Entropy-driven dynamics and robust learning procedures in games

Abstract : In this paper, we introduce a new class of game dynamics made of a pay-off replicator-like term modulated by an entropy barrier which keeps players away from the boundary of the strategy space. We show that these {\it entropy-driven} dynamics are equivalent to players computing a score as their on-going exponentially discounted cumulative payoff and then using a quantal choice model on the scores to pick an action. This dual perspective on {\it entropy-driven} dynamics helps us to extend the folk theorem on convergence to quantal response equilibria to this case, for potential games. It also provides the main ingredients to design a discrete time effective learning algorithm that is fully distributed and only requires partial information to converge to QRE. This convergence is resilient to stochastic perturbations and observation errors and does not require any synchronization between the players.
Liste complète des métadonnées

Littérature citée [33 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00790815
Contributeur : Bruno Gaujal <>
Soumis le : jeudi 21 février 2013 - 11:18:45
Dernière modification le : jeudi 9 février 2017 - 15:41:52
Document(s) archivé(s) le : dimanche 2 avril 2017 - 03:16:15

Fichier

rr.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00790815, version 1

Collections

Citation

Pierre Coucheney, Bruno Gaujal, Panayotis Mertikopoulos. Entropy-driven dynamics and robust learning procedures in games. [Research Report] RR-8210, INRIA. 2013, pp.33. 〈hal-00790815〉

Partager

Métriques

Consultations de la notice

453

Téléchargements de fichiers

218