Exploration exploitation in Go: UCT for Monte-Carlo Go

Sylvain Gelly (1) , Yizao Wang (1, 2)

1 TANC - Algorithmic number theory for cryptology
2 CMAP - Centre de Mathématiques Appliquées - Ecole Polytechnique

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.

Domains: Machine Learning [cs.LG]; Artificial Intelligence [cs.AI]; Computer Science and Game Theory [cs.GT]

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⟩