Computer Go: A Grand Challenge to AI

  • Xindi Cai
  • Donald C. WunschII
Part of the Studies in Computational Intelligence book series (SCI, volume 63)


The oriental game of Go is among the most tantalizing unconquered challenges in artificial intelligence after IBM's DEEP BLUE beat the world Chess champion in 1997. Its high branching factor prevents the conventional tree search approach, and long-range spatiotemporal interactions make position evaluation extremely difficult. Thus, Go attracts researchers from diverse fields who are attempting to understand how computers can represent human playing and win the game against humans. Numerous publications already exist on this topic with different motivations and a variety of application contexts. This chapter surveys methods and some related works used in computer Go published from 1970 until now, and offers a basic overview for future study. We also present our attempts and simulation results in building a non-knowledge game engine, using a novel hybrid evolutionary computation algorithm, for the Capture Go game.


Particle Swarm Optimization Evolutionary Algorithm Grand Challenge Game Tree Game Engine 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Allis LV, Van den Herik HJ, Herschberg IS (1991) “Which games will sur-vive?” In D. N. L. Levy andD. F. Beal, editors, Heuristic Programming in Artificial Intelligence 2-The Second Computer Olympiad, pp. 232-243, Ellis Horwood. Google Scholar
  2. [2]
    Berlekamp E, Conway J, Guy R (1982) Winning Ways, Academic Press, New York.zbMATHGoogle Scholar
  3. [3]
    Berlekamp E, Wolfe D (1994) Mathematical Go: Chilling Gets the Last Point. A. K. Peters., MA, USAzbMATHGoogle Scholar
  4. [4]
    Cai X, Wunsch II DC (2004) “Evolutionary computation in playing Cap-tureGo game,” Proc. of ICCNS’04, Boston.Google Scholar
  5. [5]
    Cai X, Zhang N, Venayagamoorthy GK, Wunsch II DC (2005) “Time series prediction with recurrent neural networks using hybrid PSO-EA algorithm,” Neurocomputing, (Accepted).Google Scholar
  6. [6]
    Chellapilla K, Fogel D (1999) “Evolution, neural networks, games, and intelligence,” Proceedings of the IEEE, vol. 87, no. 9, pp. 1471-1496, September. CrossRefGoogle Scholar
  7. [7]
    Chellapilla K, Fogel D (1999) “Evolving neural networks to play Checkers without relying on expert knowledge,” IEEE Trans. on Neural Networks, vol. 10, no. 6, pp. 1382-1391, November. CrossRefGoogle Scholar
  8. [8]
    Chellapilla K, Fogel D (2001) “Evolving an expert Checkers playing pro-grams without using human expertise,” IEEE Trans. on Evolutionary Computation, vol. 5, no. 4, pp. 422-428, August. CrossRefGoogle Scholar
  9. [9]
    Chen K, Chen Z (1999) “Static analysis of life and death in the game of Go,” Information Science, Vol. 121, pp. 113-134. CrossRefGoogle Scholar
  10. [10]
    Chen X, Zhang D, Zhang X, Li Z, Meng X, He S, Hu X (2003) “A func-tional MRI study of high-level cognition II. The game of GO,” Cognitive Brain Research, 16(1): 32-37. CrossRefGoogle Scholar
  11. [11]
    Chen Z (1995) “Programming technics in Handtalk,”
  12. [12]
    Convey J (1976) On Numbers and Games, Academic Press, London/NewYork.Google Scholar
  13. [13]
    Enderton HD (1991) “The Golem Go program,” Tech. Rep. CMU-CS-92-101, Carnegie Mellon University.Google Scholar
  14. [14]
    Enzenberger M (1996) “The integration of a priori knowledge into a Go playing neural network”.Available:
  15. [15]
    Fogel D (2002) Blondie24: Playing at the Edge of AI. SF, CA: Morgan Kaufmann.Google Scholar
  16. [16]
    Fogel D, Hays TJ, Hahn SL and Quon J (2004) “A self-learning evolution-ary Chess program,” Proc. of the IEEE, vol. 92, no. 12, pp. 1947-1954, December. CrossRefGoogle Scholar
  17. [17]
    Fotland D (1999) The 1999 FOST (Fusion of Science and Technology) cup world open computer championship, Tokyo. Available: http://www.
  18. [18]
    Fürnkranz J (2001) Machine learning in games: A survey. J. Fürnkranz & M. Kubat (eds.): Machines that Learn to Play Games, Nova Scientific Publishers, Chapter 2, pp. 11-59, Huntington, NY. Google Scholar
  19. [19]
  20. [20]
    Gomez F, Miikkulainen R (1997) “Incremental evolution of complex gen-eral behavior,” Adaptive Behavior, vol. 5, pp. 317-342. CrossRefGoogle Scholar
  21. [21]
    Hsu F (2002), Behind Deep Blue. Princeton, NJ: Princeton Univ. Press.zbMATHGoogle Scholar
  22. [22]
    Kennedy J,. Eberhart R (1995) “Particle Swarm Optimization,” IEEE International Conference on Neural Networks, vol. 4, pp. 1942-1948, Nov. 27-Dec. 1, Perth, Australia. Google Scholar
  23. [23]
    Kennedy J,. Eberhart R, Shi Y (2001) Swarm Intelligence. San Meteo, CA: Morgan Kaufmann.Google Scholar
  24. [24]
    Konidaris G, Shell D, Oren N (2002) “Evolving neural networks for the capture game,” Proc. of the SAICSIT postgraduate symposium, Port Elizabeth, South Africa. Available from:∼dshell/res/evneurocapt.pdf
  25. [25]
    Moriarty DE, Miikkulainen R (1994) “Evolving neural networks to focus minimax search,” Proc. of National Conference on Artificial Intelligence (AAAI-94), pp. 1371-1377. Google Scholar
  26. [26]
    Muller M (1999) “Decomposition search: A combinatorial games ap-proach to game tree search, with applications to solving Go endgames,” Proc. of IJCAI, vol. 1, pp. 578-583. Google Scholar
  27. [27]
    Muller M (2002) “Position evaluation in computer Go,” ICGA Journal, Vol. 25, No. 4, pp. 219-228.Google Scholar
  28. [28]
    Muller M (2003) “Conditional combinatorial games and their application to analyzing capturing race in Go,” Information Science, Vol. 154, pp. 189-202.CrossRefGoogle Scholar
  29. [29]
    Newman B (1988) “Wally, a simple minded Go-program,”
  30. [30]
    Pollack JB, Blair AD (1998) “Co-evolution in the successful learning of Backgammon strategy,” Machine Learning, Vol. 32, pp. 226-240. CrossRefGoogle Scholar
  31. [31]
    Pratola M, Wolfe T (2003) “Optimizing GoTools’ search heuristics using genetic algorithms,” ICGA Journal, vol. 26, no. 1, pp. 28-48. Google Scholar
  32. [32]
    Prokhorov D and Wunsch II DC (1997) “Adaptive critic designs,” IEEE Trans. on Neural Networks, vol. 8, no. 5, pp. 997-1007, September. CrossRefGoogle Scholar
  33. [33]
    Reiss M (1995) e-mail sent in January 1995 to the computer Go mailing list,∼richard/computer-go/.
  34. [34]
     Reitman W, Kerwin J, Nado R, Reitman J, Wilcox B (1974) “Goals and plans in a program for playing Go,” Proc. of the 29th National Conference of the ACM, pp. 123-127.Google Scholar
  35. [35]
    Reitman W, Wilcox B (1975) “Perception and representation of spatial relations in a program for playing Go,” Proc. of the 30th National Conference of the ACM, pp. 37-41.Google Scholar
  36. [36]
    Reitman W, Wilcox B (1978) “Pattern recognition and pattern-directed inference in a program for playing Go,” In D. Waterman and F. HayesRoth, editors, Pattern Directed Inference Systems, pp. 503-523, Academic Press, New York. Google Scholar
  37. [37]
    Ryder J (1971) “Heuristic analysis of large tree as generated in the game of Go,” PhD thesis, Department of Computer Science, Stanford Univer-sity.Google Scholar
  38. [38]
    Richards N, Moriarty D, McQuesten P, Miikkulainen R (1998) “Evolving neural networks to play Go,” Applied Intelligence, vol. 8, pp. 85-96.CrossRefGoogle Scholar
  39. [39]
    Schraudolph N, Dayan P, Sejnowski T (1994) “Temporal difference learn-ing of position evaluation in the game of Go,” Advances in Neural Information Processing, vol. 6, pp. 817-824. Google Scholar
  40. [40]
    Schraudolph N, Dayan P, Sejnowski T (2000) “Learning to evaluate Go position via temporal difference methods,” In L. Jain and N. Baba Eds, Soft Computing Techniques in Game Playing, Springer Verlag, Berlin.Google Scholar
  41. [41]
    Schwefel (1995) Evolution and Optimum Seeking. Wiley, NY.Google Scholar
  42. [42]
    Shannon CE (1950) “Automatic Chess player,” Scientific American 182, No. 48.Google Scholar
  43. [43]
    Smith A (1956) The Game of Go, Charles Tuttle Co., Tokyo, Japan.Google Scholar
  44. [44]
    Sutton R (1988) “Learning to predict by the method of temporal differ-ences,” Machine Learning, No. 3, pp. 9-44.Google Scholar
  45. [45]
    Tesauro G (1992)“Practical issue in temporal difference learn-ing,”Machine Learning, No. 8, pp. 257-278.zbMATHGoogle Scholar
  46. [46]
    Wilcox B (1985) “Reflections on building two Go programs,” ACM SIGART Newsletter, pp. 29-43.Google Scholar
  47. [47]
    Zaman R, Prokhorov DV, Wunsch II DC (1997) “Adaptive critic design in learning to play the game of Go,” Proc. of the International Joint Conference on Neural Networks, vol. 1, pp. 1-4, Houston.Google Scholar
  48. [48]
    Zaman R, Wunsch II DC (1999) “TD methods applied to mixture of ex-perts for learning 9x9 Go evaluation function,” Proc. of the International Joint Conference on Neural Networks, vol. 6, pp. 3734-3739Google Scholar
  49. [49]
     Zobrist A (1970) “Feature extractions and representation for pattern recognition and the game of Go,” PhD thesis, Graduate School of the University of Wisconsin.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Xindi Cai
    • 1
  • Donald C. WunschII
    • 2
  1. 1.University of MissouriRolla
  2. 2.University of MissouriRolla

Personalised recommendations