Learning-agent-based simulation for queue network systems
Learning-agent-based simulation for queue network systems
Established simulation methods generally require from the modeller a broad and detailed knowledge of the system under study. This paper proposes the application of Reinforcement Learning in an Agent-Based Simulation model to enable agents to define the necessary interaction rules. The model is applied to queue network systems, which are a proxy for broader applications, in order to be validated. Simulation tests compare results obtained from learning agents and results obtained from known good rules. The comparison shows that the learning model is able to learn efficient policies on the go, providing an interesting framework for simulation.
agent, machine learning, queue network, Simulation
1723-1739
Fuller, Daniel Barry
c1beeb41-ad67-4126-b493-ea31466a85b9
de Arruda, Edilson Fernandes
8eb3bd83-e883-4bf3-bfbc-7887c5daa911
Ferreira Filho, Virgílio José Martins
6853ee2e-9675-43be-afcb-77d1677716e9
1 November 2020
Fuller, Daniel Barry
c1beeb41-ad67-4126-b493-ea31466a85b9
de Arruda, Edilson Fernandes
8eb3bd83-e883-4bf3-bfbc-7887c5daa911
Ferreira Filho, Virgílio José Martins
6853ee2e-9675-43be-afcb-77d1677716e9
Fuller, Daniel Barry, de Arruda, Edilson Fernandes and Ferreira Filho, Virgílio José Martins
(2020)
Learning-agent-based simulation for queue network systems.
Journal of the Operational Research Society, 71 (11), .
(doi:10.1080/01605682.2019.1633232).
Abstract
Established simulation methods generally require from the modeller a broad and detailed knowledge of the system under study. This paper proposes the application of Reinforcement Learning in an Agent-Based Simulation model to enable agents to define the necessary interaction rules. The model is applied to queue network systems, which are a proxy for broader applications, in order to be validated. Simulation tests compare results obtained from learning agents and results obtained from known good rules. The comparison shows that the learning model is able to learn efficient policies on the go, providing an interesting framework for simulation.
This record has no associated files available for download.
More information
Accepted/In Press date: 28 May 2019
e-pub ahead of print date: 9 September 2019
Published date: 1 November 2020
Keywords:
agent, machine learning, queue network, Simulation
Identifiers
Local EPrints ID: 445478
URI: http://eprints.soton.ac.uk/id/eprint/445478
ISSN: 0160-5682
PURE UUID: 6ed14fb2-fd1e-4aaf-af1d-62a1135722e9
Catalogue record
Date deposited: 10 Dec 2020 17:32
Last modified: 17 Mar 2024 04:04
Export record
Altmetrics
Contributors
Author:
Daniel Barry Fuller
Author:
Edilson Fernandes de Arruda
Author:
Virgílio José Martins Ferreira Filho
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics