ApproxED: Approximate exploitability descent via learned best responses

arXiv:2301.08830v3 Announce Type: replace-cross
Abstract: There has been substantial progress on finding game-theoretic equilibria. Most of that work has focused on games with finite, discrete action spaces. However, many games involving space, time, money, and other fine-grained quantities have continuous action spaces (or are best modeled as having such). We study the problem of finding an approximate Nash equilibrium of games with continuous action sets. The standard measure of closeness to Nash equilibrium is exploitability, which measures how much players …

abstract action arxiv continuous cs.ai cs.gt cs.lg cs.ma equilibria fine-grained game games however money progress replace responses space spaces study type via work