The equivalence of dynamic and strategic stability under regularized learning in games - POLARIS - Performance analysis and Optimization of LARge Infrastructure and Systems Access content directly
Conference Papers Year : 2023

The equivalence of dynamic and strategic stability under regularized learning in games

Abstract

In this paper, we examine the long-run behavior of regularized, no-regret learning in finite games. A well-known result in the field states that the empirical frequencies of no-regret play converge to the game's set of coarse correlated equilibria; however, our understanding of how the players' actual strategies evolve over time is much more limited - and, in many cases, non-existent. This issue is exacerbated further by a series of recent results showing that only strict Nash equilibria are stable and attracting under regularized learning, thus making the relation between learning and pointwise solution concepts particularly elusive. In lieu of this, we take a more general approach and instead seek to characterize the \emph{setwise} rationality properties of the players' day-to-day play. To that end, we focus on one of the most stringent criteria of setwise strategic stability, namely that any unilateral deviation from the set in question incurs a cost to the deviator - a property known as closedness under better replies (club). In so doing, we obtain a far-reaching equivalence between strategic and dynamic stability: a product of pure strategies is closed under better replies if and only if its span is stable and attracting under regularized learning. In addition, we estimate the rate of convergence to such sets, and we show that methods based on entropic regularization (like the exponential weights algorithm) converge at a geometric rate, while projection-based methods converge within a finite number of iterations, even with bandit, payoff-based feedback.
Fichier principal
Vignette du fichier
Main.pdf (3.23 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
licence : CC BY - Attribution

Dates and versions

hal-04307883 , version 1 (26-11-2023)

Licence

Attribution

Identifiers

Cite

Victor Boone, Panayotis Mertikopoulos. The equivalence of dynamic and strategic stability under regularized learning in games. NeurIPS 2023 - 37th Conference on Neural Information Processing Systems, Dec 2023, New Orleans (LA), United States. pp.1-31. ⟨hal-04307883⟩
33 View
3 Download

Altmetric

Share

Gmail Facebook X LinkedIn More