English

Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games

Computer Science and Game Theory 2025-03-05 v2 Machine Learning

Abstract

We study last-iterate convergence properties of algorithms for solving two-player zero-sum games based on Regret Matching+^+ (RM+^+). Despite their widespread use for solving real games, virtually nothing is known about their last-iterate convergence. A major obstacle to analyzing RM-type dynamics is that their regret operators lack Lipschitzness and (pseudo)monotonicity. We start by showing numerically that several variants used in practice, such as RM+^+, predictive RM+^+ and alternating RM+^+, all lack last-iterate convergence guarantees even on a simple 3×33\times 3 matrix game. We then prove that recent variants of these algorithms based on a smoothing technique, extragradient RM+^{+} and smooth Predictive RM+^+, enjoy asymptotic last-iterate convergence (without a rate), 1/t1/\sqrt{t} best-iterate convergence, and when combined with restarting, linear-rate last-iterate convergence. Our analysis builds on a new characterization of the geometric structure of the limit points of our algorithms, marking a significant departure from most of the literature on last-iterate convergence. We believe that our analysis may be of independent interest and offers a fresh perspective for studying last-iterate convergence in algorithms based on non-monotone operators.

Keywords

Cite

@article{arxiv.2311.00676,
  title  = {Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games},
  author = {Yang Cai and Gabriele Farina and Julien Grand-Clément and Christian Kroer and Chung-Wei Lee and Haipeng Luo and Weiqiang Zheng},
  journal= {arXiv preprint arXiv:2311.00676},
  year   = {2025}
}

Comments

Accepted to ICLR 2025