Computer Go – Scholarly Papers & Bibliographies

• Sylvain Gelly & David Silver Combining Online and Offline Knowledge in UCT.

• Markus Enzenberger's Computer Go Bibliography.

• Citeulike Computer-go library.

• Commented Papers on Go Programming from the OpenGo site.

• By Martin Müller:
  • His list of his own go articles
  • His list of over 100 references

• Browne, Powley, Whitehouse, Lucas, Cowling, Rohlfshagen, Stephen, Perez, Samothrakis and Colton: A Survey of Monte Carlo Tree Search Methods.

• Petr Baudiš: Current Approaches in Computer Go.

• Stogin, Chen, Drake & Pellegrino: The Beta Distribution in the UCB Algorithm Applied to Monte-Carlo Go.

• Sylvain Gelly's Ph.D thesis Une contribution à l'Apprentissage par Renforcement; application au Computer-Go. In French and English.

• Minorization-Maximization and a Generalized Bradley-Terry Model to Learn Pattern Weights in the Game of Go", by Rémi Coulom, 2007.
  A pattern-learning technique. The author's program CrazyStone uses patterns learned in this way to weight moves for its UCT algorithm.

• Bandit based Monte-Carlo Planning, by Levente Kocsis and Csaba Szepesvári, 2006.
  Introduces a new algorithm, "UCT", that applies bandit ideas to guide Monte Carlo planning.
  This pdf document is often unavailable. Here is a badly formatted but readable html version.

• Best Play for Imperfect Players and Game Tree Search", by Eric B. Baum and Warren D. Smith, 1995.
  Standard alpha-beta searches assume that the evaluation function is correct. This paper takes a Bayesian approach to the values it generates.

• A New Computational Approach to the Game of Go", by J. Churchill, R. Cant and D. Al-Dabass, 2001.

• Approaching Go as an abstract graph problem goes back a long way, to K. J. Friedenbach's PhD thesis, "Abstraction Hierarchies: A Model of Perception and Cognition in the Game of Go", University of California, Santa Cruz, 1980.

• "Analyzing Capturing Races and Seki Situations in the Game of GO by Semeai Graphs", by Katsuhiko Nakamura, Tokyo Denki University, Saitama, Japan, given at ACC '99 9th Conference Advances in Computer Chess, to be published in "Advances in Computer Chess 9".

• "Applying Adversarial Planning Techniques to Go", Willmott, S., Richardson, J. D. C., Bundy, A., Levine, J. M., Journal of Theoretical Computer Science, 252 (1-2) (2001) pp. 45-82.

• B* Probability Based Search is an alternative to minimax searching with possible application to computer go; it is described in a paper by Hans J. Berliner and Chris McConnell, Artificial Intelligence 86(1): 97-156 (1996)).

• Thomas Thomsen. Lambda-search in game trees – with application to Go, Computers and Games 2000, LNCS (Springer).

• Not an academic paper, but a eye-catching poster that is an effective introduction to the concepts of Computer Go: Machine Learning Applied to the Game of Go", by Cook, H., Venghaus, A., & Drake, P. (2003). Twelfth Regional Conference on Undergraduate Research, Murdock College Research Program.

• Temporal difference learning for game players. The original work was by Gerald Tesauro to train a backgammon player.

  Others thought it might be a nice technique to apply to other games, such as checkers or GO. Chellapilla and Fogel trained checkers players using techniques similar to those used by Tesauro for his backgammon player.

  There has also been some work done on applying similar techniques to GO players, such as Nici Schraudolphs work on applying temporal difference learning neural networks to GO.

  Another reference is the work from J. Baxter et al. applied to the game of chess. Check out "TDLeaf(Lambda): Combining temporal difference learning with game-tree search", available here.

• "Using Hard And Soft Artificial Intelligence Algorithms To Simulate Human Go Playing Techniques", by R. Cant, J. Churchill and D. Al-Dabass, Int. J. of Simulation, Vol. 2, No.1, June 2001, pp 31-49.

• Computer Go "An international bulletin devoted to the generation and exchange of ideas about Computer Go", edited by David Erbach. Quarterly, from 1986-1991. A complete set of 16 back issues, in pdf format.

• On the ICGA web site:
  • Chen, K.-H. (2000). Some Practical Techniques for Global Search in Go. Vol. 23, No. 2, pp. 67-74.
  • Thomsen, T. (2000). Lambda-Search in Game Trees — with Application to Go. Vol. 23, No. 4, pp. 203-217.
  • Chen, K.-H. (2001). Computer Go: Knowledge, Search, and Move Decision. Vol. 24, No. 4, pp. 203-215.

• The MSRI website contains Bill Spight, Analysis of the 4/21/98 Jiang-Rui endgame, and Bill Fraser, Analysis Tools: "Brute-Force" and "Winsolve".

Other Computer Go resources
www.computer-go.info