Learning dynamics and equilibrium selection
Abstract:
One approach to distributed control of networked systems is to represent the collective system as a game and endow individual components with preferences so that a solution concept, such as Nash equilibrium, reflects desirable collective behavior. One issue is that games can have multiple equilibria, thereby resulting in loss of efficiency (cf., the notions of "price of anarchy" and "price of stability"). An additional degree of freedom in engineered systems is that one also can specify the adaptation or learning dynamics that lead the collective towards equilibrium. These dynamics can themselves serve as a devise for equilibrium selection. This talk presents a sampling of prior and recent results on the dynamics effect in equilibrium selection and provides examples from distributed coordination and network formation.
Biography:
Jeff Shamma's research interest is feedback control and systems theory. He received a BS in Mechanical Engineering from Georgia Tech in 1983 and a PhD in Systems Science and Engineering from the Massachusetts Institute of Technology in 1988. He has held faculty positions at the University of Minnesota, Minneapolis; University of Texas, Austin; and University of California, Los Angeles; and visiting positions at Caltech and MIT. In 2007, Jeff returned to Georgia Tech where he is a Professor of Electrical and Computer Engineering and Julian T. Hightower Chair in Systems & Control. He is a recipient of the NSF Young Investigator Award (1992) and the American Automatic Control Council Donald P. Eckman Award (1996), and a Fellow of the IEEE (2006). He is currently serving on the Air Force Scientific Advisory Board and is an associate editor for the IEEE Transactions on Systems, Man, and Cybernetics, Part B. Jeff's interests include fishing in the local lakes & rivers of Georgia or in his hometown of Pensacola and chatting (and arguing) with his brother.