We extend the classic regret minimization framework for approximating equilibria in normal-form games by greedily weighing iterates based on regrets observed at runtime. Theoretically, our method retains all previous convergence rate guarantees. Empirically, experiments on large randomly generated games and normal-form subgames of the AI benchmark Diplomacy show that greedy weights outperforms previous methods whenever sampling is used, sometimes by several orders of magnitude.
@article{arxiv.2204.04826,
title = {Equilibrium Finding in Normal-Form Games Via Greedy Regret Minimization},
author = {Hugh Zhang and Adam Lerer and Noam Brown},
journal= {arXiv preprint arXiv:2204.04826},
year = {2022}
}