English

Asymptotic Extinction in Large Coordination Games

Computer Science and Game Theory 2024-12-23 v1 Disordered Systems and Neural Networks

Abstract

We study the exploration-exploitation trade-off for large multiplayer coordination games where players strategise via Q-Learning, a common learning framework in multi-agent reinforcement learning. Q-Learning is known to have two shortcomings, namely non-convergence and potential equilibrium selection problems, when there are multiple fixed points, called Quantal Response Equilibria (QRE). Furthermore, whilst QRE have full support for finite games, it is not clear how Q-Learning behaves as the game becomes large. In this paper, we characterise the critical exploration rate that guarantees convergence to a unique fixed point, addressing the two shortcomings above. Using a generating-functional method, we show that this rate increases with the number of players and the alignment of their payoffs. For many-player coordination games with perfectly aligned payoffs, this exploration rate is roughly twice that of pp-player zero-sum games. As for large games, we provide a structural result for QRE, which suggests that as the game size increases, Q-Learning converges to a QRE near the boundary of the simplex of the action space, a phenomenon we term asymptotic extinction, where a constant fraction of the actions are played with zero probability at a rate o(1/N)o(1/N) for an NN-action game.

Keywords

Cite

@article{arxiv.2412.15461,
  title  = {Asymptotic Extinction in Large Coordination Games},
  author = {Desmond Chan and Bart De Keijzer and Tobias Galla and Stefanos Leonardos and Carmine Ventre},
  journal= {arXiv preprint arXiv:2412.15461},
  year   = {2024}
}

Comments

21 pages, 19 figures, to be published in AAAI (Association for the Advancement of Artificial Intelligence) 2025

R2 v1 2026-06-28T20:43:11.912Z