21773 articles – 15587 Notices  [english version]

hal-00695370, version 2

The Grand Challenge of Computer Go: Monte Carlo Tree Search and Extensions

Sylvain Gelly () 12, Marc Schoenauer () 13, Michèle Sebag () 12, Olivier Teytaud (, http://www.lri.fr/~teytaud) 1245, Levente Kocsis a6, David Silver b7, Csaba Szepesvari () 8

Communication of the ACM 55, 3 (2012) 106-113

Résumé : The ancient oriental game of Go has long been considered a grand challenge for artificial intelligence. For decades, com- puter Go has defied the classical methods in game tree search that worked so successfully for chess and checkers. How- ever, recent play in computer Go has been transformed by a new paradigm for tree search based on Monte-Carlo meth- ods. Programs based on Monte-Carlo tree search now play at human-master levels and are beginning to challenge top professional players. In this paper we describe the leading algorithms for Monte-Carlo tree search and explain how they have advanced the state of the art in computer Go.

  • a –  Mta Sztaki
  • b –  University of Alberta
  • 1 :  TAO (INRIA Saclay - Ile de France)
  • INRIA – CNRS : UMR8623 – Université Paris XI - Paris Sud
  • 2 :  Laboratoire de Recherche en Informatique (LRI)
  • CNRS : UMR8623 – Université Paris XI - Paris Sud
  • 3 :  Microsoft Research - Inria Joint Centre (MSR - INRIA)
  • INRIA – Microsoft – Microsoft Research Laboratory Cambridge
  • 4 :  OASE, National University of Tainan, Taiwan (OASE)
  • National University of Tainan
  • 5 :  Department of Electrical Engineering and Computer Science (Institut Montefiore)
  • Université de Liège
  • 6 :  LPDS
  • Mta Sztaki
  • 7 :  University of Alberta, Canada
  • University of Alberta
  • 8 :  Department of Computing Science
  • Department of Computing Science, University of Alberta
  • Collaboration : Grid'5000
 
  • hal-00695370, version 2
  • oai:hal.inria.fr:hal-00695370
  • Contributeur : 
  • Soumis le : Dimanche 19 Août 2012, 10:35:22
  • Dernière modification le : Samedi 15 Septembre 2012, 13:53:38