{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T22:34:47Z","timestamp":1792794887332,"version":"4.5.0"},"reference-count":53,"publisher":"Informa UK Limited","issue":"5","license":[{"start":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:00:00Z","timestamp":1722902400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003359","name":"Valencian Regional Government","doi-asserted-by":"publisher","award":["PROMETEO\/2021\/065"],"award-info":[{"award-number":["PROMETEO\/2021\/065"]}],"id":[{"id":"10.13039\/501100003359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"MCIN","doi-asserted-by":"publisher","award":["PDC2022-133957-I00"],"award-info":[{"award-number":["PDC2022-133957-I00"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Production Research"],"published-print":{"date-parts":[[2025,3,4]]},"DOI":"10.1080\/00207543.2024.2383293","type":"journal-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T04:02:58Z","timestamp":1723003378000},"page":"1649-1673","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":22,"title":["Optimisation of recovery policies in the era of supply chain disruptions: a system dynamics and reinforcement learning approach"],"prefix":"10.1080","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9851-5350","authenticated-orcid":false,"given":"Fabian","family":"Bussieweke","sequence":"first","affiliation":[{"name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","place":["Alcoy, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8447-3387","authenticated-orcid":false,"given":"Josefa","family":"Mula","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","place":["Alcoy, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1141-5810","authenticated-orcid":false,"given":"Francisco","family":"Campuzano-Bolarin","sequence":"additional","affiliation":[{"name":"Universidad Polit\u00e9cnica de Cartagena","place":["Cartagena, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2024,8,6]]},"reference":[{"key":"e_1_3_3_2_1","unstructured":"Alves J. C. and G. R. Mateus. 2022. \u201cMulti-Echelon Supply Chains with Uncertain Seasonal Demands and Lead Times Using Deep Reinforcement Learning.\u201d arXiv preprint arXiv:2201.04651."},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1108\/IMDS-05-2015-0215"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207540902960299"},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-85729-719-8"},{"key":"e_1_3_3_6_1","doi-asserted-by":"crossref","unstructured":"Degris T. P. M. Pilarski and R. S. Sutton. 2012. \u201cModel-Free Reinforcement Learning with Continuous Action in Practice.\u201d In 2012 American Control Conference (ACC) 2177\u20132182. IEEE.","DOI":"10.1109\/ACC.2012.6315022"},{"key":"e_1_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2017.1387680"},{"key":"e_1_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.21608\/jesaun.2010.124377"},{"key":"e_1_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2104180"},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/sys.21718"},{"key":"e_1_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1987547"},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10669-020-09777-w"},{"key":"e_1_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1080\/19397038.2016.1250838"},{"key":"e_1_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-022-09552-y"},{"key":"e_1_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2019.02.023"},{"key":"e_1_3_3_16_1","unstructured":"Hubbs C. D. H. D. Perez O. Sarwar N. V. Sahinidis I. E. Grossmann and J. M. Wassick. 2020. \u201cOr-Gym: A Reinforcement Learning Library for Operations Research Problems.\u201d arXiv preprint arXiv:2008.06319."},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2016.1275873"},{"key":"e_1_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2018.10.043"},{"key":"e_1_3_3_19_1","doi-asserted-by":"crossref","unstructured":"Ivanov D. A. Dolgui A. Das and B. Sokolov. 2019. \u201cDigital Supply Chain Twins: Managing the Ripple Effect Resilience and Disruption Risks by Data-Driven Optimization Simulation and Visibility.\u201d In Handbook of Ripple Effects in the Supply Chain 309\u2013332. Cham Switzerland: Springer.","DOI":"10.1007\/978-3-030-14302-2_15"},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2017.1330572"},{"key":"e_1_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2016.1161253"},{"key":"e_1_3_3_22_1","doi-asserted-by":"crossref","unstructured":"Jaenichen F.-M. C. J. Liepold A. Ismail C. J. Martens V. D\u00f6rrsam and H. Ehm. 2021. \u201cSimulating and Evaluating Supply Chain Disruptions Along an End-To-End Semiconductor Automotive Supply Chain.\u201d In 2021 Winter Simulation Conference (WSC) 1\u201312. IEEE.","DOI":"10.1109\/WSC52266.2021.9715436"},{"key":"e_1_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1108\/JM2-11-2018-0195"},{"key":"e_1_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-020-03912-1"},{"key":"e_1_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/a14080240"},{"key":"e_1_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/asmb.2723"},{"key":"e_1_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpe.2020.107693"},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1841318"},{"key":"e_1_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.09.596"},{"key":"e_1_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1877842"},{"key":"e_1_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss"},{"key":"e_1_3_3_32_1","unstructured":"Mnih V. A. P. Badia M. Mirza A. Graves T. Lillicrap T. Harley D. Silver and K. Kavukcuoglu. 2016. \u201cAsynchronous Methods for Deep Reinforcement Learning.\u201d In International Conference on Machine Learning 1928\u20131937. PMLR."},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"e_1_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2014.09.004"},{"key":"e_1_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1725171"},{"key":"e_1_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1287\/msom.2020.0939"},{"key":"e_1_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.3390\/pr9010102"},{"issue":"1","key":"e_1_3_3_38_1","first-page":"12348","article-title":"Stable-Baselines3: Reliable Reinforcement Learning Implementations","volume":"22","author":"Raffin A.","year":"2021","unstructured":"Raffin, A., A. Hill, A. Gleave, A. Kanervisto, M. Ernestus, and N. Dormann. 2021. \u201cStable-Baselines3: Reliable Reinforcement Learning Implementations.\u201d The Journal of Machine Learning Research 22 (1): 12348\u201312355.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_3_39_1","unstructured":"Rahmandad H. and S. Fallah-Fini. 2008. \u201cLearning Control Policies in System Dynamics Models.\u201d Systemdynamics.Org."},{"key":"e_1_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2140221"},{"key":"e_1_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.omega.2016.07.004"},{"key":"e_1_3_3_42_1","unstructured":"Schulman J. F. Wolski P. Dhariwal A. Radford and O. Klimov. 2017. \u201cProximal Policy Optimization Algorithms.\u201d arXiv preprint arXiv:1707.06347."},{"key":"e_1_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1177\/0015732520947904"},{"key":"e_1_3_3_44_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton R. S.","year":"2018","unstructured":"Sutton, R. S., and A. G. Barto. 2018. Reinforcement Learning: An Introduction. Cambridge, MA: MIT press."},{"key":"e_1_3_3_45_1","first-page":"1057","article-title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation","volume":"12","author":"Sutton R. S.","year":"1999","unstructured":"Sutton, R. S., D. McAllester, S. Singh, and Y. Mansour. 1999. \u201cPolicy Gradient Methods for Reinforcement Learning with Function Approximation.\u201d Advances in Neural Information Processing Systems 12: 1057\u20131063.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"e_1_3_3_46_1","first-page":"30","article-title":"The Real Cost of Holding Inventory","volume":"7","author":"Timme S. G.","year":"2003","unstructured":"Timme, S. G., and C. Williams-Timme. 2003. \u201cThe Real Cost of Holding Inventory.\u201d Supply Chain Management Review 7 (4): 30\u201337. (July\/August 2003), ILL.","journal-title":"Supply Chain Management Review"},{"key":"e_1_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2020.102166"},{"key":"e_1_3_3_48_1","unstructured":"Wang T. X. Bao I. Clavera J. Hoang Y. Wen E. Langlois S. Zhang et\u00a0al. 2019. \u201cBenchmarking Model-Based Reinforcement Learning.\u201d arXiv preprint arXiv:1907.02057."},{"key":"e_1_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.2020927"},{"key":"e_1_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"e_1_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2022.102712"},{"key":"e_1_3_3_52_1","doi-asserted-by":"crossref","unstructured":"Zhang H. and T. Yu. 2020. \u201cTaxonomy of Reinforcement Learning Algorithms.\u201d In Deep Reinforcement Learning: Fundamentals Research and Applications 125\u2013133. Singapore.","DOI":"10.1007\/978-981-15-4095-0_3"},{"key":"e_1_3_3_53_1","doi-asserted-by":"crossref","unstructured":"Zhou J. and X. Zhou. 2019. \u201cMulti-Echelon Inventory Optimizations for Divergent Networks by Combining Deep Reinforcement Learning and Heuristics Improvement.\u201d In 2019 12th International Symposium on Computational Intelligence and Design (ISCID) Vol. 1 69\u201373. IEEE.","DOI":"10.1109\/ISCID.2019.00023"},{"key":"e_1_3_3_54_1","doi-asserted-by":"publisher","DOI":"10.3390\/logistics5020019"}],"container-title":["International Journal of Production Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207543.2024.2383293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T15:42:25Z","timestamp":1741016545000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207543.2024.2383293"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,6]]},"references-count":53,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,3,4]]}},"alternative-id":["10.1080\/00207543.2024.2383293"],"URL":"https:\/\/doi.org\/10.1080\/00207543.2024.2383293","relation":{},"ISSN":["0020-7543","1366-588X"],"issn-type":[{"value":"0020-7543","type":"print"},{"value":"1366-588X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,6]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tprs20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tprs20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2023-11-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}