Modification of UCT with Patterns in Monte-Carlo Go

Sylvain Gelly 1 Yizao Wang 1, 2 Rémi Munos 2, 3 Olivier Teytaud 1
1 TANC - Algorithmic number theory for cryptology
LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau], INRIA Saclay - Ile de France, Polytechnique - X, CNRS - Centre National de la Recherche Scientifique : UMR7161
3 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal, INRIA Lille - Nord Europe
Abstract : Algorithm UCB1 for multi-armed bandit problem has already been extended to Algorithm UCT (Upper bound Confidence for Tree) which works for minimax tree search. We have developed a Monte-Carlo Go program, MoGo, which is the first computer Go program using UCT. We explain our modification of UCT for Go application and also the intelligent random simulation with patterns which has improved significantly the performance of MoGo. UCT combined with pruning techniques for large Go board is discussed, as well as parallelization of UCT. MoGo is now a top level Go program on $9\times9$ and $13\times13$ Go boards.
Document type :
[Research Report] RR-6062, INRIA. 2006
Contributor : Sylvain Gelly <>
Submitted on : Wednesday, December 20, 2006 - 6:52:43 PM
Last modification on : Saturday, January 30, 2016 - 1:04:51 AM


Files produced by the author(s)


  • HAL Id : inria-00117266, version 3


Sylvain Gelly, Yizao Wang, Rémi Munos, Olivier Teytaud. Modification of UCT with Patterns in Monte-Carlo Go. [Research Report] RR-6062, INRIA. 2006. <inria-00117266v3>




Record views


Document downloads