WTN-EinStein würfelt nicht! (abbreviated as EWN) chess game has been attracting much attention owing to its characteristics of randomness and incompleteness. In this study, a modified upper confidence bounds applied to trees (UCT) algorithm is proposed by optimizing selection strategy, simulation of tree nodes and establishing the game tree based on probabilistic rules and natural characteristics of the chess game. Experimental results verify that the program applying the modified UCT algorithm can greatly improve winning rate compared with others with plain UCT or Monte Carlo algorithms. The program won the first prize in 2019 Chinese University Student Computer Games Competition and 13th National Computer Games Tournament.
展开▼
