This event has passed.
Thursday, April 8, 2021 – 9:00AM to 10:00AM
Kaiqing Zhang, Ph.D. Candidate
MEMS Seminar Presents: Kaiqing Zhang, Ph.D. Candidate
Location: Virtual Zoom Link: https://duke.zoom.us/j/92522900794
Recent years have witnessed tremendous successes of AI and machine learning, especially reinforcement learning (RL), in solving many decision-making and control tasks. However, many RL algorithms are still miles away from being applied to practical autonomous systems, which usually involve more complicated scenarios with model uncertainty and multiple decision-makers by nature. In this talk, I will introduce our study of RL for control and sequential decision-making with provable guarantees, especially with robustness and multi-agent interaction considerations. I will first show that policy optimization, one of the main drivers of many empirical successes of RL, can solve a fundamental class of robust control tasks with global optimality guarantees, despite nonconvexity. More importantly, I will show that certain policy optimization approaches also automatically preserve some "robustness" during learning, a property we termed as "implicit regularization", an interesting phenomenon that has been observed in other different machine learning contexts