报告地点：信息楼自动化学院310报告厅
ZOOM（会议ID：983 8099 5221，密码：201126）
报告时间：11月26日（星期四）9:40
报 告 人：姜钟平，纽约大学教授
报告题目：Reinforcement Learning and Optimal Control for Uncertain Systems
内容简介：Entanglement of reinforcement learning and control theory has led to tremendous progresses in data-driven control over the past few years. However, most of existing results focused more on problems with stationary models plus infinite horizon costs, which leads to stationary value functions and stationary optimal controls. Relatively few results are known for problems with time-varying models plus finite or infinite horizon costs, which leads to time-varying value functions and time-varying optimal controls. Due to the fundamental difference between these two kinds of problems, the methods for the stationary case can hardly be adopted for the nonstationary setting directly. In this talk, I will present our recent results in learning-based optimal control for uncertain systems which may be time-varying. If time permits, I will also report on our latest work that looks at the robustness analysis of reinforcement learning algorithms from a nonlinear control perspective.
报告人简介：Zhong-Ping Jiang received the M.Sc. degree in statistics from the University of Paris XI, France, in 1989, and the Ph.D. degree in automatic control and mathematics from the Ecole des Mines de Paris (now, called ParisTech-Mines), France, in 1993, under the direction of Prof. Laurent Praly. Currently, he is a Professor of Electrical and Computer Engineering at the Tandon School of Engineering, New York University. His main research interests include stability theory, robust/adaptive/distributed nonlinear control, robust adaptive dynamic programming, reinforcement learning and their applications to information, mechanical and biological systems. In these fields, he has written five books and is author/co-author of over 450 peer-reviewed journal and conference papers. Dr. Jiang has served as Deputy Editor-in-Chief, Senior Editor and Associate Editor for numerous journals. Prof. Jiang is a Fellow of the IEEE, a Fellow of the IFAC, a Fellow of the CAA and is among the Clarivate Analytics Highly Cited Researchers.