Hedging Algorithms and Repeated Matrix Games - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Hedging Algorithms and Repeated Matrix Games

Résumé

Playing repeated matrix games (RMG) while maximizing the cumulative returns is a basic method to evaluate multi-agent learning (MAL) algorithms. Previous work has shown that UCB, M3, S or Exp3 algorithms have good behaviors on average in RMG. Besides, hedging algorithms have been shown to be effective on prediction problems. An hedging algorithm is made up with a top-level algorithm and a set of basic algorithms. To make its decision, an hedging algorithm uses its top-level algorithm to choose a basic algorithm, and the chosen algorithm makes the decision. This paper experimentally shows that well-selected hedging algorithms are better on average than all previous MAL algorithms on the task of playing RMG against various players. S is a very good top-level algorithm, and UCB and M3 are very good basic algorithms. Furthermore, two-level hedging algorithms are more effective than one-level hedging algorithms, and three levels are not better than two levels.
Fichier principal
Vignette du fichier
bouzy11.pdf (134.66 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00975943 , version 1 (09-04-2014)

Identifiants

  • HAL Id : hal-00975943 , version 1

Citer

Bruno Bouzy, Marc Métivier, Damien Pellier. Hedging Algorithms and Repeated Matrix Games. Workshop on Machine Learning and Data Mining in and around Games (ECML-PKDD), Sep 2011, Athens, Greece. ⟨hal-00975943⟩

Collections

LIPADE UP-SCIENCES
153 Consultations
128 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More