Title: Learning and Influence in Networked Multiagent Systems with Uncertainty
Date: 20-Jun-19
Location: Aula L3S6 (Laboratorios III)
Speaker: Ceyhun Eksin (Texas A&M University)
Attached Documents: ppt
Abstract: Networked multi-agent systems include multiple autonomous decision-makers whose individual actions give rise to collective phenomena. Examples of such decision-makers are robots in a team, smart meters in the electricity grid, or individuals during an infectious disease outbreak. The central challenge in these systems is to design decision-making rules that achieve desired system-wide behavior given the limitations of agent sensing and communication. In this talk, I first address this challenge by introducing the framework of Bayesian network games to model repeated local interactions and rational decision-making in settings of incomplete information. Under this framework, I present asymptotic convergence properties of rational behavior in coordination games, and present issues in tractable computation of rational behavior. Then, I leverage this framework to introduce tractable decentralized learning algorithms with asymptotic convergence guarantees to rational behavior in potential games. The algorithms are implemented on a team of ground robots solving a target assignment problem. The talk will conclude with a discussion on control of local decision-making algorithms aiming to explore how by influencing a subset of individuals we can improve the system level emerging behavior.
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. 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.