show their experimental evaluation on a Quanser QUBE.
Dominik is currently a postdoctoral researcher at Uppsala University. Prior, he was a joint Ph.D. student with the Max Planck Institute for Intelligent Systems in Germany and KTH Stockholm, Sweden and a postdoctoral researcher at RWTH Aachen University. His research interests are in the area of learning and control for networked multi-agent systems. In 2019, Dominik received the best demo award at the ACM/IEEE International Conference on Information Processing Systems in Montreal, Canada. The demo was supported by Quanser For more information, see https://baumanndominik.github.io/