文章基本信息

标题：State Generalization Based on Maximum Likelihood Estimation Considering Multiple Behavior Outcomes
本地全文：下载
作者：Takehisa Yairi ; Koichi Hori ; Shinichi Nakasuka 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：2001
卷号：16
期号：1
页码：128-138
DOI：10.1527/tjsai.16.128
出版社：The Japanese Society for Artificial Intelligence
摘要：State generalization problem is a significant issue for the realization of the autonomous agents which are expected to decide and learn the proper behavior with various kinds of sensor information. This paper proposes a new state generalization method based on maximum likelihood estimation of the agent’s behavior outcomes. This provides a general framework for unifying the various conventional heuristic generalization criteria which have been used in the previous works, and a way of adapting the state space gradually to the environment.
关键词：robot learning ; behavior acquisition ; state generalization ; information entropy