Salvato in:
Dettagli Bibliografici
Autori principali: Ashkenazi-Golan, Galit, Cecchelli, Domenico Mergoni, Plumb, Edward
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.10378
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916739214737408
author Ashkenazi-Golan, Galit
Cecchelli, Domenico Mergoni
Plumb, Edward
author_facet Ashkenazi-Golan, Galit
Cecchelli, Domenico Mergoni
Plumb, Edward
contents This paper examines the convergence behaviour of simultaneous best-response dynamics in random potential games. We provide a theoretical result showing that, for two-player games with sufficiently many actions, the dynamics converge quickly to a cycle of length two. This cycle lies within the intersection of the neighbourhoods of two distinct Nash equilibria. For three players or more, simulations show that the dynamics converge quickly to a Nash equilibrium with high probability. Furthermore, we show that all these results are robust, in the sense that they hold in non-potential games, provided the players' payoffs are sufficiently correlated. We also compare these dynamics to gradient-based learning methods in near-potential games with three players or more, and observe that simultaneous best-response dynamics converge to a Nash equilibrium of comparable payoff substantially faster.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10378
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Simultaneous Best-Response Dynamics in Random Potential Games
Ashkenazi-Golan, Galit
Cecchelli, Domenico Mergoni
Plumb, Edward
Computer Science and Game Theory
This paper examines the convergence behaviour of simultaneous best-response dynamics in random potential games. We provide a theoretical result showing that, for two-player games with sufficiently many actions, the dynamics converge quickly to a cycle of length two. This cycle lies within the intersection of the neighbourhoods of two distinct Nash equilibria. For three players or more, simulations show that the dynamics converge quickly to a Nash equilibrium with high probability. Furthermore, we show that all these results are robust, in the sense that they hold in non-potential games, provided the players' payoffs are sufficiently correlated. We also compare these dynamics to gradient-based learning methods in near-potential games with three players or more, and observe that simultaneous best-response dynamics converge to a Nash equilibrium of comparable payoff substantially faster.
title Simultaneous Best-Response Dynamics in Random Potential Games
topic Computer Science and Game Theory
url https://arxiv.org/abs/2505.10378