Seminar: Learning in games with applications to electricity markets by Maryam Kamgarpour

Abstract

A rising challenge in control of large-scale control systems such as the energy and the transportation networks is to address autonomous decision making of interacting agents. Game theory provides a framework to model and analyze this class of problems. In several realistic applications, such as power markets, each player has partial information about the cost functions and actions of other players. Thus, a learning approach is needed to design optimal decisions for each player. I will present our work on designing algorithms for learning in convex and non-convex games. In the convex setting, I will present our zeroth-order gradient descent based algorithm and discuss conditions for its convergence. In the non-convex setting, I will present our no-regret algorithm that leverages probabilistic estimation of a players' cost function. I will discuss the applicability of the approaches to electricity markets.

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. Her 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, NASA Excellence in Publication Award, and the European Union (ERC) Starting Grant.