Modification of UCT with Patterns in Monte-Carlo Go

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 :
Reports
[Research Report] RR-6062, 2006


https://hal.inria.fr/inria-00117266
Contributor : Sylvain Gelly <>
Submitted on : Wednesday, December 20, 2006 - 6:52:43 PM
Last modification on : Thursday, December 21, 2006 - 9:49:17 AM

File

RR-6062.pdf
fileSource_public_author

Identifiers

  • HAL Id : inria-00117266, version 3

Citation

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

Export

Share

Metrics

Consultation de
la notice

1548

Téléchargement du document

971