Canonical Sequence Directed Tactics Analyzer for Computer Go Games

Author

Li, Chung-Chih ; Koh, Hikyoo

Author_Institution

Comput. Sci. Dept., Lamar Univ., Beaumont, TX

Volume

1

fYear

2005

fDate

28-30 Nov. 2005

Firstpage

1066

Lastpage

1071

Abstract

We present an approach used in CSDTA (canonical sequence directed tactics analyzer) that uses canonical sequences (Joseki) in hoping to improve computer Go programs. We collect 1278 canonical sequences and their deviations in our system. Instead of trivially matching the current game to the collected sequences, we define a notion of similarity to extract the most suitable move from the candidate sequences for the next move. The simplicity of our method and its positive outcome make our approach a promising tool to be integrated into a complete computer Go program for a foreseeable improvement

Keywords

artificial intelligence; computer games; matrix algebra; sequences; artificial intelligence; canonical sequence directed tactics analyzer; computer Go game; matrix algebra; Algorithm design and analysis; Artificial intelligence; Books; Computational and artificial intelligence; Computer science; Humans; Machine learning; Pattern recognition; Search engines;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence for Modelling, Control and Automation, 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, International Conference on

Conference_Location

Vienna

Print_ISBN

0-7695-2504-0

Type

conf

DOI

10.1109/CIMCA.2005.1631404

Filename

1631404