Date and Time: Tuesday 3 February 2026, 16:00-16:45 CET
Speaker: Prof. Maryam Kamgarpour, EPFL
Title: Learning equilibria in games with bandit feedback
Zoom meeting ID: 687 9789 0812
More information on the website of Game On! Seminar series
Learning equilibria in games with bandit feedback
A central challenge in large-scale engineering systems, such as energy and transportation networks, is enabling autonomous decision-making among interacting agents. Game theory provides a natural framework to model and analyze such problems. In practice, however, agents often have only partial information about the costs and actions of others. This makes decentralized learning a key tool for developing effective strategies. In this talk, I will discuss recent advances in decentralized learning for static and Markov games under bandit feedback. I will outline algorithms with convergence guarantees and highlight directions for future research.
Prof. Maryam Kamgarpour, EPFL
The Game On! Seminar series is organized by Emilio Benenati and Giuseppe Belgioioso, affiliated with the Division of Decision and Control Systems (DCS) at KTH, Stockholm.
With this series, we aim to bring together researchers, practitioners, and students, in order to provide a broad overview of the current research directions being explored in modeling, analysis, and control of systems composed of multiple interacting agents.
Topics will include strategic and real-time decision-making, foundational and computational game theory, distributed control, learning in multiagent environments, and applications ranging from robotics to energy systems. Each session will feature a 30-45 minutes seminar on cutting-edge research, followed by an open discussion with the live audience.
The conference is co-sponsored by Digital Futures
