Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search

Rémi Coulom
  • Fonction : Auteur
  • PersonId : 836867

Résumé

Monte-Carlo evaluation consists in estimating a position by averaging the outcome of several random continuations, and can serve as an evaluation function at the leaves of a min-max tree. This paper presents a new framework to combine tree search with Monte-Carlo evaluation, that does not separate between a min-max phase and a Monte-Carlo phase. Instead of backing-up the min-max value close to the root, and the average value at some depth, a more general backup operator is defined that progressively changes from averaging to min-max as the number of simulations grows. This approach provides a fine-grained control of the tree growth, at the level of individual simulations, and allows efficient selectivity methods. This algorithm was implemented in a Go-playing program, Crazy Stone, that won the gold medal of the $9 \times 9$ Go tournament at the 11th Computer Olympiad.
Fichier principal
Vignette du fichier
CG2006.pdf (133.58 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

inria-00116992 , version 1 (29-11-2006)

Identifiants

  • HAL Id : inria-00116992 , version 1

Citer

Rémi Coulom. Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search. 5th International Conference on Computer and Games, May 2006, Turin, Italy. ⟨inria-00116992⟩
1490 Consultations
18937 Téléchargements

Partager

Gmail Facebook X LinkedIn More