Sustainable pavement maintenance using reinforcement learning with systematic reward design

[EN] Efficient and sustainable pavement maintenance planning remains a challenge for infrastructure managers. This study introduces a reinforcement learning methodology, based on the Q-Learning algorithm, to optimize long-term pavement maintenance policies under multiple objectives. The contribution...

Full description

Bibliographic Details
Authors: Molinero-Pérez, Noelia|||0000-0001-8279-4585, Sanz-Benlloch, Amalia|||0000-0001-8051-0649, Montalbán-Domingo, Laura|||0000-0002-9506-0350, García-Segura, Tatiana|||0000-0002-7059-0566
Format: article
Publication Date:2026
Country:España
Institution:Universitat Politècnica de València (UPV)
Repository:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Language:English
OAI Identifier:oai:dnet:riunet______::f083a6c165cdf0b9adb0b97a6fef84b4
Online Access:https://riunet.upv.es/handle/10251/234367
Access Level:Embargoed access
Keyword:Pavement maintenance
Machine learning
Systematic reward design
Sustainability
Q-learning
09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación
11.- Conseguir que las ciudades y los asentamientos humanos sean inclusivos, seguros, resilientes y sostenibles
id ES_4aa668aa24bd3d4367c6abb92c943d2e
oai_identifier_str oai:dnet:riunet______::f083a6c165cdf0b9adb0b97a6fef84b4
network_acronym_str ES
network_name_str España
repository_id_str
spelling Sustainable pavement maintenance using reinforcement learning with systematic reward designMolinero-Pérez, Noelia|||0000-0001-8279-4585Sanz-Benlloch, Amalia|||0000-0001-8051-0649Montalbán-Domingo, Laura|||0000-0002-9506-0350García-Segura, Tatiana|||0000-0002-7059-0566Pavement maintenanceMachine learningSystematic reward designSustainabilityQ-learning09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación11.- Conseguir que las ciudades y los asentamientos humanos sean inclusivos, seguros, resilientes y sostenibles[EN] Efficient and sustainable pavement maintenance planning remains a challenge for infrastructure managers. This study introduces a reinforcement learning methodology, based on the Q-Learning algorithm, to optimize long-term pavement maintenance policies under multiple objectives. The contribution is a systematic framework for designing tailored reward functions aligned with planning goals, including economic cost, environmental impact, user savings, and maintenance effectiveness. This alignment enables the model to adapt and learn optimal strategies according to different priorities. The approach is validated through fifteen real-world case studies from the Spanish road network, incorporating traffic, structural, and climatic data. For each case, Q-Learning is trained with alternative reward formulations and evaluated over a 20-year horizon, followed by robustness analysis to assess policy stability. Results show that reward functions lead to differentiated intervention strategies, influenced by the planning objective. Cost- and emissions-oriented rewards generate reactive policies, recommending intervention only when inaction would significantly increase maintenance and rehabilitation costs. In contrast, rewards focused on user savings or technical effectiveness promote proactive continuous maintenance to preserve surface conditions and reduce indirect user costs. The proposed approach underscores the critical role of reward definition in reinforcement learning and provides a practical tool to support adaptive, sustainable, and long-term pavement management.This research is part of the grant PID2022-141875OA-I00, funded by MCIN/AEI/10.13039/501100011033 and by ERDF/EU.Taylor & FrancisDepartamento de Ingeniería de la Construcción y de Proyectos de Ingeniería CivilEscuela Técnica Superior de Ingeniería de Caminos, Canales y PuertosGrupo de Gestión del Proceso Proyecto-ConstrucciónAgencia Estatal de InvestigaciónEuropean Regional Development FundRepositorio Institucional de la Universitat Politècnica de València Riunet20262026-12-3120262026-04-1620272027-12-31journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfapplication/pdfhttps://riunet.upv.es/handle/10251/234367reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valénciainstname:Universitat Politècnica de València (UPV)InglésengAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2022-141875OA-I00 REINFORCEMENT LEARNING ADAPTADO AL MANTENIMIENTO RESILIENTE DE CARRETERAS FRENTE AL CAMBIO CLIMATICOembargoed accesshttp://purl.org/coar/access_right/c_f1cfReserva de todos los derechoshttp://rightsstatements.org/vocab/InC/1.0/info:eu-repo/semantics/embargoedAccessoai:dnet:riunet______::f083a6c165cdf0b9adb0b97a6fef84b42026-06-13T07:49:27Z
dc.title.none.fl_str_mv Sustainable pavement maintenance using reinforcement learning with systematic reward design
title Sustainable pavement maintenance using reinforcement learning with systematic reward design
spellingShingle Sustainable pavement maintenance using reinforcement learning with systematic reward design
Molinero-Pérez, Noelia|||0000-0001-8279-4585
Pavement maintenance
Machine learning
Systematic reward design
Sustainability
Q-learning
09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación
11.- Conseguir que las ciudades y los asentamientos humanos sean inclusivos, seguros, resilientes y sostenibles
title_short Sustainable pavement maintenance using reinforcement learning with systematic reward design
title_full Sustainable pavement maintenance using reinforcement learning with systematic reward design
title_fullStr Sustainable pavement maintenance using reinforcement learning with systematic reward design
title_full_unstemmed Sustainable pavement maintenance using reinforcement learning with systematic reward design
title_sort Sustainable pavement maintenance using reinforcement learning with systematic reward design
dc.creator.none.fl_str_mv Molinero-Pérez, Noelia|||0000-0001-8279-4585
Sanz-Benlloch, Amalia|||0000-0001-8051-0649
Montalbán-Domingo, Laura|||0000-0002-9506-0350
García-Segura, Tatiana|||0000-0002-7059-0566
author Molinero-Pérez, Noelia|||0000-0001-8279-4585
author_facet Molinero-Pérez, Noelia|||0000-0001-8279-4585
Sanz-Benlloch, Amalia|||0000-0001-8051-0649
Montalbán-Domingo, Laura|||0000-0002-9506-0350
García-Segura, Tatiana|||0000-0002-7059-0566
author_role author
author2 Sanz-Benlloch, Amalia|||0000-0001-8051-0649
Montalbán-Domingo, Laura|||0000-0002-9506-0350
García-Segura, Tatiana|||0000-0002-7059-0566
author2_role author
author
author
dc.contributor.none.fl_str_mv Departamento de Ingeniería de la Construcción y de Proyectos de Ingeniería Civil
Escuela Técnica Superior de Ingeniería de Caminos, Canales y Puertos
Grupo de Gestión del Proceso Proyecto-Construcción
Agencia Estatal de Investigación
European Regional Development Fund
Repositorio Institucional de la Universitat Politècnica de València Riunet
dc.subject.none.fl_str_mv Pavement maintenance
Machine learning
Systematic reward design
Sustainability
Q-learning
09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación
11.- Conseguir que las ciudades y los asentamientos humanos sean inclusivos, seguros, resilientes y sostenibles
topic Pavement maintenance
Machine learning
Systematic reward design
Sustainability
Q-learning
09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación
11.- Conseguir que las ciudades y los asentamientos humanos sean inclusivos, seguros, resilientes y sostenibles
description [EN] Efficient and sustainable pavement maintenance planning remains a challenge for infrastructure managers. This study introduces a reinforcement learning methodology, based on the Q-Learning algorithm, to optimize long-term pavement maintenance policies under multiple objectives. The contribution is a systematic framework for designing tailored reward functions aligned with planning goals, including economic cost, environmental impact, user savings, and maintenance effectiveness. This alignment enables the model to adapt and learn optimal strategies according to different priorities. The approach is validated through fifteen real-world case studies from the Spanish road network, incorporating traffic, structural, and climatic data. For each case, Q-Learning is trained with alternative reward formulations and evaluated over a 20-year horizon, followed by robustness analysis to assess policy stability. Results show that reward functions lead to differentiated intervention strategies, influenced by the planning objective. Cost- and emissions-oriented rewards generate reactive policies, recommending intervention only when inaction would significantly increase maintenance and rehabilitation costs. In contrast, rewards focused on user savings or technical effectiveness promote proactive continuous maintenance to preserve surface conditions and reduce indirect user costs. The proposed approach underscores the critical role of reward definition in reinforcement learning and provides a practical tool to support adaptive, sustainable, and long-term pavement management.
publishDate 2026
dc.date.none.fl_str_mv 2026
2026-12-31
2026
2026-04-16
2027
2027-12-31
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://riunet.upv.es/handle/10251/234367
url https://riunet.upv.es/handle/10251/234367
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2022-141875OA-I00 REINFORCEMENT LEARNING ADAPTADO AL MANTENIMIENTO RESILIENTE DE CARRETERAS FRENTE AL CAMBIO CLIMATICO
dc.rights.none.fl_str_mv embargoed access
http://purl.org/coar/access_right/c_f1cf
Reserva de todos los derechos
http://rightsstatements.org/vocab/InC/1.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/embargoedAccess
rights_invalid_str_mv embargoed access
http://purl.org/coar/access_right/c_f1cf
Reserva de todos los derechos
http://rightsstatements.org/vocab/InC/1.0/
eu_rights_str_mv embargoedAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Taylor & Francis
publisher.none.fl_str_mv Taylor & Francis
dc.source.none.fl_str_mv reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname:Universitat Politècnica de València (UPV)
instname_str Universitat Politècnica de València (UPV)
reponame_str RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
collection RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407508025573376
score 15.812429

Similar Items