JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/11410

Title: Adaptation of Game AIs using Genetic Algorithm: Keeping Variety and Suitable Strength
Authors: Ikeda, Kokolo
Tanaka, Yu
Viennot, Simon
Quoc, Nguyen Huy
Ueda, Yohei
Keywords: genetic algorithm
variety maintenance
natural behavior
entertainment
Issue Date: 2012-11
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Magazine name: 2012 Joint 6th International Conference on Soft Computing and Intelligent Systems (SCIS) and 13th International Symposium on Advanced Intelligent Systems (ISIS)
Start page: 945
End page: 951
DOI: 10.1109/SCIS-ISIS.2012.6505249
Abstract: Advancement of artificial intelligence (AI) technology have made computer game players stronger than any human players in many games. However, it is still difficult to create game Als that have a suitable strength for the average human player, while having various strategies and avoiding unnatural moves. We propose a method for generating "a group of rival Als" which satisfy these requirements by using a Genetic Algorithm. In this paper, this method is applied to Othello game and evaluated through some experiments and questionnaires.
Rights: This is the author's version of the work. Copyright (C) 2012 IEEE. 2012 Joint 6th International Conference on Soft Computing and Intelligent Systems (SCIS) and 13th International Symposium on Advanced Intelligent Systems (ISIS), 2012, 945-951. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
URI: http://hdl.handle.net/10119/11410
Material Type: author
Appears in Collections:b11-1. 会議発表論文・発表資料 (Conference Papers)

Files in This Item:

File Description SizeFormat
18703.pdf578KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.

 


Contact : Library Information Section, Japan Advanced Institute of Science and Technology