{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:08:22Z","timestamp":1784218102876,"version":"3.55.0"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72072029"],"award-info":[{"award-number":["72072029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72192830"],"award-info":[{"award-number":["72192830"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72192831"],"award-info":[{"award-number":["72192831"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["B16009"],"award-info":[{"award-number":["B16009"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.asoc.2026.115534","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T15:18:11Z","timestamp":1779376691000},"page":"115534","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Solving multi-objective production inventory control problems with reinforcement learning aided by differential evolution"],"prefix":"10.1016","volume":"201","author":[{"given":"Lue","family":"Tao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1766-0630","authenticated-orcid":false,"given":"Gongshu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9600-0229","authenticated-orcid":false,"given":"Lijie","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4540-0908","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115534_bib1","doi-asserted-by":"crossref","first-page":"1025","DOI":"10.1007\/s10845-020-01601-1","article-title":"Computer aided manufacturing method for surface silicon steel inspection based on an efficient anisotropic diffusion algorithm","volume":"32","author":"Ben Gharsallah","year":"2021","journal-title":"J. Intell. Manuf."},{"key":"10.1016\/j.asoc.2026.115534_bib2","first-page":"204","article-title":"A single-vendor multi-buyer integrated production-inventory system with stock-dependent demand","volume":"5","author":"Omar","year":"2018","journal-title":"Int. J. Syst. Sci. -Oper. Logist."},{"key":"10.1016\/j.asoc.2026.115534_bib3","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2022.106080","article-title":"Implications on managing inventory systems for products with stock-dependent demand and nonlinear holding cost via the adaptive EOQ policy","volume":"150","author":"Guo","year":"2023","journal-title":"Comput. Oper. Res."},{"key":"10.1016\/j.asoc.2026.115534_bib4","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1051\/ro\/2013058","article-title":"Production-inventory system with finite production rate, stock-dependent demand, and variable holding cost","volume":"48","author":"Alfares","year":"2014","journal-title":"RAIRO-Oper. Res."},{"key":"10.1016\/j.asoc.2026.115534_bib5","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1080\/00207720802088272","article-title":"A perishable inventory model under stock-dependent selling rate and shortage-dependent partial backlogging with capacity constraint","volume":"40","author":"Min","year":"2009","journal-title":"Int. J. Syst. Sci."},{"key":"10.1016\/j.asoc.2026.115534_bib6","doi-asserted-by":"crossref","first-page":"2203","DOI":"10.1007\/s10845-017-1383-6","article-title":"Optimal control model for finite capacity continuous MRP with deteriorating items","volume":"30","author":"Pooya","year":"2019","journal-title":"J. Intell. Manuf."},{"key":"10.1016\/j.asoc.2026.115534_bib7","first-page":"34","article-title":"Periodic review policy in the production management of a single-item inventory with deterioration","volume":"24","author":"Dey","year":"2024","journal-title":"Oper. Res."},{"key":"10.1016\/j.asoc.2026.115534_bib8","doi-asserted-by":"crossref","first-page":"5523","DOI":"10.1080\/00207543.2021.1963876","article-title":"Linear-quadratic optimal control of multi-modal distribution systems with imperfect channels","volume":"60","author":"Ignaciuk","year":"2022","journal-title":"Int. J. Prod. Res."},{"key":"10.1016\/j.asoc.2026.115534_bib9","doi-asserted-by":"crossref","first-page":"5064","DOI":"10.1109\/TNNLS.2022.3207346","article-title":"Deep Reinforcement Learning: A Survey","volume":"35","author":"Wang","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.asoc.2026.115534_bib10","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106785","article-title":"Optimal model-free adaptive control based on reinforcement Q-Learning for solar thermal collector fields","volume":"126","author":"Pataro","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.asoc.2026.115534_bib11","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.isatra.2022.08.024","article-title":"Linear quadratic regulator design via metaheuristics applied to the damping of low-frequency oscillations in power systems","volume":"134","author":"Carvalho","year":"2023","journal-title":"ISA Trans."},{"key":"10.1016\/j.asoc.2026.115534_bib12","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2022.109450","article-title":"Reinforcement learning based adaptive PID controller design for control of linear\/nonlinear unstable processes","volume":"128","author":"Shuprajhaa","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2026.115534_bib13","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1057\/palgrave.jors.2602335","article-title":"Raw material inventory solution in iron and steel industry using Lagrangian relaxation","volume":"59","author":"Tang","year":"2008","journal-title":"J. Oper. Res. Soc."},{"key":"10.1016\/j.asoc.2026.115534_bib14","doi-asserted-by":"crossref","DOI":"10.3390\/math7080718","article-title":"Data-driven iron and steel inventory control policies","volume":"7","author":"Tseng","year":"2019","journal-title":"Mathematics"},{"key":"10.1016\/j.asoc.2026.115534_bib15","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1287\/inte.2021.1073","article-title":"Seasonal inventory management model for raw materials in steel industry","volume":"51","author":"Kawakami","year":"2021","journal-title":"INFORMS J. Appl. Anal."},{"key":"10.1016\/j.asoc.2026.115534_bib16","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.ijpe.2004.06.018","article-title":"Model and analysis of integrated production-inventory system: The case of steel production","volume":"93\u201394","author":"Zanoni","year":"2005","journal-title":"Int. J. Prod. Econ."},{"key":"10.1016\/j.asoc.2026.115534_bib17","series-title":"Proceedings of the World Congress on Engineering","first-page":"791","article-title":"Model of integrated production-inventory-distribution system: The case of billet steel manufacturing","author":"Moengin","year":"2015"},{"key":"10.1016\/j.asoc.2026.115534_bib18","doi-asserted-by":"crossref","first-page":"2037","DOI":"10.1016\/j.cjche.2015.10.003","article-title":"Modeling and optimization methods of integrated production planning for steel plate mill with flexible customization","volume":"23","author":"Lu","year":"2015","journal-title":"Chin. J. Chem. Eng."},{"key":"10.1016\/j.asoc.2026.115534_bib19","doi-asserted-by":"crossref","first-page":"4264","DOI":"10.1080\/00207543.2017.1413257","article-title":"Robust policies for a multi-stage production\/inventory problem with switching costs and uncertain demand","volume":"56","author":"Cheng","year":"2018","journal-title":"Int. J. Prod. Res."},{"key":"10.1016\/j.asoc.2026.115534_bib20","doi-asserted-by":"crossref","first-page":"1343","DOI":"10.1007\/s12613-021-2310-6","article-title":"Multiproduct and multistage integrated production planning model and algorithm based on an available production capacity network","volume":"28","author":"L\u00fc","year":"2021","journal-title":"Int. J. Miner. Metall. Mater."},{"key":"10.1016\/j.asoc.2026.115534_bib21","first-page":"186","article-title":"An integrated optimization model of production plan in a large steel manufacturing company","volume":"38","author":"Rosyidi","year":"2021","journal-title":"J. Ind. Prod. Eng."},{"key":"10.1016\/j.asoc.2026.115534_bib22","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2020.106606","article-title":"A review of planning and scheduling methods for hot rolling mills in steel production","volume":"151","author":"\u00d6zg\u00fcr","year":"2021","journal-title":"Comput. & Ind. Eng."},{"key":"10.1016\/j.asoc.2026.115534_bib23","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1007\/s00170-017-0942-5","article-title":"A delayed optimal control model for multi-stage production-inventory system with production lead times","volume":"94","author":"Pooya","year":"2018","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"10.1016\/j.asoc.2026.115534_bib24","doi-asserted-by":"crossref","first-page":"1982","DOI":"10.1016\/j.automatica.2010.09.010","article-title":"Linear-quadratic optimal control strategy for periodic-review inventory systems","volume":"46","author":"Ignaciuk","year":"2010","journal-title":"Automatica"},{"key":"10.1016\/j.asoc.2026.115534_bib25","doi-asserted-by":"crossref","first-page":"2108","DOI":"10.1109\/TAC.2013.2246093","article-title":"LQ optimal and robust control of perishable inventory systems with multiple supply options","volume":"58","author":"Ignaciuk","year":"2013","journal-title":"IEEE Trans. Autom. Control"},{"key":"10.1016\/j.asoc.2026.115534_bib26","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/S0377-2217(97)00327-5","article-title":"Optimal control of a divergent multi-echelon inventory system","volume":"111","author":"Diks","year":"1998","journal-title":"Eur. J. Oper. Res."},{"key":"10.1016\/j.asoc.2026.115534_bib27","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1109\/TSMC.2014.2347012","article-title":"Discrete-time control of production-inventory systems with deteriorating stock and unreliable supplies","volume":"45","author":"Ignaciuk","year":"2015","journal-title":"IEEE Trans. Syst. Man Cybern. -Syst."},{"key":"10.1016\/j.asoc.2026.115534_bib28","doi-asserted-by":"crossref","first-page":"1167","DOI":"10.1016\/j.automatica.2014.02.015","article-title":"Reinforcement Q-learning for optimal tracking control of linear discrete-time systems with unknown dynamics","volume":"50","author":"Kiumarsi","year":"2014","journal-title":"Automatica"},{"key":"10.1016\/j.asoc.2026.115534_bib29","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1109\/TNNLS.2014.2358227","article-title":"Actor-critic-based optimal tracking for partially unknown nonlinear discrete-time systems","volume":"26","author":"Kiumarsi","year":"2015","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.asoc.2026.115534_bib30","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2022.109347","article-title":"Using Hill Climb Modular Assembler Encoding and Differential Evolution to evolve modular neuro-controllers of an autonomous underwater vehicle acting as a Magnetic Anomaly Detector","volume":"127","author":"Praczyk","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2026.115534_bib31","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2023.111116","article-title":"Metaheuristic adaptive control based on polynomial regression and differential evolution for robotic manipulators","volume":"151","author":"Rodr\u00edguez-Molina","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2026.115534_bib32","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2024.132888","article-title":"A multi-objective co-optimization method of controller parameters for the overall system of small pressurized water reactor","volume":"308","author":"Li","year":"2024","journal-title":"Energy"},{"key":"10.1016\/j.asoc.2026.115534_bib33","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2023.e19381","article-title":"Multi-objective control optimization of isolated bridge using replicator controller and NSGA-II","volume":"9","author":"Momeni","year":"2023","journal-title":"Heliyon"},{"key":"10.1016\/j.asoc.2026.115534_bib34","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2022.108944","article-title":"Data-based variable universe adaptive fuzzy controller with self-tuning parameters","volume":"123","author":"Jin","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2026.115534_bib35","doi-asserted-by":"crossref","first-page":"18330","DOI":"10.1109\/ACCESS.2022.3149951","article-title":"A. Ma\u2019Arif, Improved LQR Control Using PSO Optimization and Kalman Filter Estimator","volume":"10","author":"Maghfiroh","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.asoc.2026.115534_bib36","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2020.106342","article-title":"Multi-objective meta-heuristic optimization in intelligent control: A survey on the controller tuning problem","volume":"93","author":"Rodr\u00edguez-Molina","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2026.115534_bib37","doi-asserted-by":"crossref","first-page":"3283","DOI":"10.1007\/s00521-021-06608-0","article-title":"Tuning of LQR-PID controller to control parallel manipulator","volume":"34","author":"Choubey","year":"2022","journal-title":"Neural Comput. & Appl."},{"key":"10.1016\/j.asoc.2026.115534_bib38","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1016\/j.epsr.2017.08.004","article-title":"GA-based robust LQR controller for interleaved boost DC\u2013DC converter improving fuel cell voltage regulation","volume":"152","author":"Habib","year":"2017","journal-title":"Electr. Power Syst. Res."},{"key":"10.1016\/j.asoc.2026.115534_bib39","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.asoc.2015.12.024","article-title":"Multi-objective design of state feedback controllers using reinforced quantum-behaved particle swarm optimization","volume":"41","author":"Hassani","year":"2016","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2026.115534_bib40","doi-asserted-by":"crossref","first-page":"1267","DOI":"10.1007\/s00170-013-5358-2","article-title":"A dynamic multi-commodity inventory and facility location problem in steel supply chain network design","volume":"70","author":"Sabzevari Zadeh","year":"2014","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"10.1016\/j.asoc.2026.115534_bib41","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1016\/j.automatica.2006.09.019","article-title":"Model-free Q-learning designs for linear discrete-time zero-sum games with application to H-infinity control","volume":"43","author":"Al-Tamimi","year":"2007","journal-title":"Automatica"},{"key":"10.1016\/j.asoc.2026.115534_bib42","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1109\/TEVC.2014.2360890","article-title":"Differential Evolution with an Individual-Dependent Mechanism","volume":"19","author":"Tang","year":"2015","journal-title":"IEEE Trans. Evolut. Comput."},{"key":"10.1016\/j.asoc.2026.115534_bib43","doi-asserted-by":"crossref","first-page":"1478","DOI":"10.1109\/TASE.2020.3019694","article-title":"An Estimation of Distribution Algorithm with Filtering and Learning","volume":"18","author":"Tang","year":"2021","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.asoc.2026.115534_bib44","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1109\/4235.996017","article-title":"A fast and elitist multiobjective genetic algorithm: NSGA-II","volume":"6","author":"Deb","year":"2002","journal-title":"IEEE Trans. Evolut. Comput."},{"key":"10.1016\/j.asoc.2026.115534_bib45","first-page":"520","article-title":"DEMO: Differential Evolution for Multiobjective Optimization","volume":"3410","author":"Robi\u010d","year":"2005"},{"key":"10.1016\/j.asoc.2026.115534_bib46","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1109\/TEVC.2018.2866854","article-title":"A Strengthened Dominance Relation Considering Convergence and Diversity for Evolutionary Many-Objective Optimization","volume":"23","author":"Tian","year":"2019","journal-title":"IEEE Trans. Evolut. Comput."},{"key":"10.1016\/j.asoc.2026.115534_bib47","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1109\/TEVC.2007.892759","article-title":"MOEA\/D: A multiobjective evolutionary algorithm based on decomposition","volume":"11","author":"Zhang","year":"2007","journal-title":"IEEE Trans. Evolut. Comput."},{"key":"10.1016\/j.asoc.2026.115534_bib48","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1109\/TEVC.2016.2519378","article-title":"A Reference Vector Guided Evolutionary Algorithm for Many-Objective Optimization","volume":"20","author":"Cheng","year":"2016","journal-title":"IEEE Trans. Evolut. Comput."},{"key":"10.1016\/j.asoc.2026.115534_bib49","series-title":"2013 IEEE Congress on Evolutionary Computation","first-page":"2758","article-title":"Use of cooperative coevolution for solving large scale multiobjective optimization problems","author":"Antonio","year":"2013"},{"key":"10.1016\/j.asoc.2026.115534_bib50","doi-asserted-by":"crossref","first-page":"732","DOI":"10.1016\/j.ejor.2015.06.071","article-title":"A novel multi-objective particle swarm optimization with multiple search strategies","volume":"247","author":"Lin","year":"2015","journal-title":"Eur. J. Oper. Res."}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626009828?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626009828?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:53:45Z","timestamp":1784217225000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626009828"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":50,"alternative-id":["S1568494626009828"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115534","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Solving multi-objective production inventory control problems with reinforcement learning aided by differential evolution","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115534","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115534"}}