Recently, Monte-Carlo Tree Search (MCTS) has advancedthe field of computer Go substantially. In this article we investigate theapplication of MCTS for the game Lines of Action (LOA). A new MCTSvariant, 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 selectionstrategy. It is able to prove the game-theoretical value of a position givensufficient 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 programusing MCTS against several different versions of the world-class alpha-betta program MIA. Thus, MCTS-Solver constitutes genuine progress in using simulation-based search approaches in sudden-death games, significantly improving upon MCTS-based programs

Keywords for this software

Anything in here will be replaced on browsers that support the canvas element