• français
    • English
  • English 
    • français
    • English
  • Login
JavaScript is disabled for your browser. Some features of this site may not work without it.
BIRD Home

Browse

This CollectionBy Issue DateAuthorsTitlesSubjectsJournals BIRDResearch centres & CollectionsBy Issue DateAuthorsTitlesSubjectsJournals

My Account

Login

Statistics

View Usage Statistics

Generalized Rapid Action Value Estimation

Thumbnail
View/Open
generalized.pdf (163.1Kb)
Date
2015
Dewey
Méthodes informatiques spéciales
Sujet
Monte Carlo Tree Search
Conference name
24th International Conference on Artificial Intelligence
Conference date
07-2015
Conference city
Buenos Aires
Conference country
Argentina
Book title
IJCAI'15 Proceedings of the 24th International Conference on Artificial Intelligence
Author
Yang, Qiang; Wooldridge, Michael
Publisher
AAAI Press
Publisher city
Palo Alto (USA)
Year
07-2015
Pages number
1199
ISBN
978-1-57735-738-4
URI
https://basepub.dauphine.fr/handle/123456789/16166
Collections
  • LAMSADE : Publications
Metadata
Show full item record
Author
Cazenave, Tristan
989 Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Type
Communication / Conférence
Item number of pages
754-760
Abstract (EN)
Monte Carlo Tree Search (MCTS) is the state of the art algorithm for many games including the game of Go and General Game Playing (GGP). The standard algorithm for MCTS is Upper Confidence bounds applied to Trees (UCT). For games such as Go a big improvement over UCT is the Rapid Action Value Estimation (RAVE) heuristic. We propose to generalize the RAVE heuristic so as to have more accurate estimates near the leaves. We test the resulting algorithm named GRAVE for Atarigo, Knighthrough, Domineering and Go.

  • Accueil Bibliothèque
  • Site de l'Université Paris-Dauphine
  • Contact
SCD Paris Dauphine - Place du Maréchal de Lattre de Tassigny 75775 Paris Cedex 16

 Content on this site is licensed under a Creative Commons 2.0 France (CC BY-NC-ND 2.0) license.