hal-00695370, version 2
The Grand Challenge of Computer Go: Monte Carlo Tree Search and Extensions
1, 2
1, 3
1, 2
1, 2, 4, 5 a, 6 b, 7
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 :
- INRIA – CNRS : UMR8623 – Université Paris XI - Paris Sud
- 2 :
- CNRS : UMR8623 – Université Paris XI - Paris Sud
- 3 :
- INRIA – Microsoft – Microsoft Research Laboratory Cambridge
- 4 :
- National University of Tainan
- 5 :
- Université de Liège
- 6 :
- Mta Sztaki
- 7 :
- University of Alberta
- 8 :
- Department of Computing Science, University of Alberta
- Collaboration : Grid'5000
- Domaine : Mathématiques/Optimisation et contrôle
- Versions disponibles : v1 (08-05-2012) v2 (20-08-2012) v3 (20-02-2013)
- hal-00695370, version 2
- http://hal.inria.fr/hal-00695370
- 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


Documents associés
Exporter