文章基本信息

标题：A Machine Learning System for Analyzing Human Tactics in a Game
本地全文：下载
作者：Hirotaka Ito ; Toshimitsu Tanaka ; Noboru Sugie 等
期刊名称：人工知能学会論文誌
印刷版ISSN：1346-0714
电子版ISSN：1346-8030
出版年度：2003
卷号：18
期号：3
页码：161-164
DOI：10.1527/tjsai.18.161
出版社：The Japanese Society for Artificial Intelligence
摘要：In order to realize advanced man-machine interfaces, it is desired to develop a system that can infer the mental state of human users and then return appropriate responses. As the first step toward the above goal, we developed a system capable of inferring human tactics in a simple game played between the system and a human. We present a machine learning system that plays a color expectation game. The system infers the tactics of the opponent, and then decides the action based on the result. We employed a modified version of classifier system like XCS in order to design the system. In addition, three methods are proposed in order to accelerate the learning rate. They are a masking method, an iterative method, and tactics templates. The results of computer experiments confirmed that the proposed methods effectively accelerate the machine learning. The masking method and the iterative method are effective to a simple strategy that considers only a part of past information. However, study speed of these methods is not enough for the tactics that refers to a lot of past information. For the case, the tactics template was able to settle the study rapidly when the tactics is identified.
关键词：machine learning system ; game ; GA ; classifier system ; AI