文章基本信息

标题：A Rough - Neuro Model for Classifying Opponent Behavior in Real Time Strategy Games
本地全文：下载
作者：M. Z. Rashad
期刊名称：International Journal of Computer Science & Information Technology (IJCSIT)
印刷版ISSN：0975-4660
电子版ISSN：0975-3826
出版年度：2012
卷号：4
期号：5
页码：185
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Real Time strategy games offer an environment where game AI is known to conduct actuality. One featureof realistic behavior in game AI is the ability to recognize the strategy of the opponent player. This isknown as opponent modeling. In this paper, a classification Rough-Neuro hybrid model of the RTSopponent player behavior process is proposed. As a mean to achieve better game performance, reductionof the agent decision space and better high-level winning of real-time strategy games. The Rough-Neuromethodology allows the classification model to some extent simulate opponent behavior in playing RTSgames. The methodology incorporates a two-stage hybrid mechanism. Rough sets for reduction of relevantattributes and artificial neural networks for classification opponent behavior during game playing. Theproposed hybrid approach has been tested on an open source 3D RTS game called Glest. From our resultswe can deduce that the tactic may be successfully used for foretelling the demeanor of contender in theGlest game.
关键词：Real-Time Strategy Games; rough sets; attribute reduction; opponent modeling; neural network