Skip to Main content Skip to Navigation
Conference papers

Exploration exploitation in Go: UCT for Monte-Carlo Go

Sylvain Gelly 1 Yizao Wang 1, 2
1 TANC - Algorithmic number theory for cryptology
Inria Saclay - Ile de France, LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]
Abstract : Algorithm UCB1 for multi-armed bandit problem has already been extended to Algorithm UCT which works for minimax tree search. We have developed a Monte-Carlo program, MoGo, which is the first computer Go program using UCT. We explain our modifications of UCT for Go application, among which efficient memory management, parametrization, ordering of non-visited nodes and parallelization. MoGo is now a top-level Computer-Go program on 9 x 9 Go board.
Complete list of metadata

Cited literature [10 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00115330
Contributor : Sylvain Gelly <>
Submitted on : Tuesday, November 21, 2006 - 10:36:52 AM
Last modification on : Thursday, March 5, 2020 - 6:20:17 PM
Long-term archiving on: : Thursday, September 20, 2012 - 2:51:57 PM

File

nips_exploration_exploitation....
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00115330, version 1

Collections

Citation

Sylvain Gelly, Yizao Wang. Exploration exploitation in Go: UCT for Monte-Carlo Go. NIPS: Neural Information Processing Systems Conference On-line trading of Exploration and Exploitation Workshop, Dec 2006, Canada. ⟨hal-00115330⟩

Share

Metrics

Record views

1691

Files downloads

2438