Applying Adversarial Planning Techniques to Go

Approaches to computer game playing based on α–β search of the tree of possible move sequences combined with a position evaluation function have been successful for many games, notably Chess. Such approaches are less successful for games with large search spaces and complex positions, such as Go, and we are led to seek alternatives. One such alternative is to model the goals of the players, and their strategies for achieving these goals. This approach means searching the space of possible goal expansions, typically much smaller than the space of move sequences. Previous attempts to apply these techniques to Go have been unable to provide results for anything other than a high strategic level or very open game positions. In this paper we describe how adversarial hierarchical task network planning can provide a framework for goal-directed game playing in Go which is also applicable both strategic and tactical problems.