Self-adaptive genetic algorithm learning in game playing

Chuen-Tsai Sun*, Ming Da Wu

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

6 Scopus citations

Abstract

Genetic algorithms (GAs) are known to be effective search methods that are also robust and efficient. In this paper, we introduce a self-adaptive function for conventional GAs. A dynamic fitness technique helpful for continuous evolution and robust solution is also presented. We expect to improve the quality of GA searches in solving direct competitive problems. We tested our idea by using it to play the game Othello, a typical problem with the direct competitive properties. Experimental results show that our method is better than traditional approaches.

Original languageEnglish
Pages814-818
Number of pages5
DOIs
StatePublished - 1 Dec 1995
EventProceedings of the 1995 IEEE International Conference on Evolutionary Computation. Part 1 (of 2) - Perth, Aust
Duration: 29 Nov 19951 Dec 1995

Conference

ConferenceProceedings of the 1995 IEEE International Conference on Evolutionary Computation. Part 1 (of 2)
CityPerth, Aust
Period29/11/951/12/95

Fingerprint Dive into the research topics of 'Self-adaptive genetic algorithm learning in game playing'. Together they form a unique fingerprint.

Cite this