Thumbnail

A Parallel General Game Player

Méhat, Jean; Cazenave, Tristan (2011), A Parallel General Game Player, KI. Künstliche Intelligenz, 25, 1, p. 43-47. http://dx.doi.org/10.1007/s13218-010-0083-6

Voir/Ouvrir
Type
Article accepté pour publication ou publié
Date
2011
Nom de la revue
KI. Künstliche Intelligenz
Volume
25
Numéro
1
Éditeur
Springer
Pages
43-47
Identifiant publication
Métadonnées
Afficher la notice complète
Auteur(s)
Méhat, Jean
Cazenave, Tristan
Résumé (EN)
We have parallelized our general game player Ary on a cluster of computers.We propose multiple parallelization algorithms. For the sake of simplicity all our algorithms have processes that run independently and that join their results at the end of the thinking time in order to choose a move. Parallelization works very well for checkers, quite well for other two player sequential move games and not at all for a few other games.
Mots-clés
Parallelization; Monte-Carlo tree search; General Game Playing