On the afternoon of November 16, 2014, a remarkable academic lecture entitled “Reinforcement Learning Structures for Real-Time Optimal Control and Differential Games && Distributed optimization of multi-agent systems” was held by the School of Automation Science and Engineering in Building 3. The lecture was given by Professor Biosketch F.L. Lewis and Professor Yiguang Hong. Professor Biosketch F.L. Lewis, the Distinguished Scholar Professor, the Distinguished Teaching Professor, and Moncrief-O Donnell Endowed Chair of The University of Texas at Arlington , is the Fellow of IEEE, IFAC and U.K. Institute of Measurement & Control. Professor Yiguang Hong is currently a professor of Academy of Mathematics and Systems Science, Chinese Academy of Sciences (CAS). He is the director of Key Lab of Systems & Control, CAS, and the director of Information Technology Division of National Center for Mathematics and Interdisciplinary Sciences, CAS.
The lecture was hosted by Prof. Weizhou Su, who is the professor of School of Automation Science and Engineering. At the beginning of this lecture, Prof. Lewis presented us the topic of “Reinforcement Learning Structures for Real-Time Optimal Control and Differential Games”. He talked about how to use the method of reinforcement learning structures to deal with real-time optimal control. What’s more, an iterative algorithm of cooperation strategy was introduced to solve the differential game. In the second half of this lecture, Prof. Hong showed us the outstanding lecture titled “Distributed optimization of multi-agent systems”. He firstly introduced the background and the basic challenges of multi-agent, and then brought up concept of the distributed optimization and its application. Furthermore, the distributed convex calculation method and the technological problems was explained in detail. In these two sub-lectures, the interation was active between lecturers and students.
