Dr Maryam Kamgarpour

Biography

Maryam Kamgarpour holds a Doctor of Philosophy in Engineering from the University of California, Berkeley and a Bachelor of Applied Science from University of Waterloo, Canada. Her research is on safe decision-making and control under uncertainty, game theory and mechanism design, mixed integer and stochastic optimization and control.

Dr Kamgarpour’s theoretical research is motivated by control challenges arising in intelligent transportation networks, robotics, power grid systems and healthcare. She is the recipient of NASA High Potential Individual Award (2010) the European Union (ERC) Starting Grant (2015) and European Control Award (2024).

Abstract

A significant challenge in managing large-scale engineering systems, such as energy and transportation networks, lies in enabling the autonomous decision-making of interacting agents. Game theory offers a framework for modeling and analyzing this class of problems. In many practical applications, each player only has partial information about the cost functions and actions of others. Therefore, a decentralized learning approach is essential to devising optimal strategies for each player.

Dr Kamgarour’s talk will focus on recent advances in decentralized learning algorithms for multiagent games. She will highlight challenges of computing and learning equilibria in games compared to single-agent optimization and learning. She will then proceed by discussing algorithms with provable convergence guarantees for learning equilibria in static and dynamic games. She will present applications from the domain of energy, robotics and transportation.