Learning of Go Board State Evaluation Function by Artificial Neural Network

  • Hiroki Tomizawa
  • Shin-ichi Maeda
  • Shin Ishii
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5863)


We construct an artificial neural network called T361G to evaluate Go board state (expected winning probability of Black’s/White’s win conditioned on the current board state in Black’s/White’s turn). Different from the existing Mote-Carlo Go [3][4], which evaluates the next move (the next board state) by performing random simulations in every turn, we use a large number of experts’ game records of Go as training data in order for T361G to learn the evaluation function of Go board states. We reduce the number of parameters to be learned by taking Go-specific properties into account. It is shown that T361G predicts the winning probability fairly well with avoiding overtraining, even from insufficient amount of data.


Go neural network supervised learning 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Machine Learning 47, 235–256 (2002)MATHCrossRefGoogle Scholar
  2. 2.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)MATHGoogle Scholar
  3. 3.
    Bruegmann, B.: Monte Carlo Go,
  4. 4.
    Kocsis, L., Szepesvari, C.: Bandit based Monte-Carlo planning. In: 15th European Conference on Machine Learning, pp. 282–293 (2006)Google Scholar
  5. 5.
    Newborn, M.: Computer Chess Comes of Age. Springer, Heidelberg (1996)Google Scholar
  6. 6.
    Robbins, H., Monro, S.: A stochastic approximation method. Annals of Mathematical Statistics 22, 400–407 (1951); Springer-Verlag (1996)MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Hiroki Tomizawa
    • 1
  • Shin-ichi Maeda
    • 1
  • Shin Ishii
    • 1
  1. 1.Graduate School of InformaticsKyoto UniversityJapan

Personalised recommendations