Equilibrium Selection in Potential Games with Noisy Rewards

Abstract : Game theoretical learning in potential games is a highly active research area stemming from the connection between potential games and distributed optimisation. In many settings an optimisation problem can be represented by a potential game where the optimal solution corresponds to the potential function maximizer. Accordingly, significant research attention has focused on the design of distributed learning algorithms that guarantee convergence to the potential maximizer in potential games. However, there are currently no existing algorithms that provide convergence to the potential function maximiser when utility functions are corrupted by noise. In this paper we rectify this issue by demonstrating that a version of payoff-based loglinear learning guarantees that the only stochastically stable states are potential function maximisers even in noisy settings.
Type de document :
Communication dans un congrès
Roberto Cominetti and Sylvain Sorin and Bruno Tuffin. NetGCOOP 2011 : International conference on NETwork Games, COntrol and OPtimization, Oct 2011, Paris, France. IEEE, 2011
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00644411
Contributeur : Ist Rennes <>
Soumis le : jeudi 24 novembre 2011 - 14:02:10
Dernière modification le : mardi 26 décembre 2017 - 13:48:05
Document(s) archivé(s) le : vendredi 16 novembre 2012 - 11:56:29

Fichier

17-PDFexpress_Approved.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00644411, version 1

Collections

Citation

David Leslie, Jason Marden. Equilibrium Selection in Potential Games with Noisy Rewards. Roberto Cominetti and Sylvain Sorin and Bruno Tuffin. NetGCOOP 2011 : International conference on NETwork Games, COntrol and OPtimization, Oct 2011, Paris, France. IEEE, 2011. 〈hal-00644411〉

Partager

Métriques

Consultations de la notice

78

Téléchargements de fichiers

305