MAE Seminar (ZOOM): Game Theory and Self-organizing Decision Systems

Abstract: The language of game theory naturally lends itself to distributed decision architectures, where individual, yet interconnected, actors take decisions based on local information and interactions. From the perspective of a system planner, a goal is to incentivize individual behaviors to induce desirable global outcomes. From the perspective of a system modeler, a goal is to understand possible emergent behaviors stemming from local interactions. This talk presents how game theory---more specifically game-theoretic learning---can address these issues in both natural and artificial settings, with examples drawn from distributed matching, multi-agent reinforcement learning and swarm robotics.

Bio: Jeff S. Shamma is a professor of electrical engineering and director for the Center of Excellence for NEOM Research at the King Abdullah University of Science and Technology, Saudi Arabia (KAUST). Prior to joining KAUST, he was the Julian T. Hightower Chair in Systems & Control at the Georgia Institute of Technology. Shamma received a doctorate in systems science and engineering from MIT in 1988. He is the recipient of an NSF Young Investigator Award, the AACC Donald P. Eckman Award, and the IFAC High Impact Paper Award, and he is a fellow of IEEE and IFAC. Shamma is currently serving as the editor-in-chief for the IEEE Transactions on Control of Network Systems and an associate editor of the IEEE Transactions on Robotics.