28943 articles – 22382 Notices  [english version]

inria-00544758, version 2

Intelligent Agents for the Game of Go

Jean-Baptiste Hoock () 12, Chang-Shing Lee 3, Arpad Rimmel () 2, Fabien Teytaud () 12, Olivier Teytaud () 12, Mei-Hui Wang a4

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
  • Collaboration : Grid'5000
 
  • inria-00544758, version 2
  • oai:hal.inria.fr:inria-00544758
  • Contributeur : 
  • Soumis le : Jeudi 14 Avril 2011, 14:41:08
  • Dernière modification le : Lundi 23 Avril 2012, 16:43:05