Abstract
It has been said to be very useful for Go playing systems to have knowledge. We focus on pattern level knowledge and propose a new model of pattern acquisition based on our cognitive experiments. The model consists of two steps: pattern acquisition step, using only positive examples, and pattern refinement step, using both positive and negative examples. The latter step acquires precise conditions to apply and/or the way of conflict resolution. This model has advantages in computational time and precise control for conflict resolution. One algorithm is given for each step, and each algorithm can change independently, it is possible to compare algorithms with this model. Three algorithms are introduced for the first step and two for the second step. Patterns acquired by this model are applied to Tsume-Go problems (life and death problems) and the performance between six conditions are compared. In the best condition, the percentage of correct answers is about 31%. This result equals the achievement of one dan human players. It is also shown that the patterns enhance search techniques when the search space is very large.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
T. Cazenave. Automatic acquisition of tactical go rules. In Game Programming Workshop in Japan’ 96, pages 10–19, 1996.
D. Fotland. Knowledge representation in the Many Faces of Go. Available from ftp://igs.nuri.net/Go/computer/mfg.Z, 1993.
I. D. House. Igo Data enjoy Books’ 60 ~’ 95. Nihon Ki-in, 1996. in Japanese.
Y. Ishida. Godan Toppa-no Tsume-Go 100. Tsuchiya Shoten, 1989.
Y. Ishida. Sandan Chosen-no Tsume-Go 100. Tsuchiya Shoten, 1989.
Y. Ishida. Kihon Tsume-Go 100 Dai. Nihon Bunge-sha, 1994.
T. Kojima, K. Ueda, and S. Nagano. An evolutionary algorithm extended by ecological analogy and its application to the game of Go. In Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence (IJCAI-97), pages 684–689. Morgan Kaufmann, 1997.
T. Kojima, K. Ueda, and S. Nagano. Flexible acquisition of various types of knowledge from game records: Application to the game of go. In Proceedings of the Using Games as an Experimental Testbed for AI Research, IJCAI-97 Workshop, pages 51–57, 1997.
T. Kojima, K. Ueda, and S. Nagano. Flexible acquisition of various types of knowledge from game records: Application to the game of go. In V. den Herik, editor, Using Games as An Experimental Testbed for AI Research. Drukkerij van Spijk B.V. Velno, in press.
Y. Saito. Cognitive Scientific Study of Go. PhD thesis, The University of Tokyo, 1996. in Japanese.
Y. Saito and A. Yoshikawa. An analysis of strong Go-players’ protocols. In Game Programming Workshop in Japan’ 96, pages 66–75, 1996.
N. Sasaki and Y. Sawada. Neural networks for solving Go games. In Proc. of The 2nd R.I.E.C. International Symposium on Design and Architecture of Information Processing Systems Based on The Brain Information Principles, pages 241–244. 1998.
S. Sei and T. Kawashima. The experiment of creating move from “local pattern” knowledge in Go program. In Game Programming Workshop in Japan’ 94, pages 97–104, 1994. in Japanese.
T. Wolf. The program GoTools and its computer-generated tsume go database. In Game Programming Workshop in Japan’ 94, pages 84–96, 1994.
A. Yoshikawa and Y. Saito. Perception in tsume-go under 3 second time pressure. In Game Programming Workshop in Japan’ 95, pages 105–112, 1995. in Japanese.
A. Yoshikawa and Y. Saito. Perception in tsumego under 4 seconds time pressure. In Proceedings of the 18th Annual Conference of the Cognitive Science Society, page 868, 1996.
A. Yoshikawa and Y. Saito. The difference of the knowledge for solving tsume-go problem according to the skill. In Game Programming Workshop in Japan rs97, pages 87–95, 1997.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kojima, T., Yoshikawa, A. (1999). A Two-Step Model of Pattern Acquisition: Application to Tsume-Go. In: van den Herik, H.J., Iida, H. (eds) Computers and Games. CG 1998. Lecture Notes in Computer Science, vol 1558. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48957-6_9
Download citation
DOI: https://doi.org/10.1007/3-540-48957-6_9
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65766-8
Online ISBN: 978-3-540-48957-3
eBook Packages: Springer Book Archive