Adaptive interactive device control by using reinforcement learning in ambient information environment

被引：0

作者：

Nakase, Junya ^{[1
]}

Moriyama, Koichi ^{[2
]}

Kiyokawa, Kiyoshi ^{[1
]}

Numao, Masayuki ^{[2
]}

Oyama, Mayumi ^{[3
]}

Kurihara, Satoshi ^{[2
]}

机构：

[1] Osaka Univ, Grad Sch Informat Sci & Technol, Suita, Osaka 565, Japan

[2] Osaka Univ, Inst Sci & Ind Res, Osaka 5670047, Japan

[3] Kwansei Gakuin Univ, Osaka, Japan

来源：

IEEE VIRTUAL REALITY CONFERENCE 2012 PROCEEDINGS | 2012年

关键词：

interaction sequence; reinforcement learning; profit-sharing; ambient information system;

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

In ambient information systems, not only extracting human behavior by sensor network but also adaptive autonomous interaction between the environment and humans is an important function. In this paper we propose a reinforcement learning framework to extract suitable interaction for each person from daily behavior. In the experiment, we show the feasibility of the proposed methodology.

引用

页数：4