Learning from human behavior in participatory simulation

Toru Ishida, Yohei Murakami, Yuu Nakajima

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

To design socially embedded systems, this paper proposes to learn from human behavior in participatory simulation, where scenario-guided agents and human-controlled avatars coexist in a shared virtual space and jointly perform simulations. To create agent models incrementally, we use machine learning technologies. We characterize agents by using a various combinations of behavior rules instantiated by the user operating his/her avatar. We apply hypothetical reasoning, which offers consistent selection of hypotheses and allows us to start with incompatible behavior rules, for incrementally improving the agent models. Using data obtained during the participatory simulation and the hypotheses including known behavior rules, we can generate an explanation for human behavior.

Original languageEnglish
Title of host publicationAmbient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009
Pages147-157
Number of pages11
DOIs
Publication statusPublished - 2009 Dec 1
Externally publishedYes
EventAmbient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009 - Hradec Kralove, Czech Republic
Duration: 2009 Sep 162009 Sep 17

Publication series

NameAmbient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009
Volume5

Conference

ConferenceAmbient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009
CountryCzech Republic
CityHradec Kralove
Period09/9/1609/9/17

Fingerprint

Embedded systems
Learning systems

Keywords

  • Agent modeling
  • Machine learning
  • Multiagent simulation
  • Participatory simulation

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Ishida, T., Murakami, Y., & Nakajima, Y. (2009). Learning from human behavior in participatory simulation. In Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009 (pp. 147-157). (Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009; Vol. 5). https://doi.org/10.3233/978-1-60750-481-8-147

Learning from human behavior in participatory simulation. / Ishida, Toru; Murakami, Yohei; Nakajima, Yuu.

Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009. 2009. p. 147-157 (Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009; Vol. 5).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ishida, T, Murakami, Y & Nakajima, Y 2009, Learning from human behavior in participatory simulation. in Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009. Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009, vol. 5, pp. 147-157, Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009, Hradec Kralove, Czech Republic, 09/9/16. https://doi.org/10.3233/978-1-60750-481-8-147
Ishida T, Murakami Y, Nakajima Y. Learning from human behavior in participatory simulation. In Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009. 2009. p. 147-157. (Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009). https://doi.org/10.3233/978-1-60750-481-8-147
Ishida, Toru ; Murakami, Yohei ; Nakajima, Yuu. / Learning from human behavior in participatory simulation. Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009. 2009. pp. 147-157 (Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009).
@inproceedings{4a3524fea3b84a728a594492e254eb4e,
title = "Learning from human behavior in participatory simulation",
abstract = "To design socially embedded systems, this paper proposes to learn from human behavior in participatory simulation, where scenario-guided agents and human-controlled avatars coexist in a shared virtual space and jointly perform simulations. To create agent models incrementally, we use machine learning technologies. We characterize agents by using a various combinations of behavior rules instantiated by the user operating his/her avatar. We apply hypothetical reasoning, which offers consistent selection of hypotheses and allows us to start with incompatible behavior rules, for incrementally improving the agent models. Using data obtained during the participatory simulation and the hypotheses including known behavior rules, we can generate an explanation for human behavior.",
keywords = "Agent modeling, Machine learning, Multiagent simulation, Participatory simulation",
author = "Toru Ishida and Yohei Murakami and Yuu Nakajima",
year = "2009",
month = "12",
day = "1",
doi = "10.3233/978-1-60750-481-8-147",
language = "English",
isbn = "9781607504801",
series = "Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009",
pages = "147--157",
booktitle = "Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009",

}

TY - GEN

T1 - Learning from human behavior in participatory simulation

AU - Ishida, Toru

AU - Murakami, Yohei

AU - Nakajima, Yuu

PY - 2009/12/1

Y1 - 2009/12/1

N2 - To design socially embedded systems, this paper proposes to learn from human behavior in participatory simulation, where scenario-guided agents and human-controlled avatars coexist in a shared virtual space and jointly perform simulations. To create agent models incrementally, we use machine learning technologies. We characterize agents by using a various combinations of behavior rules instantiated by the user operating his/her avatar. We apply hypothetical reasoning, which offers consistent selection of hypotheses and allows us to start with incompatible behavior rules, for incrementally improving the agent models. Using data obtained during the participatory simulation and the hypotheses including known behavior rules, we can generate an explanation for human behavior.

AB - To design socially embedded systems, this paper proposes to learn from human behavior in participatory simulation, where scenario-guided agents and human-controlled avatars coexist in a shared virtual space and jointly perform simulations. To create agent models incrementally, we use machine learning technologies. We characterize agents by using a various combinations of behavior rules instantiated by the user operating his/her avatar. We apply hypothetical reasoning, which offers consistent selection of hypotheses and allows us to start with incompatible behavior rules, for incrementally improving the agent models. Using data obtained during the participatory simulation and the hypotheses including known behavior rules, we can generate an explanation for human behavior.

KW - Agent modeling

KW - Machine learning

KW - Multiagent simulation

KW - Participatory simulation

UR - http://www.scopus.com/inward/record.url?scp=84877706964&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877706964&partnerID=8YFLogxK

U2 - 10.3233/978-1-60750-481-8-147

DO - 10.3233/978-1-60750-481-8-147

M3 - Conference contribution

AN - SCOPUS:84877706964

SN - 9781607504801

T3 - Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009

SP - 147

EP - 157

BT - Ambient Intelligence Perspectives II - Selected Papers from the 2nd International Ambient Intelligence Forum 2009, AmIF 2009

ER -