Fuzzy Markup Language for game of NoGo

Game of Go is one of the main challenges in the artificial intelligence. In particular, it is much harder than chess, in spite of the fact that it is fully observable and has very intuitive rules. Computer Go has been developing for the past several years, and NoGo game is similar to Go, in the sense that each player puts a stone on the board alternatively, and stones do not move. However, the goal is different, for example, the first player who either suicides or kills a group has lost the game. In this paper, the Fuzzy Markup Language (FML) is applied to infer the position of the good move for the new game of NoGo. The fuzzy ontology, machine learning and evolutionary approach are also proposed to support the knowledge base and rule base of FML. In addition, the Monte-Carlo Tree Search (MCTS) is also applied to predict the winning rate for each move. The experimental results show that the proposed approach is workable for the game of NoGo.