A Parallel Monte-Carlo Tree Search Algorithm - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

A Parallel Monte-Carlo Tree Search Algorithm

Résumé

Monte-Carlo tree search is a powerful paradigm for the game of Go. We present a parallel Master-Slave algorithm for Monte-Carlo tree search. We experimented the algorithm on a network of computers using various configurations: from 12,500 to 100,000 playouts, from 1 to 64 slaves, and from 1 to 16 computers. On our architecture we obtain a speedup of 14 for 16 slaves. With a single slave and five seconds per move our algorithm scores 40.5% against GNUGO, with sixteen slaves and five seconds per move it scores 70.5%. We also give the potential speedups of our algorithm for various playout times.
Fichier principal
Vignette du fichier
parallelMCTS.pdf (59.37 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02310189 , version 1 (09-10-2019)

Identifiants

Citer

Tristan Cazenave, Nicolas Jouandeau. A Parallel Monte-Carlo Tree Search Algorithm. 6th international Conference on Computers and Games, Sep 2008, Beijing, China. ⟨10.1007/978-3-540-87608-3_7⟩. ⟨hal-02310189⟩
57 Consultations
189 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More