Research on improvement of UCT based on static evaluation

NoGo was born in the National University Student Machine Game Competition. It is a new chess that has only emerged from recent years. At present, there are relatively few studies on it, and the existing methods are not perfect. There are three main methods currently used which are Monte Carlo method, UCT algorithm and static evaluation method. But it is usually a single algorithm application, which has shortcomings. In this article, the author uses the static evaluation method to optimize the program of the UCT algorithm based on the rules and characteristics of NoGo. The experimental results show that this method has higher accuracy and shorter search time than either method alone.