Data Assimilation Technique for Social Agent-Based Simulation by Using Reinforcement Learning

Dong Oh Kang; Jang Won Bae; Chunhee Lee; Joon Young Jung; Euihyun Paik

doi:10.1109/DISTRA.2018.8600925

Data Assimilation Technique for Social Agent-Based Simulation by Using Reinforcement Learning

Dong Oh Kang, Jang Won Bae, Chunhee Lee, Joon Young Jung, Euihyun Paik

School of Computer Science & Engineering

Electronics and Telecommunications Research Institute

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

4 Scopus citations

Abstract

This paper presents a data assimilation technique for social agent-based simulation to fit real world data automatically by a reinforcement learning method. We used the hidden Markov model in order to estimate the states of the system during the reinforcement learning. The proposed method can improve simulation models of the social agent-based simulation incrementally when new real data are available without total optimization. In order to show the feasibility, we applied the proposed method to a housing market problem with real Korean housing market data.

Original language	English
Title of host publication	Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018
Editors	Eva Besada, Oscar Rodriguez Polo, Robson De Grande, Robson De Grande, Jose Luis Risco Martin
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	220-221
Number of pages	2
ISBN (Electronic)	9781538650486
DOIs	https://doi.org/10.1109/DISTRA.2018.8600925
State	Published - 2 Jul 2018
Event	22nd IEEE/ACM International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018 - Madrid, Spain Duration: 15 Oct 2018 → 17 Oct 2018

Publication series

Name	Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018

Conference

Conference	22nd IEEE/ACM International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018
Country/Territory	Spain
City	Madrid
Period	15/10/18 → 17/10/18

Keywords

Agent-based
Data assimilation
Hidden Markov model
Reinforcement learning
Social simulation

Access to Document

10.1109/DISTRA.2018.8600925

Cite this

Kang, D. O., Bae, J. W., Lee, C., Jung, J. Y., & Paik, E. (2018). Data Assimilation Technique for Social Agent-Based Simulation by Using Reinforcement Learning. In E. Besada, O. R. Polo, R. De Grande, R. De Grande, & J. L. Risco Martin (Eds.), Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018 (pp. 220-221). Article 8600925 (Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DISTRA.2018.8600925

Kang, Dong Oh ; Bae, Jang Won ; Lee, Chunhee et al. / Data Assimilation Technique for Social Agent-Based Simulation by Using Reinforcement Learning. Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018. editor / Eva Besada ; Oscar Rodriguez Polo ; Robson De Grande ; Robson De Grande ; Jose Luis Risco Martin. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 220-221 (Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018).

@inproceedings{b48ec0ad8a6b4bcb8b9f8e5b1c6933b9,

title = "Data Assimilation Technique for Social Agent-Based Simulation by Using Reinforcement Learning",

abstract = "This paper presents a data assimilation technique for social agent-based simulation to fit real world data automatically by a reinforcement learning method. We used the hidden Markov model in order to estimate the states of the system during the reinforcement learning. The proposed method can improve simulation models of the social agent-based simulation incrementally when new real data are available without total optimization. In order to show the feasibility, we applied the proposed method to a housing market problem with real Korean housing market data.",

keywords = "Agent-based, Data assimilation, Hidden Markov model, Reinforcement learning, Social simulation",

author = "Kang, {Dong Oh} and Bae, {Jang Won} and Chunhee Lee and Jung, {Joon Young} and Euihyun Paik",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 22nd IEEE/ACM International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018 ; Conference date: 15-10-2018 Through 17-10-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/DISTRA.2018.8600925",

language = "English",

series = "Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "220--221",

editor = "Eva Besada and Polo, {Oscar Rodriguez} and {De Grande}, Robson and {De Grande}, Robson and {Risco Martin}, {Jose Luis}",

booktitle = "Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018",

address = "United States",

}

Kang, DO, Bae, JW, Lee, C, Jung, JY & Paik, E 2018, Data Assimilation Technique for Social Agent-Based Simulation by Using Reinforcement Learning. in E Besada, OR Polo, R De Grande, R De Grande & JL Risco Martin (eds), Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018., 8600925, Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018, Institute of Electrical and Electronics Engineers Inc., pp. 220-221, 22nd IEEE/ACM International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018, Madrid, Spain, 15/10/18. https://doi.org/10.1109/DISTRA.2018.8600925

Data Assimilation Technique for Social Agent-Based Simulation by Using Reinforcement Learning. / Kang, Dong Oh; Bae, Jang Won; Lee, Chunhee et al.
Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018. ed. / Eva Besada; Oscar Rodriguez Polo; Robson De Grande; Robson De Grande; Jose Luis Risco Martin. Institute of Electrical and Electronics Engineers Inc., 2018. p. 220-221 8600925 (Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018).

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

TY - GEN

T1 - Data Assimilation Technique for Social Agent-Based Simulation by Using Reinforcement Learning

AU - Kang, Dong Oh

AU - Bae, Jang Won

AU - Lee, Chunhee

AU - Jung, Joon Young

AU - Paik, Euihyun

PY - 2018/7/2

Y1 - 2018/7/2

N2 - This paper presents a data assimilation technique for social agent-based simulation to fit real world data automatically by a reinforcement learning method. We used the hidden Markov model in order to estimate the states of the system during the reinforcement learning. The proposed method can improve simulation models of the social agent-based simulation incrementally when new real data are available without total optimization. In order to show the feasibility, we applied the proposed method to a housing market problem with real Korean housing market data.

AB - This paper presents a data assimilation technique for social agent-based simulation to fit real world data automatically by a reinforcement learning method. We used the hidden Markov model in order to estimate the states of the system during the reinforcement learning. The proposed method can improve simulation models of the social agent-based simulation incrementally when new real data are available without total optimization. In order to show the feasibility, we applied the proposed method to a housing market problem with real Korean housing market data.

KW - Agent-based

KW - Data assimilation

KW - Hidden Markov model

KW - Reinforcement learning

KW - Social simulation

UR - http://www.scopus.com/inward/record.url?scp=85061642242&partnerID=8YFLogxK

U2 - 10.1109/DISTRA.2018.8600925

DO - 10.1109/DISTRA.2018.8600925

M3 - Conference contribution

AN - SCOPUS:85061642242

T3 - Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018

SP - 220

EP - 221

BT - Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018

A2 - Besada, Eva

A2 - Polo, Oscar Rodriguez

A2 - De Grande, Robson

A2 - Risco Martin, Jose Luis

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 22nd IEEE/ACM International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018

Y2 - 15 October 2018 through 17 October 2018

ER -

Kang DO, Bae JW, Lee C, Jung JY, Paik E. Data Assimilation Technique for Social Agent-Based Simulation by Using Reinforcement Learning. In Besada E, Polo OR, De Grande R, De Grande R, Risco Martin JL, editors, Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 220-221. 8600925. (Proceedings of the 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2018). doi: 10.1109/DISTRA.2018.8600925

Data Assimilation Technique for Social Agent-Based Simulation by Using Reinforcement Learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this