A Bayesian optimization approach to find Nash equilibria

Abstract : Game theory finds nowadays a broad range of applications in engineering and machine learning. However, in a derivative-free, expensive black-box context, very few algorithmic solutions are available to find game equilibria. Here, we propose a novel Gaussian-process based approach for solving games in this context. We follow a classical Bayesian optimization framework, with sequential sampling decisions based on acquisition functions. Two strategies are proposed, based either on the probability of achieving equilibrium or on the Stepwise Uncertainty Reduction paradigm. Practical and numerical aspects are discussed in order to enhance the scalability and reduce computation time. Our approach is evaluated on several synthetic game problems with varying number of players and decision space dimensions. We show that equilibria can be found reliably for a fraction of the cost (in terms of black-box evaluations) compared to classical, derivative-based algorithms.
Type de document :
Pré-publication, Document de travail
2016
Liste complète des métadonnées

Littérature citée [39 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01405074
Contributeur : Abderrahmane Habbal <>
Soumis le : jeudi 15 décembre 2016 - 15:57:26
Dernière modification le : jeudi 3 mai 2018 - 13:32:58
Document(s) archivé(s) le : jeudi 16 mars 2017 - 18:26:31

Fichier

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

Identifiants

  • HAL Id : hal-01405074, version 1

Collections

Citation

Victor Picheny, Mickael Binois, Abderrahmane Habbal. A Bayesian optimization approach to find Nash equilibria. 2016. 〈hal-01405074〉

Partager

Métriques

Consultations de la notice

580

Téléchargements de fichiers

107