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

Junya Nakase; Koichi Moriyama; Kiyoshi Kiyokawa; Masayuki Numao; Mayumi Oyama; Satoshi Kurihara

doi:10.1109/VR.2012.6180848

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

Junya Nakase, Koichi Moriyama, Kiyoshi Kiyokawa, Masayuki Numao, Mayumi Oyama, Satoshi Kurihara

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

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.

Original language	English
Title of host publication	IEEE Virtual Reality Conference 2012, VR 2012 - Proceedings
DOIs	https://doi.org/10.1109/VR.2012.6180848
Publication status	Published - 2012
Externally published	Yes
Event	19th IEEE Virtual Reality Conference, VR 2012 - Costa Mesa, CA, United States Duration: 2012 Mar 4 → 2012 Mar 8

Publication series

Name	Proceedings - IEEE Virtual Reality

Other

Other	19th IEEE Virtual Reality Conference, VR 2012
Country/Territory	United States
City	Costa Mesa, CA
Period	12/3/4 → 12/3/8

Keywords

ambient information system
interaction sequence
profit-sharing
reinforcement learning

ASJC Scopus subject areas

Engineering(all)

Access to Document

10.1109/VR.2012.6180848

Cite this

Nakase, J, Moriyama, K, Kiyokawa, K, Numao, M, Oyama, M & Kurihara, S 2012, Adaptive interactive device control by using reinforcement learning in ambient information environment. in IEEE Virtual Reality Conference 2012, VR 2012 - Proceedings., 6180848, Proceedings - IEEE Virtual Reality, 19th IEEE Virtual Reality Conference, VR 2012, Costa Mesa, CA, United States, 12/3/4. https://doi.org/10.1109/VR.2012.6180848

@inproceedings{2c447c095ec742038966cdf1cef615a3,

title = "Adaptive interactive device control by using reinforcement learning in ambient information environment",

abstract = "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.",

keywords = "ambient information system, interaction sequence, profit-sharing, reinforcement learning",

author = "Junya Nakase and Koichi Moriyama and Kiyoshi Kiyokawa and Masayuki Numao and Mayumi Oyama and Satoshi Kurihara",

year = "2012",

doi = "10.1109/VR.2012.6180848",

language = "English",

isbn = "9781467312462",

series = "Proceedings - IEEE Virtual Reality",

booktitle = "IEEE Virtual Reality Conference 2012, VR 2012 - Proceedings",

note = "19th IEEE Virtual Reality Conference, VR 2012 ; Conference date: 04-03-2012 Through 08-03-2012",

}

TY - GEN

T1 - Adaptive interactive device control by using reinforcement learning in ambient information environment

AU - Nakase, Junya

AU - Moriyama, Koichi

AU - Kiyokawa, Kiyoshi

AU - Numao, Masayuki

AU - Oyama, Mayumi

AU - Kurihara, Satoshi

PY - 2012

Y1 - 2012

N2 - 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.

AB - 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.

KW - ambient information system

KW - interaction sequence

KW - profit-sharing

KW - reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=84860754114&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860754114&partnerID=8YFLogxK

U2 - 10.1109/VR.2012.6180848

DO - 10.1109/VR.2012.6180848

M3 - Conference contribution

AN - SCOPUS:84860754114

SN - 9781467312462

T3 - Proceedings - IEEE Virtual Reality

BT - IEEE Virtual Reality Conference 2012, VR 2012 - Proceedings

T2 - 19th IEEE Virtual Reality Conference, VR 2012

Y2 - 4 March 2012 through 8 March 2012

ER -

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

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this