I am a first-year Ph.D. student at the Empirical Inference department, supervised by Bernhard Schölkopf. Currently, I am researching methods to make reinforcement learning agents discover and explore causal mechanisms in their environments. My goal is to help to make reinforcement learning more robust and sample-efficient.
Schmid, K., Belzner, L., Kiermeier, M., Neitz, A., Phan, T., Gabor, T., Linnhoff, C.
Risk-Sensitivity in Simulation Based Online PlanningKI 2018: Advances in Artificial Intelligence - 41st German Conference on AI, pages: 229-240, (Editors: F. Trollmann and A. Y. Turhan), Springer, Cham, September 2018 (conference)
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems