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.
|
2331
|
Optimization by Simulated Annealing
– Kirkpatrick, Gelatt, et al.
- 1983
|
|
931
|
Learning to predict by the methods of temporal differences
– Sutton
- 1988
|
|
778
|
Image Analysis and Mathematical Morphology
– Serra
- 1988
|
|
487
|
Some studies in machine learning using the game of checkers II: Recent progress
– Samuel
- 1967
|
|
453
|
Explanation-based generalization: A unified view
– Mitchell, Keller, et al.
- 1986
|
|
441
|
Theory of games and economic behavior
– Neumann, Morgenstern
- 1947
|
|
408
|
Protocol Analysis: Verbal Reports as Data
– Ericsson, Simon
- 1984
|
|
271
|
Quantitative Results Concerning the Utility of Explanation-based Learning
– Minton
- 1990
|
|
270
|
Temporal difference learning and TD-Gammon
– Tesauro
- 1995
|
|
198
|
An analysis of alpha-beta pruning
– Knuth, Moore
- 1975
|
|
193
|
Unfold/fold transformation of logic programs
– Tamaki, Sato
- 1984
|
|
178
|
Depth-first iterative deepening: an optimal admissible tree search
– Korf
- 1985
|
|
166
|
On Numbers and Games
– Conway
- 2001
|
|
155
|
TD-Gammon, a self-teaching backgammon program, achieves master-level play
– Tesauro
- 1994
|
|
154
|
Telling more than we can know: Verbal reports on mental processes
– Nisbett, Wilson
- 1977
|
|
141
|
Explanationbased learning: A problem-solving perspective
– Minton, Carbonell, et al.
- 1989
|
|
87
|
Finding optimal solutions to rubik’s cube using pattern databases
– Korf
- 1997
|
|
80
|
A world championship caliber checkers program
– Schaeffer, Culberson, et al.
- 1992
|
|
70
|
Pattern databases
– Culberson, Schaeffer
- 1998
|
|
69
|
A minimax algorithm better than alpha-beta
– Stockman
- 1979
|
|
63
|
Conspiracy numbers for min-max search
– McAllester
- 1988
|
|
63
|
A New Hashing Method with Application for Game Playing
– Zobrist
- 1970
|
|
58
|
A parallel network that learns to play backgammon
– Tesauro, Sejnowski
- 1989
|
|
56
|
The B* tree search algorithm: A best-first proof procedure
– Berliner
- 1979
|
|
52
|
Singular extensions: adding selectivity to brute force searching
– Anantharaman, Campbell, et al.
- 1988
|
|
47
|
A comparison of minimax tree search algorithms
– Campbell, Marsland
- 1983
|
|
46
|
One Jump Ahead: Challenging Human Supremacy in Checkers
– Schaeffer
- 1997
|
|
39
|
Retrograde analysis of certain endgames
– Thompson
- 1986
|
|
36
|
Searching for solutions
– Allis
- 1994
|
|
33
|
A generalised quiescence search algorithm
– Beal
- 1990
|
|
32
|
van den Herik. Proofnumber search
– Allis, Meulen, et al.
- 1994
|
|
31
|
Explanation Based Learning: an alternative view
– Dejong, Mooney
- 1986
|
|
31
|
The program GoTools and its computer-generated tsume Go database
– Wolf
- 1994
|
|
30
|
Système d’Apprentissage par AutoObservation. Application au Jeu de
– Cazenave
- 1996
|
|
30
|
Conspiracy numbers
– Schaeffer
- 1990
|
|
26
|
The Greenblatt Chess program
– Greenblatt, Eastlake, et al.
- 1967
|
|
25
|
The Integration of a Priori of Knowledge into a Go Playing Neural Network
– Enzenberger
- 1996
|
|
24
|
Computing a perfect strategy for n × n Chess requires time exponential in n
– Fraenkel, Lichtenstein
- 1981
|
|
23
|
GO is polynomial-space hard
– Lichtenstein, Sipser
- 1980
|
|
23
|
Skilled perception in Go: Deducing memory structures from interresponse times. Cognition Psychology
– Reitman
- 1976
|
|
22
|
Forward pruning and other heuristic search techniques in tsume Go
– Wolf
- 2000
|
|
21
|
Go-moku solved by new search techniques
– Allis, Herik, et al.
- 1995
|
|
21
|
Life in the game of Go
– Benson
|
|
20
|
Tutorial on specialization of logic programs
– Gallagher
- 1993
|
|
20
|
A Grandmaster Chess Machine
– Hsu, Anantharaman, et al.
- 1990
|
|
20
|
Feature extraction and representation for pattern recognition and the game of Go
– Zobrist
- 1970
|
|
19
|
Constraint-based Generalization: Learning game-playing plans from single examples
– Minton
- 1984
|
|
19
|
N by N checkers is EXPTIME complete
– Robson
- 1984
|
|
18
|
The move decision process of Go Intellect
– Chen
- 1990
|
|
17
|
About problems in generalizing a tsumego program to open positions
– Wolf
- 1996
|