Thumbnail

Score Bounded Monte-Carlo Tree Search

Saffidine, Abdallah; Cazenave, Tristan (2011), Score Bounded Monte-Carlo Tree Search, in Plaat, Aske; Iida, Hiroyuki; van den Herik, H. Jaap, Computers and Games 7th International Conference, CG 2010, Kanazawa, Japan, September 24-26, 2010, Revised Selected Papers, Springer : Berlin, p. 93-104

View/Open
Type
Communication / Conférence
Date
2011
Conference title
International Conference on Computers and Games 2010
Conference date
2010-09
Conference city
Kanazawa
Conference country
Japon
Book title
Computers and Games 7th International Conference, CG 2010, Kanazawa, Japan, September 24-26, 2010, Revised Selected Papers
Book author
Plaat, Aske; Iida, Hiroyuki; van den Herik, H. Jaap
Publisher
Springer
Series title
Lecture Notes in Computer Science
Series number
6515
Published in
Berlin
ISBN
978-3-642-17927-3
Number of pages
277
Pages
93-104
Publication identifier
Metadata
Show full item record
Author(s)
Saffidine, Abdallah
Cazenave, Tristan
Abstract (EN)
Monte-Carlo Tree Search (MCTS) is a successful algorithm used in many state of the art game engines. We propose to improve a MCTS solver when a game has more than two outcomes. It is for example the case in games that can end in draw positions. In this case it improves significantly a MCTS solver to take into account bounds on the possible scores of a node in order to select the nodes to explore. We apply our algorithm to solving Seki in the game of Go and to Connect Four.
Subjects / Keywords
Monte-Carlo tree search; MCTS solver