Combining Tactical Search and Monte-Carlo in the Game of Go

Abstract- We present a way to integrate search andMonte-Carlo methods in the game of Go. Our program uses search to find the status of tactical goals, buildsgroups, selects interesting goals, and computes statistics on the realization of tactical goals during the randomgames. The mean score of the random games where a selected tactical goal has been reached and the mean scoreof the random games where it has failed are computed. They are used to evaluate the selected goals. Experimen-tal results attest that combining search and Monte-Carlo significantly improves the playing level. 1 Introduction Monte-Carlo Go has been invented in 1993 [1]; it is a sim-ple way to program a decent computer Go program usin