In this study, we consider a variant of the Follow the Regularized Leader (FTRL) dynamics in two-player zero-sum games. FTRL is guaranteed to converge to a Nash equilibrium when time-averaging the strategies, while a lot of variants suffer from the issue of limit cycling behavior, i.e., lack the last-iterate convergence guarantee. To this end, we propose mutant FTRL (M-FTRL), an algorithm that introduces mutation for the perturbation of action probabilities. We then investigate the continuous-time dynamics of M-FTRL and provide the strong convergence guarantees toward stationary points that approximate Nash equilibria under full-information feedback. Furthermore, our simulation demonstrates that M-FTRL can enjoy faster convergence rates than FTRL and optimistic FTRL under full-information feedback and surprisingly exhibits clear convergence under bandit feedback.
@article{arxiv.2206.09254,
title = {Mutation-Driven Follow the Regularized Leader for Last-Iterate Convergence in Zero-Sum Games},
author = {Kenshi Abe and Mitsuki Sakamoto and Atsushi Iwasaki},
journal= {arXiv preprint arXiv:2206.09254},
year = {2022}
}