Intelligent Agents for the Game of Go

Jean-Baptiste Hoock; Chang-Shing Lee; Arpad Rimmel; Fabien Teytaud; Olivier Teytaud; Mei-Hui Wang

inria-00544758, version 1

Intelligent Agents for the Game of Go

Jean-Baptiste Hoock () ^1, 2, Chang-Shing Lee ³, Arpad Rimmel () ², Fabien Teytaud () ^1, 2, Olivier Teytaud () ^1, 2, Mei-Hui Wang^a^, 4

IEEE Computational Intelligence Magazine (2010)

Résumé : Monte-Carlo Tree Search (MCTS) is a very efficient recent technology for games and planning, par- ticularly in the high-dimensional case, when the number of time steps is moderate and when there is no natural evaluation function. Surprisingly, MCTS makes very little use of learning. In this paper, we present four techniques (ontologies, Bernstein races, Contextual Monte-Carlo and poolRave) for learning agents in Monte-Carlo Tree Search, and experiment them in difficult games and in particular, the game of Go.

a – Dept. of Computer Science and Information Engineering
1 : Laboratoire de Recherche en Informatique (LRI)
CNRS : UMR8623 – Université Paris XI - Paris Sud
2 : TAO (INRIA Saclay - Ile de France)
INRIA – CNRS : UMR8623 – Université Paris XI - Paris Sud
3 : Department of Computer Science and Information Engineering (CSIE)
National University of Tainan
4 : National University of Tainan (NUTN)
National University of Tainan

inria-00544758, version 1
http://hal.inria.fr/inria-00544758
oai:hal.inria.fr:inria-00544758
Contributeur : Jean-Baptiste Hoock <>
Soumis le : Mercredi 8 Décembre 2010, 21:24:31
Dernière modification le : Vendredi 10 Décembre 2010, 11:08:58

Voir la fiche détaillée

Documents associés

PDF :

Exporter

Bibtex EndNote TEI RefWorks

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="article"><head>Articles dans des revues sans comité de lecture</head>
<biblStruct type="article" xml:id="inria-00544758"><analytic>
<author><persName><forename>Jean-Baptiste</forename><surname>Hoock</surname></persName>
<affiliation>
<orgName type="laboratory">LRI</orgName>
<orgName type="team">Laboratoire de Recherche en Informatique</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR8623</orgName>
<orgName type="institution">Université Paris XI - Paris Sud</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">INRIA Saclay - Ile de France</orgName>
<orgName type="team">TAO</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR8623</orgName>
<orgName type="institution">Université Paris XI - Paris Sud</orgName>
</affiliation>
</author>
<author><persName><forename>Chang-Shing</forename><surname>Lee</surname></persName>
<affiliation>
<orgName type="laboratory">CSIE</orgName>
<orgName type="team">Department of Computer Science and Information Engineering</orgName>
<country>TW</country>
<orgName type="institution">National University of Tainan</orgName>
</affiliation>
</author>
<author><persName><forename>Arpad</forename><surname>Rimmel</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA Saclay - Ile de France</orgName>
<orgName type="team">TAO</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR8623</orgName>
<orgName type="institution">Université Paris XI - Paris Sud</orgName>
</affiliation>
</author>
<author><persName><forename>Fabien</forename><surname>Teytaud</surname></persName>
<affiliation>
<orgName type="laboratory">LRI</orgName>
<orgName type="team">Laboratoire de Recherche en Informatique</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR8623</orgName>
<orgName type="institution">Université Paris XI - Paris Sud</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">INRIA Saclay - Ile de France</orgName>
<orgName type="team">TAO</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR8623</orgName>
<orgName type="institution">Université Paris XI - Paris Sud</orgName>
</affiliation>
</author>
<author><persName><forename>Olivier</forename><surname>Teytaud</surname></persName>
<affiliation>
<orgName type="laboratory">LRI</orgName>
<orgName type="team">Laboratoire de Recherche en Informatique</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR8623</orgName>
<orgName type="institution">Université Paris XI - Paris Sud</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">INRIA Saclay - Ile de France</orgName>
<orgName type="team">TAO</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR8623</orgName>
<orgName type="institution">Université Paris XI - Paris Sud</orgName>
</affiliation>
</author>
<author><persName><forename>Mei-Hui</forename><surname>Wang</surname></persName>
<affiliation>
<orgName type="laboratory">NUTN</orgName>
<orgName type="team">National University of Tainan</orgName>
<country>TW</country>
<orgName type="institution">National University of Tainan</orgName>
</affiliation>
</author>
<title type="main" level="a">Intelligent Agents for the Game of Go</title></analytic><monogr><title level="j" type="main">IEEE Computational Intelligence Magazine</title><imprint><publisher>IEEE</publisher><biblScope type="publicationDate">2010-11-00</biblScope></imprint></monogr><idno type="HALid">http://hal.inria.fr/inria-00544758</idno><idno type="HALFile">http://hal.inria.fr/inria-00544758/PDF/cimok.pdf</idno></biblStruct>
</listBibl>
</listBibl>