IE Seminar: “Networked Strategic Learning for Autonomous Systems”, Ceyhun Eksin, 1:30PM December 28 (EN)

Speaker: Ceyhun Eksin, Texas A&M University

Date & Time: December 28, 2022, Wednesday 13:30

Place: EA-409

Title: Networked Strategic Learning for Autonomous Systems

Abstract: Networked multi-agent systems include multiple autonomous decision-makers that aspire to achieve their objectives in the absence of a central coordinator. Examples of such decision-makers include robots in a team, or smart meters in the electricity grid. The central challenge in these systems is to design decision-making rules that achieve system-wide desired behavior given the limitations of agent sensing and communication. In a networked autonomous system, barring unreasonable accuracy of environmental information and unjustifiable levels of coordination, agents cannot be sure of what other agents are optimizing when agents’ objectives depend on others’ actions, and dynamic and unknown environment variables. In such settings, agents have persisting differences in their estimates of their objectives. In this talk, upon adopting game-theoretic equilibrium notions as the optimal
(desired) behavior, we present a suite of decentralized algorithms based on fictitious play in which agents reason about the actions of other agents to make their selections in random communication settings, and unknown and dynamic environments. We show the convergence of the decentralized fictitious play to an equilibrium under a general condition for communication. Based on this general condition, we provide novel communication protocols, and discuss trade-offs in communication cost versus optimality. Lastly, we provide convergence guarantees when environmental uncertainty among agents persists, i.e., when consensus is not feasible. Our results push toward understanding the values of communication and local information in achieving a team objective in autonomous systems.

Bio: Ceyhun Eksin is an assistant professor at Industrial and Systems Engineering Department in Texas A&M University. He received his Ph.D. in Electrical and Systems Engineering from the University of Pennsylvania in 2015, and was subsequently a Postdoctoral Fellow at the Georgia Institute of Technology affiliated with both the School of Electrical & Computer Engineering and the School of Biological Sciences. He also has a M.S. degree in Industrial Engineering from Boğaziçi University, Istanbul, Turkey in 2008. His B.S. degree is in Control Engineering from Istanbul Technical University, Istanbul, Turkey in 2005. His research interests are in the areas of distributed optimization, network science, game theory and control theory. His current research focuses on game theoretic modeling and optimization of multi-agent systems in biological, communication and social networks.