A study on finding an optimal response strategy considering infrastructures in an agent-based radiological emergency model using a deep Q-network

Gibeom Kim; Gyunyoung Heo

doi:10.3850/978-981-18-5183-4_R06-03-388-cd

A study on finding an optimal response strategy considering infrastructures in an agent-based radiological emergency model using a deep Q-network

Gibeom Kim
, Gyunyoung Heo

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

Abstract

A radioactive emergency involves a variety of elements such as evacuees, hazardous materials, and response facilities and resources, and the interactions of those elements make it difficult to predict consequences or response effects. Agent-based modeling (ABM) may be a useful method for the integrated modeling of the radiological emergency. In this paper, a simple case study that simulates emergency evacuation considering shelter’s relief supplies using ABM is presented. The evacuation completion time may vary depending on how to distribute the limited shelter resources. To obtain an optimal strategy for the resource distribution, reinforcement learning is applied. Deep Q-network (DQN) was applied in consideration of the extensive state space due to the complexity of the radiological emergency. By applying DQN, a shelter resource distribution scenario that shortens the evacuation completion time was obtained. Through this study, the availability of DQN as a way to find the optimal response strategy was assessed.

Original language	English
Title of host publication	Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future
Editors	Maria Chiara Leva, Edoardo Patelli, Luca Podofillini, Simon Wilson
Publisher	Research Publishing
Pages	212-216
Number of pages	5
ISBN (Print)	9789811851834
DOIs	https://doi.org/10.3850/978-981-18-5183-4_R06-03-388-cd
Publication status	Published - 2022
Event	32nd European Safety and Reliability Conference, ESREL 2022 - Dublin, Ireland Duration: 28 Aug 2022 → 1 Sept 2022

Publication series

Name	Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future

Conference

Conference	32nd European Safety and Reliability Conference, ESREL 2022
Country/Territory	Ireland
City	Dublin
Period	28/08/22 → 1/09/22

Bibliographical note

Publisher Copyright:
© 2022 ESREL2022 Organizers. Published by Research Publishing, Singapore.

Keywords

Agent-based model
Deep Q-network
Emergency response
Reinforcement learning

Access to Document

10.3850/978-981-18-5183-4_R06-03-388-cd

Cite this

Kim, G., & Heo, G. (2022). A study on finding an optimal response strategy considering infrastructures in an agent-based radiological emergency model using a deep Q-network. In M. C. Leva, E. Patelli, L. Podofillini, & S. Wilson (Eds.), Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future (pp. 212-216). (Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future). Research Publishing. https://doi.org/10.3850/978-981-18-5183-4_R06-03-388-cd

Kim, Gibeom ; Heo, Gyunyoung. / A study on finding an optimal response strategy considering infrastructures in an agent-based radiological emergency model using a deep Q-network. Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future. editor / Maria Chiara Leva ; Edoardo Patelli ; Luca Podofillini ; Simon Wilson. Research Publishing, 2022. pp. 212-216 (Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future).

@inproceedings{3d7b3b72938d4f19a724f0707546ac54,

title = "A study on finding an optimal response strategy considering infrastructures in an agent-based radiological emergency model using a deep Q-network",

abstract = "A radioactive emergency involves a variety of elements such as evacuees, hazardous materials, and response facilities and resources, and the interactions of those elements make it difficult to predict consequences or response effects. Agent-based modeling (ABM) may be a useful method for the integrated modeling of the radiological emergency. In this paper, a simple case study that simulates emergency evacuation considering shelter{\textquoteright}s relief supplies using ABM is presented. The evacuation completion time may vary depending on how to distribute the limited shelter resources. To obtain an optimal strategy for the resource distribution, reinforcement learning is applied. Deep Q-network (DQN) was applied in consideration of the extensive state space due to the complexity of the radiological emergency. By applying DQN, a shelter resource distribution scenario that shortens the evacuation completion time was obtained. Through this study, the availability of DQN as a way to find the optimal response strategy was assessed.",

keywords = "Agent-based model, Deep Q-network, Emergency response, Reinforcement learning",

author = "Gibeom Kim and Gyunyoung Heo",

note = "Publisher Copyright: {\textcopyright} 2022 ESREL2022 Organizers. Published by Research Publishing, Singapore.; 32nd European Safety and Reliability Conference, ESREL 2022 ; Conference date: 28-08-2022 Through 01-09-2022",

year = "2022",

doi = "10.3850/978-981-18-5183-4\_R06-03-388-cd",

language = "English",

isbn = "9789811851834",

series = "Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future",

publisher = "Research Publishing",

pages = "212--216",

editor = "Leva, \{Maria Chiara\} and Edoardo Patelli and Luca Podofillini and Simon Wilson",

booktitle = "Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future",

}

Kim, G & Heo, G 2022, A study on finding an optimal response strategy considering infrastructures in an agent-based radiological emergency model using a deep Q-network. in MC Leva, E Patelli, L Podofillini & S Wilson (eds), Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future. Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future, Research Publishing, pp. 212-216, 32nd European Safety and Reliability Conference, ESREL 2022, Dublin, Ireland, 28/08/22. https://doi.org/10.3850/978-981-18-5183-4_R06-03-388-cd

A study on finding an optimal response strategy considering infrastructures in an agent-based radiological emergency model using a deep Q-network. / Kim, Gibeom; Heo, Gyunyoung.
Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future. ed. / Maria Chiara Leva; Edoardo Patelli; Luca Podofillini; Simon Wilson. Research Publishing, 2022. p. 212-216 (Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future).

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

TY - GEN

T1 - A study on finding an optimal response strategy considering infrastructures in an agent-based radiological emergency model using a deep Q-network

AU - Kim, Gibeom

AU - Heo, Gyunyoung

PY - 2022

Y1 - 2022

N2 - A radioactive emergency involves a variety of elements such as evacuees, hazardous materials, and response facilities and resources, and the interactions of those elements make it difficult to predict consequences or response effects. Agent-based modeling (ABM) may be a useful method for the integrated modeling of the radiological emergency. In this paper, a simple case study that simulates emergency evacuation considering shelter’s relief supplies using ABM is presented. The evacuation completion time may vary depending on how to distribute the limited shelter resources. To obtain an optimal strategy for the resource distribution, reinforcement learning is applied. Deep Q-network (DQN) was applied in consideration of the extensive state space due to the complexity of the radiological emergency. By applying DQN, a shelter resource distribution scenario that shortens the evacuation completion time was obtained. Through this study, the availability of DQN as a way to find the optimal response strategy was assessed.

AB - A radioactive emergency involves a variety of elements such as evacuees, hazardous materials, and response facilities and resources, and the interactions of those elements make it difficult to predict consequences or response effects. Agent-based modeling (ABM) may be a useful method for the integrated modeling of the radiological emergency. In this paper, a simple case study that simulates emergency evacuation considering shelter’s relief supplies using ABM is presented. The evacuation completion time may vary depending on how to distribute the limited shelter resources. To obtain an optimal strategy for the resource distribution, reinforcement learning is applied. Deep Q-network (DQN) was applied in consideration of the extensive state space due to the complexity of the radiological emergency. By applying DQN, a shelter resource distribution scenario that shortens the evacuation completion time was obtained. Through this study, the availability of DQN as a way to find the optimal response strategy was assessed.

KW - Agent-based model

KW - Deep Q-network

KW - Emergency response

KW - Reinforcement learning

UR - https://www.scopus.com/pages/publications/85208253695

U2 - 10.3850/978-981-18-5183-4_R06-03-388-cd

DO - 10.3850/978-981-18-5183-4_R06-03-388-cd

M3 - Conference contribution

AN - SCOPUS:85208253695

SN - 9789811851834

T3 - Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future

SP - 212

EP - 216

BT - Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future

A2 - Leva, Maria Chiara

A2 - Patelli, Edoardo

A2 - Podofillini, Luca

A2 - Wilson, Simon

PB - Research Publishing

T2 - 32nd European Safety and Reliability Conference, ESREL 2022

Y2 - 28 August 2022 through 1 September 2022

ER -

Kim G, Heo G. A study on finding an optimal response strategy considering infrastructures in an agent-based radiological emergency model using a deep Q-network. In Leva MC, Patelli E, Podofillini L, Wilson S, editors, Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future. Research Publishing. 2022. p. 212-216. (Proceedings of the 32nd European Safety and Reliability Conference, ESREL 2022 - Understanding and Managing Risk and Reliability for a Sustainable Future). doi: 10.3850/978-981-18-5183-4_R06-03-388-cd

A study on finding an optimal response strategy considering infrastructures in an agent-based radiological emergency model using a deep Q-network

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this