| Distinguished Lecture 6 | Data-Driven Optimization Control with Off-policy Reinforcement Learning |
| Date/Time | Tuesday, May 31, 2016 17:00-17:40 |
| Venue | International Leture Hall of the 2nd floor |
| Presenter | Dr. Biao Luo, Institute of Automation, Chinese Academy of Sciences, China |
Abstract
For practical complex systems, it is extremely difficult to identify their accurate mathematical model for control design. In the past few years, data-driven control has appeared as a promising method to overcome this difficulty and has attracted extensive attention from researchers.Dr. Biao Luo studied the data-driven optimization control problems of complex systems and developed the off-policy reinforcement learning methods to learn the optimization controller directly.
Biography
Paulo Tabuada an Assistant Professor at Institute of Automation, Chinese Academy of Sciences, Beijing, China. He received his Ph.D. degree from Beihang University, Beijing, China, 2014. From February 2013 to August 2013, he was a Research Assistant with the Department of System Engineering and Engineering Management, City University of Hong Kong, Kowloon, Hong Kong. From September 2013 to December 2013, from June 2014 to August 2014 and from June 2015 to July 2015, he was a Research Assistant/Associate with Department of Mathematics and Science, Texas A&M University at Qatar, Doha, Qatar. His current research interests include distributed parameter systems, optimal control, data-based control, fuzzy/neural modeling and control, learning and control from big data, reinforcement learning, approximate dynamic programming, and evolutionary computation. Dr. Luo serves as Associate Editor of the Artificial Intelligence Review. He was a recipient of the Chinese Association of Automation (CAA) Excellent Doctoral Dissertation Award in 2015.