My goal is to enable robots to safely and autonomously learn in uncertain real-world environments. This requires new reinforcement learning algorithms that respect the physical limitations and constraints of dynamic systems and provide theoretical safety guarantees.
I completed my BSc and MSc in mechanical engineering at ETH Zurich and conducted the research for my master thesis at the University of Toronto.Students:
Invited talk at the Workshop on Reliable AI 2017
NIPS/CoRL 2017: "Safe Model-based Reinforcement Learning with Stability Guarantees".