Journal of Korea Game Society (한국게임학회 논문지)

Korea Game Society (한국게임학회)
권호 표지

Applying Neuro-fuzzy Reasoning to Go Opening Games

뉴로-퍼지 추론을 적용한 포석 바둑

  • Lee, Byung-Doo (Dept. of Information and Communication Engineering, Sungkyul University)
  • 이병두 (성결대 정보통신공학부)
  • Published : 2009.12.20
Download PDF
⟨ Previous Next ⟩

Abstract

This paper describes the result of applying neuro-fuzzy reasoning, which conducts Go term knowledge based on pattern knowledge, to the opening game of Go. We discuss the implementation of neuro-fuzzy reasoning for deciding the best next move to proceed through the opening game. We also let neuro-fuzzy reasoning play against TD($\lambda$) learning to test the performance. The experimental result reveals that even the simple neuro-fuzzy reasoning model can compete against TD($\lambda$) learning and it shows great potential to be applied to the real game of Go.

본 논문은 포석 바둑을 위해, 패턴 지식을 근간으로 바둑 용어 지식을 수행할 수 있는 뉴로-퍼지 추론에 대한 실험 결과를 설명하였다. 즉, 포석 시 최선의 착점을 결정하기 위한 뉴로-퍼지 추론 시스템의 구현을 논하였다. 또한 추론 시스템의 성능을 시험하기 위하여 시차 학습(TD($\lambda$) learning) 시스템과의 대결을 벌였다. 대결 결과에 의하면 단순한 뉴로-퍼지 추론 시스템조차 시차 학습 모델과 충분히 대결할 만하며, 뉴로-퍼지 추론 시스템이 실제 바둑 게임에도 적용될 수 있는 잠재력을 보였다.

Keywords

References

  1. J. Burmeister and J. Wiles, "The Challenge of Go as a Domain: A Comparison Between Go and Chess", Proc. of the Third Australian and New Zealand Conference on Intelligent Information Systems (1995) 181-186.
  2. X. Cai and D. Wunsch, "A Parallel Computer Go Player, Using HDP Method", Proc. of IEEE International Joint Conference on Neural Networks 4 (2001) 2373-2375.
  3. Y. Moon, Discovery of Go: Understanding of Modern Go, Booki Press, Korea, 1998.
  4. A. Zobrist, Feature Extraction and Representation for Pattern Recognition and the Game of Go, PhD Thesis, University of Wisconsin, USA, 1970.
  5. K. Chen, "Heuristic Search in Go Game", Proc. of Joint Conference on Information Sciences `98 2 (1998) 274-278.
  6. J. R. Jang, "Neuro-Fuzzy Modeling and Control", Proc. of the IEEE 83 (1995) 378-406. https://doi.org/10.1109/5.364486
  7. M. Negnevitsky, Artificial Intelligence: A Guide to Intelligent Systems, Addison Wesley, England, 2005.
  8. J. Binfet and B. M. Wilamowski, "Microprocessor Implementation of Fuzzy Systems and Neural Networks", IEEE (2001) 234-239.
  9. D. Nauck and R. Kruse, "A Neuro-Fuzzy Approach to Obtain Interpretable Fuzzy Systems for Function Approximation", Proc. IEEE International Conference on Fuzzy Systems (USA, 1998) 1106-1111.
  10. R. S. Sutton, "Learning to Predict by the Methods of Temporal Differences", Machine Learning 3 (1988) 9-44.
  11. J. Baxter and A. Tridgell and L. Weaver, "Learning to Play Chess Using Temporal Differences", Machine Learning 40 (2000) 243-263. https://doi.org/10.1023/A:1007634325138
  12. J. Burmeister and J. Wiles, "AI Techniques Used in Computer Go", Proc. of the Fourth Conference of the Australasian Cognitive Science Society (Australia, 1997).
  13. J. Burmeister, Studies in Human and Computer Go: Assessing the Game of Go as a Research Domain for Cognitive Science, PhD thesis, University of Queensland, Australia, 1995.
  14. Y. Jin and J. Jiang, "Techniques in Neural Network Based Fuzzy System Identification and Their Application in Control of Complex Systems", Fuzzy Theory Systems: Techniques and Applications 1 (1999) 112-128.
  15. J. Binfel and B. M. Wilamowski, "Microprocessor Implementation of Fuzzy Systems and Neural Networks", IEEE (2001) 234-239.
  16. D. Nauck and R. Kruse, "A Neural-Fuzzy Approach to Obtain Interpretable Fuzzy Systems for Function Approximation", Proc. IEEE International Conference on Fuzzy Systems (USA, 1998) 1106-1111.
  17. M. Reiss, Go++, Available from http://www.goplusplus.com/go4ppfaq.htm [accessed on 27 September 2009].
  18. B. Lee, Multi-strategic Learning, Reasoning and Searching in the Game of Go, PhD Thesis, University of Auckland, New Zealand, 2005.