Monte-Carlo Tree Search Solver

9 years 8 days ago
Monte-Carlo Tree Search Solver
Recently, Monte-Carlo Tree Search (MCTS) has advanced the field of computer Go substantially. In this article we investigate the application of MCTS for the game Lines of Action (LOA). A new MCTS variant, called MCTS-Solver, has been designed to play narrow tactical lines better in sudden-death games such as LOA. The variant differs from the traditional MCTS in respect to backpropagation and selection strategy. It is able to prove the game-theoretical value of a position given sufficient time. Experiments show that a Monte-Carlo LOA program using MCTS-Solver defeats a program using MCTS by a winning score of 65%. Moreover, MCTS-Solver performs much better than a program using MCTS against several different versions of the world-class program MIA. Thus, MCTS-Solver constitutes genuine progress in using simulation-based search approaches in sudden-death games, significantly improving upon MCTS-based programs.
Mark H. M. Winands, Yngvi Björnsson, Jahn-Tak
Added 12 Oct 2010
Updated 12 Oct 2010
Type Conference
Year 2008
Where CG
Authors Mark H. M. Winands, Yngvi Björnsson, Jahn-Takeshi Saito
Comments (0)