A new self-acquired knowledge process for Monte Carlo Tree Search - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

A new self-acquired knowledge process for Monte Carlo Tree Search

André Fabbri
Frédéric Armetta
Eric Duchene
Salima Hassas

Résumé

Computer Go is one of the most challenging field in Artificial Intelligence Game. In this area the use of Monte Carlo Tree Search has emerged as a very attractive research direction, where recent advances have been achieved and permitted to significantly increase programs efficiency. These enhancements result from combining tree search used to identify best next moves, and a Monte Carlo process to estimate and gradually refine a position accuracy (estimation function). The more the estimation process is accurate, the better the Go program performs. In this paper, we propose a new approach to extract knowledge from the Go tree search which allows to increase the evaluation function accuracy (BHRF: Background History Reply Forest). The experiments results provided by this new approach are very promising.
Fichier principal
Vignette du fichier
fabbri_armetta_duchene_hassas_wecai2012.pdf (298.4 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01240220 , version 1 (08-12-2015)

Identifiants

  • HAL Id : hal-01240220 , version 1

Citer

André Fabbri, Frédéric Armetta, Eric Duchene, Salima Hassas. A new self-acquired knowledge process for Monte Carlo Tree Search. European Conference on Artificial Intelligence, Aug 2012, Montpellier, France. ⟨hal-01240220⟩
211 Consultations
85 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More