Skip to main content
Browse by:
GROUP

Until further notice, in-person public events have been canceled. Event listings include how to access online content.
Please check https://returnto.duke.edu/campus-visitors/ before coming to campus.

MEMS Seminar Presents: Robust and Multi-Agent Reinforcement Learning: Towards Safe and Large-scale Autonomy

Kaiqing Zhang
Icon calendar
Thursday, April 08, 2021
Icon time
9:00 am - 10:00 am
Icon location
Icon speaker
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

Contact: Glenda Hester