Prof. Maryam Kamgarpour, EPFL

Title: Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics (paper on arxiv)

Abstract: We study Nash equilibrium learning in partially observable Markov games (POMGs), a multi-agent reinforcement learning framework in which agents cannot fully observe the underlying state. Prior work in this setting relies on centralization or information sharing, and suffers from sample and computational complexity that scales exponentially in the number of players. We focus on a subclass of POMGs with independent state transitions, where agents remain coupled through their rewards, and assume that the underlying fully observed Markov game is a Markov potential game. For this class, we present an independent learning algorithm in which players, observing only their own actions and observations and without communication, jointly converge to an approximate Nash equilibrium. Due to partial observability, optimal policies may in general depend on the full action-observation history. Under a filter stability assumption, we show that policies based on finite history windows provide sufficient approximation guarantees. This enables us to approximate the POMG by a surrogate Markov game that is near-potential, leading to quasi-polynomial sample and computational complexity for independent Nash equilibrium learning in the underlying POMG.

Brief bio: Maryam Kamgarpour is an associate professor in the School of Engineering of École Polytechnique Fédérale de Lausanne. Prior to joining EPFL, she served as a faculty at the University of British Columbia and at ETH Zürich. She holds a Doctor of Philosophy in Engineering from the University of California, Berkeley and a Bachelor of Applied Science from the University of Waterloo, Canada. Her research focuses on developing theory and algorithms for control and learning in stochastic and multi-agent systems, as well as inverse control and learning, and mechanism design. These theoretical directions are motivated by control challenges in intelligent transportation systems, robotics, and power grid applications.

She has been awarded the European Union Consolidator Grant (2026-2031), the 2024 European Control Award, the European Union Starting Grant (2016-2021), an IEEE Transactions on Control of Network Systems Outstanding Paper (2022), NASA High Potential Individual Award (2010) and NASA Excellence in Publication Award (2010). She is an ELLIS Fellow and an associate editor for IEEE Transactions on Automatic Control.