Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dong, Jing, Wang, Baoxiang, Yu, Yaoliang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913469301784576
author Dong, Jing
Wang, Baoxiang
Yu, Yaoliang
author_facet Dong, Jing
Wang, Baoxiang
Yu, Yaoliang
contents We study the problem of no-regret learning algorithms for general monotone and smooth games and their last-iterate convergence properties. Specifically, we investigate the problem under bandit feedback and strongly uncoupled dynamics, which allows modular development of the multi-player system that applies to a wide range of real applications. We propose a mirror-descent-based algorithm, which converges in $O(T^{-1/4})$ and is also no-regret. The result is achieved by a dedicated use of two regularizations and the analysis of the fixed point thereof. The convergence rate is further improved to $O(T^{-1/2})$ in the case of strongly monotone games. Motivated by practical tasks where the game evolves over time, the algorithm is extended to time-varying monotone games. We provide the first non-asymptotic result in converging monotone games and give improved results for equilibrium tracking games.
format Preprint
id arxiv_https___arxiv_org_abs_2408_08395
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback
Dong, Jing
Wang, Baoxiang
Yu, Yaoliang
Computer Science and Game Theory
We study the problem of no-regret learning algorithms for general monotone and smooth games and their last-iterate convergence properties. Specifically, we investigate the problem under bandit feedback and strongly uncoupled dynamics, which allows modular development of the multi-player system that applies to a wide range of real applications. We propose a mirror-descent-based algorithm, which converges in $O(T^{-1/4})$ and is also no-regret. The result is achieved by a dedicated use of two regularizations and the analysis of the fixed point thereof. The convergence rate is further improved to $O(T^{-1/2})$ in the case of strongly monotone games. Motivated by practical tasks where the game evolves over time, the algorithm is extended to time-varying monotone games. We provide the first non-asymptotic result in converging monotone games and give improved results for equilibrium tracking games.
title Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback
topic Computer Science and Game Theory
url https://arxiv.org/abs/2408.08395