• 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

Monte-Carlo Tree Reductions for Stochastic Games

Thumbnail
Date
2014
Link to item file
https://hal.archives-ouvertes.fr/hal-02317159
Dewey
Intelligence artificielle
Sujet
Perfect Information; Stochastic Game; Main Loop; Classical Move; Select Function
DOI
http://dx.doi.org/10.1007/978-3-319-13987-6_22
Conference name
19th International Conference, TAAI 2014
Conference date
11-2014
Conference city
Taipei
Conference country
"Taiwan
Book title
Technologies and Applications of Artificial Intelligence
Author
Cheng, Shin-Ming; Day, Min-Yuh
Publisher
Springer
Pages number
396
ISBN
978-3-319-13986-9
Book URL
10.1007/978-3-319-13987-6
URI
https://basepub.dauphine.fr/handle/123456789/20899
Collections
  • LAMSADE : Publications
Metadata
Show full item record
Author
Jouandeau, Nicolas
Cazenave, Tristan
989 Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Type
Communication / Conférence
Item number of pages
228-238
Abstract (EN)
Monte-Carlo Tree Search (MCTS) is a powerful paradigm for perfect information games. When considering stochastic games, the tree model that represents the game has to take chance and a huge branching factor into account. As effectiveness of MCTS may decrease in such a setting, tree reductions may be useful. Chance-nodes are a way to deal with random events. Move-groups are another way to deal efficiently with a large branching factor by regrouping nodes. Group-nodes are regrouping only reveal moves and enable a choice between reveal moves and classical moves. We present various policies to use such reductions for the stochastic game Chinese Dark Chess. Move-groups, chance-nodes and group-nodes are compared.

  • 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.