讲座题目(Title of Lecture)：Scalable uncertainty evaluation for learning control and differential games

讲座时间(Time of Lecture)：2020年12月17日 上午10点

讲座地点(Site of Lecture)：腾讯会议  会议 ID：800 505 538

点击链接入会，或添加至会议列表：https://meeting.tencent.com/s/UNJMaX3HIewc

主讲人(Lecturer)：Professor Yan Wan，University of Texas at Arlington

报告人简介(Introduction of Lecturer)：

Dr. Yan Wan is currently a Professor in the Electrical Engineering Department at the University of Texas at Arlington. She received her Ph.D. degree in Electrical Engineering from Washington State University in 2009 and then did postdoctoral training at the University of California, Santa Barbara. Her research interests lie in the modeling, evaluation, and control of large-scale dynamical networks, cyber-physical system, stochastic networks, decentralized control, learning control, networking, uncertainty analysis, algebraic graph theory, and their applications to urban aerial mobility, autonomous driving, robot networking, and air traffic management. She received research grants from NSF, ONR, ARO, NIST, IEEE, Ford, Toyota, Lockheed, and MITRE Corporation as subcontracts from the FAA. Her research has led to over 190 publications and successful technology transfer outcomes. She has been recognized by several prestigious awards, including the NSF CAREER Award, RTCA William E. Jackson Award, U.S. Ignite and GENI demonstration awards, IEEE WCNC and ICCA Best Paper Awards, UTA Outstanding Research Achievement Award, and Tech Titan of the Future – University Level Award.

讲座内容(Content of Lecture)：

Multi-dimensional uncertainties often modulate modern system dynamics in a complicated fashion. They lead to challenges for real-time control, considering the significant computation load needed to evaluate them in real-time decision processes. We introduce the use of computationally effective uncertainty evaluation methods for adaptive optimal control, including learning control and differential games. Two uncertainty evaluation methods are described, the multivariate probabilistic collocation method (MPCM) and its extension the MPCM-OFFD that integrates the MPCM with the orthogonal fractional factorial design (OFFD) to break the curse of dimensionality. These scalable uncertainty evaluation methods are then developed for reinforcement learning (RL)-based adaptive optimal control and stochastic differential games. Nash equilibrium solutions for these games are found in real time using the MPCM-based on-policy/off-policy RL methods. Real-world applications on broad-band long-distance aerial networking, strategic air traffic management, and autonomous driving demonstrate the practical use of MPCM- and MPCM-OFFD- based learning control for uncertain systems.