MAE Seminar – Multi-agent higher-order learning vs Nash equilibrium

Details

Dear Undergraduate and Graduate Students, Faculty, and Staff,
You are invited! UF Department of Mechanical and Aerospace Engineering’s Seminar Series
This is a perfect opportunity to enjoy some coffee, cookies, and captivating talks! These sessions feature amazing guest speakers, from academic trailblazers and industry movers to our very own faculty candidates showing off their expertise and fresh perspectives.
Come for the treats, stay for the engaging discussions, and connect with fellow MAE enthusiasts. Everyone is welcome!

Multi-agent higher-order learning vs Nash equilibrium

April 3, 2025, at 12:50pm, Location: MAE-A 303

Prof. Jeff Shamma
Department Head, Professor and Jerry S. Dobrovolny Chair in ISE
Department of Industrial and Enterprise Systems Engineering
University of Illinois Urbana-Champaign

Abstract
The framework of multi-agent learning explores the dynamics of how individual agent strategies evolve in response to the evolving strategies of other agents. Of particular interest is whether agent strategies converge to well-known solution concepts such as Nash Equilibrium (NE). Most standard learning dynamics restrict an agent’s underlying state to be its own strategy. In “higher order” learning, agent dynamics can include auxiliary states that can capture phenomena such as path dependencies. We introduce higher-order gradient play dynamics. The dynamics are “payoff based” in that each agent’s dynamics depend on its own evolving payoff, and hence “uncoupled” since an agent’s dynamics do not depend explicitly on the utility functions of other agents. We first show that for any specific game with an isolated completely mixed-strategy NE, there exist higher-order gradient play dynamics that lead (locally) to that NE, both for the original game and nearby games. Conversely, we show that such dynamics, there exists a game with a unique isolated completely mixed-strategy NE for which the dynamics do not lead to NE. Finally, we consider the mixed-strategy equilibrium associated with coordination games. While higher-order gradient play can converge to such equilibria, we show such dynamics must be inherently irrational.

Biography
Dr. Jeff Shamma is Department Head of Industrial and Enterprise Systems Engineering and Jerry S. Dobrovolny Chair at the University of Illinois Urbana-Champaign. He previously held faculty positions at the King Abdullah University of Science and Technology (KAUST) and at Georgia Tech as the Julian T. Hightower Chair in Systems and Controls. Dr. Shamma received a PhD in Systems Science and Engineering from MIT in 1988. He is a Fellow of IEEE and IFAC, a past Distinguished Lecturer of the IEEE Control Systems Society, and a recipient of the IFAC High Impact Paper Award, AACC Donald P. Eckman Award, and NSF Young Investigator Award. Dr. Shamma has been a plenary/semi-plenary speaker at NeurIPS, World Congress of the Game Theory Society, and IEEE Conference on Decision and Control. He was Editor-in-Chief of the IEEE Transactions on Control of Network Systems from 2020-2024. Dr. Shamma’s research focuses on decision and control, game theory, and multi-agent systems.

MAE Faculty Host: Rushikesh Kamalapurkar