IFML Seminar: 11/21/25 - Learning Dynamics in Multiplayer Games

Abstract: Intelligence often emerges through interaction and competition. Likewise, advanced AI algorithms often rely on competing learning objectives. Whether through data sampling, environmental interaction, or self-play, agents iteratively adapt their strategies in pursuit of an equilibrium—where the competing objectives are balanced. This talk explores the learning dynamics in multiplayer games, where multiple agents learn and adapt simultaneously. We will examine how these dynamics differ from single-agent optimization, addressing key challenges such as rotational learning dynamics, stochastic noise, and strategic constraints. Drawing on examples from machine learning— including robust optimization, generative adversarial networks, and multi-agent reinforcement learning—the talk will highlight the implications of these dynamics for understanding and designing modern learning systems.

 

Bio: Tatjana Chavdarova is currently a visiting professor in the Department of Electronics, Information, and Bioengineering (DEIB) at Politecnico di Milano (PoliMi), where she collaborates with Nicola Gatti and Nicolò Cesa-Bianchi. Her research lies at the intersection of game theory and machine learning, with a particular emphasis on optimization and algorithmic innovation. She received her Ph.D. in machine learning from EPFL and Idiap Research Institute, supervised by François Fleuret. During her doctoral studies, she completed internships at Mila, working with Yoshua Bengio and Simon Lacoste-Julien, and at DeepMind, under the mentorship of Irina Jurenka (formerly Higgins). Following her Ph.D., Tatjana was a Postdoctoral Research Scientist at EPFL’s Machine Learning and Optimization (MLO) lab with Martin Jaggi, and at UC Berkeley working with Michael I. Jordan. Her research has been supported by the Swiss National Science Foundation through the Early.Postdoc.Mobility and Postdoc.Mobility fellowships and, most recently, by the Vienna Science and Technology Fund (WWTF). Website: https://chavdarova.github.io/

Zoom link: https://utexas.zoom.us/j/84254847215