Last-Iterate Convergence with Full and Noisy Feedback in Two-Player Zero-Sum Games
Kenshi Abe, Kaito Ariu, Mitsuki Sakamoto, Kentaro Toyoshima, Atsushi Iwasaki
Abstract
This paper proposes Mutation-Driven Multiplicative Weights Update (M2WU) for learning an equilibrium in two-player zero-sum normal-form games and proves that it exhibits the last-iterate convergence property in both full and noisy feedback settings. In the former, players observe their exact gradient vectors of the utility functions. In the latter, they only observe the noisy gradient vectors. Even the celebrated Multiplicative Weights Update (MWU) and Optimistic MWU (OMWU) algorithms may not converge to a Nash equilibrium with noisy feedback. On the contrary, M2WU exhibits the last-iterate convergence to a stationary point near a Nash equilibrium in both feedback settings. We then prove that it converges to an exact Nash equilibrium by iteratively adapting the mutation term. We empirically confirm that M2WU outperforms MWU and OMWU in exploitability and convergence rates.
BibTeX
@InProceedings{pmlr-v206-abe23a,
title = {Last-Iterate Convergence with Full and Noisy Feedback in Two-Player Zero-Sum Games},
author = {Abe, Kenshi and Ariu, Kaito and Sakamoto, Mitsuki and Toyoshima, Kentaro and Iwasaki, Atsushi},
booktitle = {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics},
pages = {7999--8028},
year = {2023},
editor = {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem},
volume = {206},
series = {Proceedings of Machine Learning Research},
month = {25--27 Apr},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v206/abe23a/abe23a.pdf},
url = {https://proceedings.mlr.press/v206/abe23a.html},
abstract = {This paper proposes Mutation-Driven Multiplicative Weights Update (M2WU) for learning an equilibrium in two-player zero-sum normal-form games and proves that it exhibits the last-iterate convergence property in both full and noisy feedback settings. In the former, players observe their exact gradient vectors of the utility functions. In the latter, they only observe the noisy gradient vectors. Even the celebrated Multiplicative Weights Update (MWU) and Optimistic MWU (OMWU) algorithms may not converge to a Nash equilibrium with noisy feedback. On the contrary, M2WU exhibits the last-iterate convergence to a stationary point near a Nash equilibrium in both feedback settings. We then prove that it converges to an exact Nash equilibrium by iteratively adapting the mutation term. We empirically confirm that M2WU outperforms MWU and OMWU in exploitability and convergence rates.}
}