Multiple Tree for Partially Observable Monte-Carlo Tree Search - Archive ouverte HAL
Pré-Publication, Document De Travail Année : 2011

Multiple Tree for Partially Observable Monte-Carlo Tree Search

Résumé

We propose an algorithm for computing approximate Nash equilibria of partially observable games using Monte-Carlo tree search based on recent bandit methods. We obtain experimental results for the game of phantom tic-tac-toe, showing that strong strategies can be efficiently computed by our algorithm.
Fichier principal
Vignette du fichier
auger.pdf (152.65 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00563480 , version 1 (05-02-2011)
hal-00563480 , version 2 (08-02-2011)

Identifiants

Citer

David Auger. Multiple Tree for Partially Observable Monte-Carlo Tree Search. 2011. ⟨hal-00563480v2⟩
310 Consultations
937 Téléchargements

Altmetric

Partager

More