Multi-agent online learning in time-varying games
Computer Science and Game Theory
2022-08-11 v3 Machine Learning
Optimization and Control
Abstract
We examine the long-run behavior of multi-agent online learning in games that evolve over time. Specifically, we focus on a wide class of policies based on mirror descent, and we show that the induced sequence of play (a) converges to Nash equilibrium in time-varying games that stabilize in the long run to a strictly monotone limit; and (b) it stays asymptotically close to the evolving equilibrium of the sequence of stage games (assuming they are strongly monotone). Our results apply to both gradient-based and payoff-based feedback - i.e., the "bandit feedback" case where players only get to observe the payoffs of their chosen actions.
Cite
@article{arxiv.1809.03066,
title = {Multi-agent online learning in time-varying games},
author = {Benoit Duvocelle and Panayotis Mertikopoulos and Mathias Staudigl and Dries Vermeulen},
journal= {arXiv preprint arXiv:1809.03066},
year = {2022}
}
Comments
35 pages