No abstract

a b s t r a c tClassic methods such as A ⁄ and IDA ⁄ are a popular and successful choice for one-player games. However, without an accurate admissible evaluation function, they fail. In this article we investigate whether Monte-Carlo tree search (MCTS) is an interesting alternative for one-player games where A ⁄ and IDA ⁄ methods do not perform well. Therefore, we propose a new MCTS variant, called single-player MonteCarlo tree search (SP-MCTS). The selection and backpropagation strategy in SP-MCTS are different from standard MCTS. Moreover, SP-MCTS makes use of randomized restarts. We tested IDA ⁄ and SP-MCTS on the puzzle SameGame and used the cross-entropy method to tune the SP-MCTS parameters. It turned out that our SP-MCTS program is able to score a substantial number of points on the standardized test set.

Monte Carlo Tree Search (MCTS) is a widel y -used technique for game-tree search in sequential turn-based games.The extension to simultaneous move games, where all pla y ers choose moves simultaneousl y each turn, is non-trivial due to the complexit y of this class of games. In this paper, we describe simultaneous move MCTS and anal y ze its application in a set of nine disparate simultaneous move games. We use several possible variants, Decoupled VCT, Sequential VCT, Exp3, and Regret Matching. These variants include both deterministic and stochastic selection strategies and we characterize the game-pla y performance of each one. The results indicate that the relative performance of each variant depends strongl y on the game and the opponent, and that parameter tuning can also not be as straightforward as the purel y sequential case. Overall, Decoupled VCT performs best despite its theoretical shortcomings.

The aim of General Game Playing (GGP) is to create programs capable of playing a wide range of different games at an expert level, given only the rules of the game. The most successful GGP programs currently employ simulation-based Monte Carlo Tree Search (MCTS). The performance of MCTS depends heavily on the simulation strategy used. In this article, we investigate the application of a decay factor for two domain-independent simulation strategies: N-Gram Selection Technique (NST) and Move-Average Sampling Technique (MAST). Three decay factor methods, called Move Decay, Batch Decay and Simulation Decay are applied. Furthermore, a combination of Move Decay and Simulation Decay is also tested. The decay variants are implemented in the GGP program CADIAPLAYER. Four types of games are used: turn-taking, simultaneous-move, one-player and multi-player. Except for one-player games, experiments show that decaying can significantly improve the performance of both NST and MAST simulation strategies.