Equilibrium tracking and convergence in dynamic games - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Equilibrium tracking and convergence in dynamic games

Abstract

In this paper, we examine the equilibrium tracking and convergence properties of no-regret learning algorithms in continuous games that evolve over time. Specifically, we focus on learning via "mirror descent", a widely used class of noregret learning schemes where players take small steps along their individual payoff gradients and then "mirror" the output back to their action sets. In this general context, we show that the induced sequence of play stays asymptotically close to the evolving equilibrium of the sequence of stage games (assuming they are strongly monotone), and converges to it if the game stabilizes to a strictly monotone limit. Our results apply to both gradient-and payoff-based feedback, i.e., the "bandit" case where players only observe the payoffs of their chosen actions.
Fichier principal
Vignette du fichier
2021-CDC-EquilibriumTracking.pdf (277.12 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03342397 , version 1 (13-09-2021)

Identifiers

  • HAL Id : hal-03342397 , version 1

Cite

Panayotis Mertikopoulos, Mathias Staudigl. Equilibrium tracking and convergence in dynamic games. CDC 2021 - 60th IEEE Annual Conference on Decision and Control, Dec 2021, Austin, United States. pp.1-8. ⟨hal-03342397⟩
61 View
158 Download

Share

Gmail Facebook X LinkedIn More