Predicting the COVID19 Trajectory with a Simulation Deep Reinforcement Learning Approach

Sabah Bushaj; Esra Büyüktahtakın; Arjeta Beqiri

Predicting the COVID19 Trajectory with a Simulation Deep Reinforcement Learning Approach

Sabah Bushaj, Esra Büyüktahtakın, Arjeta Beqiri

Mechanical and Industrial Engr

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

Abstract

COVID19 pandemic has severely impacted every government and citizen of the world. At the same time, it has emphasized the significance of governmental decisionmaking when facing a sudden outbreak. In this paper, we aim to aid governments in addressing the difficult problem of epidemic control planning by providing a disease trajectory and economic impacts. We study a SimulationDeep Reinforcement Learning (SiRL) methodology to predict the COVID19 pandemic's trajectory for the next three months considering different intervention strategies. Our experiments show that if no action is taken, and the current rate of vaccination is assumed, the daily cases could see an increase of 145%. Our Reinforcement Learning (RL) agent builds a compromise between the size of the infected population and the pandemicrelated economic costs.

Original language	English (US)
Title of host publication	IISE Annual Conference and Expo 2022
Editors	K. Ellis, W. Ferrell, J. Knapp
Publisher	Institute of Industrial and Systems Engineers, IISE
ISBN (Electronic)	9781713858072
State	Published - 2022
Event	IISE Annual Conference and Expo 2022 - Seattle, United States Duration: May 21 2022 → May 24 2022

Publication series

Name	IISE Annual Conference and Expo 2022

Conference

Conference	IISE Annual Conference and Expo 2022
Country/Territory	United States
City	Seattle
Period	5/21/22 → 5/24/22

All Science Journal Classification (ASJC) codes

Control and Systems Engineering
Industrial and Manufacturing Engineering

Keywords

AgentBased Simulation
COVID19
Deep Reinforcement Learning
Epidemic Control Planning
SimulationDeep Reinforcement Learning

Cite this

@inproceedings{d8efbbe7b4f84df9bdcc117c08ec1a38,

title = "Predicting the COVID19 Trajectory with a Simulation Deep Reinforcement Learning Approach",

abstract = "COVID19 pandemic has severely impacted every government and citizen of the world. At the same time, it has emphasized the significance of governmental decisionmaking when facing a sudden outbreak. In this paper, we aim to aid governments in addressing the difficult problem of epidemic control planning by providing a disease trajectory and economic impacts. We study a SimulationDeep Reinforcement Learning (SiRL) methodology to predict the COVID19 pandemic's trajectory for the next three months considering different intervention strategies. Our experiments show that if no action is taken, and the current rate of vaccination is assumed, the daily cases could see an increase of 145%. Our Reinforcement Learning (RL) agent builds a compromise between the size of the infected population and the pandemicrelated economic costs.",

keywords = "AgentBased Simulation, COVID19, Deep Reinforcement Learning, Epidemic Control Planning, SimulationDeep Reinforcement Learning",

author = "Sabah Bushaj and Esra B{\"u}y{\"u}ktahtakın and Arjeta Beqiri",

year = "2022",

language = "English (US)",

series = "IISE Annual Conference and Expo 2022",

publisher = "Institute of Industrial and Systems Engineers, IISE",

editor = "K. Ellis and W. Ferrell and J. Knapp",

booktitle = "IISE Annual Conference and Expo 2022",

}

Bushaj, S, Büyüktahtakın, E & Beqiri, A 2022, Predicting the COVID19 Trajectory with a Simulation Deep Reinforcement Learning Approach. in K Ellis, W Ferrell & J Knapp (eds), IISE Annual Conference and Expo 2022. IISE Annual Conference and Expo 2022, Institute of Industrial and Systems Engineers, IISE, IISE Annual Conference and Expo 2022, Seattle, United States, 5/21/22.

Predicting the COVID19 Trajectory with a Simulation Deep Reinforcement Learning Approach. / Bushaj, Sabah; Büyüktahtakın, Esra; Beqiri, Arjeta.
IISE Annual Conference and Expo 2022. ed. / K. Ellis; W. Ferrell; J. Knapp. Institute of Industrial and Systems Engineers, IISE, 2022. (IISE Annual Conference and Expo 2022).

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

TY - GEN

T1 - Predicting the COVID19 Trajectory with a Simulation Deep Reinforcement Learning Approach

AU - Bushaj, Sabah

AU - Büyüktahtakın, Esra

AU - Beqiri, Arjeta

PY - 2022

Y1 - 2022

N2 - COVID19 pandemic has severely impacted every government and citizen of the world. At the same time, it has emphasized the significance of governmental decisionmaking when facing a sudden outbreak. In this paper, we aim to aid governments in addressing the difficult problem of epidemic control planning by providing a disease trajectory and economic impacts. We study a SimulationDeep Reinforcement Learning (SiRL) methodology to predict the COVID19 pandemic's trajectory for the next three months considering different intervention strategies. Our experiments show that if no action is taken, and the current rate of vaccination is assumed, the daily cases could see an increase of 145%. Our Reinforcement Learning (RL) agent builds a compromise between the size of the infected population and the pandemicrelated economic costs.

AB - COVID19 pandemic has severely impacted every government and citizen of the world. At the same time, it has emphasized the significance of governmental decisionmaking when facing a sudden outbreak. In this paper, we aim to aid governments in addressing the difficult problem of epidemic control planning by providing a disease trajectory and economic impacts. We study a SimulationDeep Reinforcement Learning (SiRL) methodology to predict the COVID19 pandemic's trajectory for the next three months considering different intervention strategies. Our experiments show that if no action is taken, and the current rate of vaccination is assumed, the daily cases could see an increase of 145%. Our Reinforcement Learning (RL) agent builds a compromise between the size of the infected population and the pandemicrelated economic costs.

KW - AgentBased Simulation

KW - COVID19

KW - Deep Reinforcement Learning

KW - Epidemic Control Planning

KW - SimulationDeep Reinforcement Learning

UR - http://www.scopus.com/inward/record.url?scp=85137178047&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85137178047&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85137178047

T3 - IISE Annual Conference and Expo 2022

BT - IISE Annual Conference and Expo 2022

A2 - Ellis, K.

A2 - Ferrell, W.

A2 - Knapp, J.

PB - Institute of Industrial and Systems Engineers, IISE

T2 - IISE Annual Conference and Expo 2022

Y2 - 21 May 2022 through 24 May 2022

ER -

Predicting the COVID19 Trajectory with a Simulation Deep Reinforcement Learning Approach

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Keywords

Other files and links

Fingerprint

Cite this