- -

Reinforcement learning applied to production planning and control

RiuNet: Repositorio Institucional de la Universidad Politécnica de Valencia

Compartir/Enviar a

Citas

Estadísticas

  • Estadisticas de Uso

Reinforcement learning applied to production planning and control

Mostrar el registro sencillo del ítem

Ficheros en el ítem

dc.contributor.author Esteso, Ana es_ES
dc.contributor.author Peidro Payá, David es_ES
dc.contributor.author Mula, Josefa es_ES
dc.contributor.author Díaz-Madroñero Boluda, Francisco Manuel es_ES
dc.date.accessioned 2023-09-21T18:06:26Z
dc.date.available 2023-09-21T18:06:26Z
dc.date.issued 2023-08-18 es_ES
dc.identifier.issn 0020-7543 es_ES
dc.identifier.uri http://hdl.handle.net/10251/196934
dc.description.abstract [EN] The objective of this paper is to examine the use and applications of reinforcement learning (RL) techniques in the production planning and control (PPC) field addressing the following PPC areas: facility resource planning, capacity planning, purchase and supply management, production scheduling and inventory management. The main RL characteristics, such as method, context, states, actions, reward and highlights, were analysed. The considered number of agents, applications and RL software tools, specifically, programming language, platforms, application programming interfaces and RL frameworks, among others, were identified, and 181 articles were sreviewed. The results showed that RL was applied mainly to production scheduling problems, followed by purchase and supply management. The most revised RL algorithms were model-free and single-agent and were applied to simplified PPC environments. Nevertheless, their results seem to be promising compared to traditional mathematical programming and heuristics/metaheuristics solution methods, and even more so when they incorporate uncertainty or non-linear properties. Finally, RL value-based approaches are the most widely used, specifically Q-learning and its variants and for deep RL, deep Q-networks. In recent years however, the most widely used approach has been the actor-critic method, such as the advantage actor critic, proximal policy optimisation, deep deterministic policy gradient and trust region policy optimisation. es_ES
dc.description.sponsorship The funding for the research work that has led to the obtained results came from the following grants: CADS4.0 (Ref. RTI2018-101344-B-I00) and NIOTOME (Ref. RTI2018102020-B-I00), financed byMCIN/AEI/10.13039/501100011033 and 'ERDF A way of making DEurope'; the EU H2020 research and innovation programme with grant numbers 825631 'Zero-Defect Manufacturing Platform (ZDMP)' and 958205 'Industrial Data Services for Quality Control in SmartManufacturing (i4Q)'; 'Industrial Production and Logistics Optimization in Industry 4.0' (i4OPT) (Ref. PROMETEO/2021/065) and 'Resilient, Sustainable and PeopleOriented Supply Chain 5.0 Optimization Using Hybrid Intelligence' (RESPECT) (Ref. CIGE/2021/159) Projects were funded by the Generalitat Valenciana (Valencian Regional Government). es_ES
dc.language Inglés es_ES
dc.publisher Taylor & Francis es_ES
dc.relation.ispartof International Journal of Production Research es_ES
dc.rights Reconocimiento - No comercial - Sin obra derivada (by-nc-nd) es_ES
dc.subject Artificial intelligence es_ES
dc.subject Machine learning es_ES
dc.subject Reinforcement learning es_ES
dc.subject Deep reinforcement learning es_ES
dc.subject Production planning and control es_ES
dc.subject Industry 4.0 es_ES
dc.subject.classification ORGANIZACION DE EMPRESAS es_ES
dc.title Reinforcement learning applied to production planning and control es_ES
dc.type Artículo es_ES
dc.identifier.doi 10.1080/00207543.2022.2104180 es_ES
dc.relation.projectID info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/RTI2018-101344-B-I00/ES/OPTIMIZACION DE TECNOLOGIAS DE PRODUCCION CERO-DEFECTOS HABILITADORAS PARA CADENAS DE SUMINISTRO 4.0/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/GENERALITAT VALENCIANA//PROMETEO%2F2021%2F065//Industrial Production and Logistics Optimization in Industry 4.0 (i4OPT) / es_ES
dc.relation.projectID info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/RTI2018-102020-B-I00/ES/INTEGRACION DE LA TOMA DE DECISIONES DE LOS NIVELES TACTICO-OPERATIVO PARA LA MEJORA DE LA EFICIENCIA DEL SISTEMA DE PRODUCTIVO EN ENTORNOS INDUSTRIA 4.0/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/GENERALITAT VALENCIANA//CIGE%2F2021%2F159//Optimización de cadenas de suministro 5.0 resilientes, sostenibles y orientadas a personas mediante inteligencia híbrida/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/825631/EU es_ES
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/958205/EU es_ES
dc.rights.accessRights Abierto es_ES
dc.contributor.affiliation Universitat Politècnica de València. Escuela Técnica Superior de Ingenieros Industriales - Escola Tècnica Superior d'Enginyers Industrials es_ES
dc.contributor.affiliation Universitat Politècnica de València. Escuela Politécnica Superior de Alcoy - Escola Politècnica Superior d'Alcoi es_ES
dc.description.bibliographicCitation Esteso, A.; Peidro Payá, D.; Mula, J.; Díaz-Madroñero Boluda, FM. (2023). Reinforcement learning applied to production planning and control. International Journal of Production Research. 61(16):5772-5789. https://doi.org/10.1080/00207543.2022.2104180 es_ES
dc.description.accrualMethod S es_ES
dc.relation.publisherversion https://doi.org/10.1080/00207543.2022.2104180 es_ES
dc.description.upvformatpinicio 5772 es_ES
dc.description.upvformatpfin 5789 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.description.volume 61 es_ES
dc.description.issue 16 es_ES
dc.relation.pasarela S\472042 es_ES
dc.contributor.funder GENERALITAT VALENCIANA es_ES
dc.contributor.funder AGENCIA ESTATAL DE INVESTIGACION es_ES
dc.contributor.funder European Regional Development Fund es_ES
dc.contributor.funder COMISION DE LAS COMUNIDADES EUROPEA es_ES
dc.subject.ods 09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación es_ES
upv.costeAPC 3085,5 es_ES


Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem