Since the beginning of AI, mind games have been studied as relevant application fields. Nowadays, some programs are better than human players in most classical games. Their results highlight the efficiency of AI methods that are now quite standard. Such methods are very useful to Go programs, but they do not enable a strong Go program to be built. The problems related to Computer Go require new AI problem solving methods. Given the great number of problems and the diversity of possible solutions, Computer Go is an attractive research domain for AI. Prospective methods of programming the game of Go will probably be of interest in other domains as well. The goal of this paper is to present Computer Go by showing the links between existing studies on Computer Go and different AI related domains: evaluation function, heuristic search, machine learning, automatic knowledge generation, mathematical morphology and cognitive science. In addition, this paper describes both the practical aspects of Go programming, such as program optimization, and various theoretical aspects such as combinatorial game theory, mathematical morphology, and MonteCarlo methods. B. Bouzy T. Cazenave page 2 08/06/01 1.

This paper provides a survey of previously published work on machine learning in game playing. The material is organized around a variety of problems that typically arise in game playing and that can be solved with machine learning methods. This approach, we believe, allows both, researchers in game playing to find appropriate learning techniques for helping to solve their problems as well as machine learning researchers to identify rewarding topics for further research in game-playing domains. The paper covers learning techniques that range from neural networks to decision tree learning in games that range from poker to chess.

Approaches to computer game playing based on alpha-beta 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.

The main objective of this chapter is to present a comparative study of two techniques that automatically generate useful knowledge in games. Retrograde analysis of patterns generates pattern databases, starting with a simple definition of a sub-goal in a game and progressively finding all the pattern of given sizes that fulfill this sub-goal. Metaprogramming is based on similar concepts, but instead of generating fixed size patterns, it generates programs. Programs enable to represent knowledge in a more flexible way. However, they may take more time to use than pattern knowledge. We will describe the application of these two methods to the game of Hex, and compare their behaviors on this game. 1

Abstract—In order to stimulate the development and