Many researchers have written or attempted to write programs that play the ancient Chinese board game called Go. Although some programs play the game quite well compared with beginners, few play extremely well, and none of the best programs rely on soft computing artificial intelligence techniques like genetic algorithms or neural networks. This paper explores the advantages and possibilities of using genetic algorithms to evolve a multiagent Go player. We show that although individual agents may play poorly, collectively the agents working together play the game significantly better.
This is the published version. Copyright De Gruyter
Blackman, Todd, and Arvin Agah. "A Multi-Agent Approach to the Game of Go Using Genetic Algorithms." Journal of Intelligent Systems 18.1-2 (2011): n. pag. http://dx.doi.org/10.1515/JISYS.2009.18.1-2.143.
Items in KU ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
We want to hear from you! Please
share your stories
about how Open Access to this item benefits YOU.
The University of Kansas prohibits discrimination on the basis of race, color, ethnicity, religion, sex, national origin, age, ancestry, disability, status as a veteran, sexual orientation, marital status, parental status, gender identity, gender expression and genetic information in the University’s programs and activities. The following person has been designated to handle inquiries regarding the non-discrimination policies: Director of the Office of Institutional Opportunity and Access, IOA@ku.edu, 1246 W. Campus Road, Room 153A, Lawrence, KS, 66045, (785)864-6414, 711 TTY.