The research of Chinese chess based on database with self learning

Most of the existing Chinese chess programs improved only through optimizing the data structure and improving the search strategy. Game-tree search is one of the key technologies in Chinese Chess computer programs and the required memory storage is huge. Therefore, a new method is introduced. In each match, the movement of the opponent and the position value are stored in database. Then it can avoid making the same mistake next time. The more it stores, the better it performs. Meanwhile, a new game tree search strategy is presented in this paper. The experiment demonstrate the effectiveness and the feasibility of the proposed algorithm.