GAIN – Games, AI, and Networks Research Lab

We study learning and control in multi-agent systems—where humans and AI make decisions together. Our goal: principled methods to analyze, steer, and optimize socio-technical systems. Therefore, at the GAIN Lab,

  • We focus on developing a foundational understanding of learning and autonomy in complex, dynamic, and multi-agent systems.
  • We develop new methodologies for analyzing, controlling, and optimizing socio-technical systems.
  • We apply these methodologies to specific problems in urban mobility, robotics, and the digital economy.

See the following posters and the video recordings as examples of our recent research projects:

A. S. Donmez, Y. Arslantas, and M. O. Sayin, “Team-fictitious play for reaching team-Nash equilibrium in multi-team games,” In Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2024.
M. O. Sayin, K. Zhang, D. S. Leslie, T. Başar, and A. Ozdaglar, “Decentralized Q-learning in zero-sum Markov games,” In Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), virtual, 2021.
Algorithmic Learning in Games Seminar Series in March 2025
University of Minnesota, Institute for Mathematics & Its Applications, Data Science Seminar in Apr. 2023
ACM Conference on Economics and Computation, University of Colorado Boulder in July 2022

We are looking for new team members. Please get in touch with us if you are interested in!

Recent News

  • [Oct. 2025] Dr. Sayin is Technical Program Co-Chair of GameSec 2025 – Conference on Game Theory and AI for Security (Athens, October 13–15). The conference will feature keynote speakers Marta Kwiatkowska (Oxford), Milind Tambe (Harvard & Google Deepmind), Michael I. Jordan (Inria & UC Berkeley), and Lorenzo Cavallaro (UCL).
  • [Sep. 2025] New team members at GAIN! We are pleased to welcome Arda Koşay and Ozan Cem Baş to the GAIN Lab.
  • [Jun. 2025] Our paper “Logit-Q dynamics for efficient learning in stochastic teams” got accepted to the SIAM Journal on Control and Optimization.
  • [May 2025] Our paper “Convergence of heterogeneous learning dynamics in zero-sum stochastic games” got accepted to the IEEE Transactions on Automatic Control.
  • [May 2025] Our joint work “Dynamic feedback strategies for duopolies over partially observed consumer networks” with Dr. Saeed Ahmed from the University of Groningen got accepted to the Dynamic Games and Applications.
  • [Mar. 2025] Dr. Sayin gave an invited talk titled “Multi-team reinforcement learning” at the Algorithmic Learning in Games Seminar (ALIGS) Series.