{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T11:46:14Z","timestamp":1787312774705,"version":"build-2736575974"},"reference-count":59,"publisher":"Informa UK Limited","issue":"6","license":[{"start":{"date-parts":[[2022,4,7]],"date-time":"2022-04-07T00:00:00Z","timestamp":1649289600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Production Research"],"published-print":{"date-parts":[[2023,3,19]]},"DOI":"10.1080\/00207543.2022.2056540","type":"journal-article","created":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T03:00:48Z","timestamp":1649386848000},"page":"1955-1978","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":41,"title":["Using the proximal policy optimisation algorithm for solving the stochastic capacitated lot sizing problem"],"prefix":"10.1080","volume":"61","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8434-5505","authenticated-orcid":false,"given":"Lotte","family":"van Hezewijk","sequence":"first","affiliation":[{"name":"Department of Industrial Engineering and Innovation Sciences, Eindhoven University of Technology, Eindhoven, Netherlands"},{"name":"ORTEC B.V., Zoetermeer, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2343-7574","authenticated-orcid":false,"given":"Nico","family":"Dellaert","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and Innovation Sciences, Eindhoven University of Technology, Eindhoven, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4766-2346","authenticated-orcid":false,"given":"Tom","family":"Van Woensel","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and Innovation Sciences, Eindhoven University of Technology, Eindhoven, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1546-2879","authenticated-orcid":false,"given":"Noud","family":"Gademann","sequence":"additional","affiliation":[{"name":"ORTEC B.V., Zoetermeer, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2022,4,7]]},"reference":[{"key":"CIT0001","doi-asserted-by":"publisher","DOI":"10.2307\/1906813"},{"key":"CIT0002","doi-asserted-by":"publisher","DOI":"10.1016\/S0927-0507(05)80184-7"},{"key":"CIT0003","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-5915.1977.tb01065.x"},{"key":"CIT0004","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1954-09848-8"},{"key":"CIT0005","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.34.9.1096"},{"key":"CIT0006","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2021.07.016"},{"key":"CIT0007","doi-asserted-by":"publisher","DOI":"10.1080\/00207540500435116"},{"key":"CIT0008","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2018.09.005"},{"key":"CIT0009","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2008.03.007"},{"key":"CIT0010","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.44.7.950"},{"key":"CIT0011","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1736722"},{"key":"CIT0012","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1090.1141"},{"key":"CIT0013","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.35.7.898"},{"key":"CIT0014","doi-asserted-by":"publisher","DOI":"10.1287\/opre.32.6.1268"},{"key":"CIT0015","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-5273(00)00156-0"},{"key":"CIT0016","author":"Gijsbrechts Joren","year":"2021","journal-title":"Manufacturing & Service Operations Management"},{"key":"CIT0017","first-page":"249","volume":"9","author":"Glorot Xavier","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"CIT0018","volume-title":"Deep Learning","author":"Goodfellow Ian","year":"2016"},{"key":"CIT0019","doi-asserted-by":"publisher","DOI":"10.1007\/s00291-005-0018-z"},{"key":"CIT0020","first-page":"67","volume":"1","author":"Graves Stephen C.","year":"1988","journal-title":"Journal of Manufacturing and Operations Management"},{"key":"CIT0021","doi-asserted-by":"publisher","DOI":"10.1287\/msom.2.1.68.23267"},{"key":"CIT0022","doi-asserted-by":"publisher","DOI":"10.1007\/s00291-012-0283-6"},{"key":"CIT0023","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106685"},{"key":"CIT0024","doi-asserted-by":"publisher","DOI":"10.1080\/00207540600902262"},{"key":"CIT0025","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.07.036"},{"key":"CIT0026","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.08.046"},{"key":"CIT0027","doi-asserted-by":"publisher","DOI":"10.1016\/S0305-0483(03)00059-8"},{"key":"CIT0028","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-004-2069-8"},{"key":"CIT0029","unstructured":"Kingma, Diederik P., and Jimmy Ba. 2014. \u201cAdam: A Method for Stochastic Optimization.\u201d Preprint arXiv:1412.6980."},{"key":"CIT0030","unstructured":"Kool, Wouter, Herke van Hoof, and Max Welling. 2019. \u201cAttention, Learn to Solve Routing Problems!,\u201d 1\u201325. Preprint arXiv:1803.08475v3."},{"key":"CIT0031","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2007.07.002"},{"issue":"10","key":"CIT0032","first-page":"102","volume":"82","author":"Lee Hau L.","year":"2004","journal-title":"Harvard Business Review"},{"key":"CIT0033","doi-asserted-by":"publisher","DOI":"10.17265\/2159-5313\/2016.09.003"},{"key":"CIT0034","unstructured":"Mnih, Volodymyr, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. \u201cPlaying Atari with Deep Reinforcement Learning,\u201d 1\u20139. Preprint arXiv:1312.5602."},{"key":"CIT0035","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"CIT0036","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpe.2005.09.001"},{"key":"CIT0037","first-page":"198","volume-title":"Production and Operations Analysis","author":"Nahmias Steven","year":"2015","edition":"7"},{"key":"CIT0038","first-page":"249","volume-title":"Production and Operations Analysis","author":"Nahmias Steven","year":"2015","edition":"7"},{"key":"CIT0039","unstructured":"Oroojlooyjadid, Afshin, Mohammad Reza Nazari, Lawrence V. Snyder, and Martin Tak\u00e1\u010d. 2017. \u201cA Deep Q-Network for the Beer Game: Reinforcement Learning for Inventory Optimization.\u201d Preprint arXiv:1708.05924v3."},{"key":"CIT0040","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1870013"},{"key":"CIT0041","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2004.12.003"},{"key":"CIT0042","doi-asserted-by":"publisher","DOI":"10.1080\/00207540110118640"},{"key":"CIT0043","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"CIT0044","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.11.397"},{"key":"CIT0045","author":"Schulman John","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning"},{"key":"CIT0046","author":"Schulman John","year":"2016","journal-title":"Conference Track Proceedings of the 4th International Conference on Learning Representations"},{"key":"CIT0047","unstructured":"Schulman, John, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. \u201cProximal Policy Optimization Algorithms.\u201d Preprint arXiv:1707.06347, 1\u201312."},{"key":"CIT0048","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"CIT0049","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton Richard S.","year":"2018"},{"key":"CIT0050","first-page":"1000","volume":"23","author":"Tang Jie","year":"2010","journal-title":"Advances in Neural Information Processing Systems"},{"key":"CIT0051","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1773003"},{"key":"CIT0052","volume-title":"Inventory Management in Supply Networks: Problems, Models, Solutions","author":"Tempelmeier Horst.","year":"2006"},{"key":"CIT0053","doi-asserted-by":"publisher","DOI":"10.1016\/j.omega.2011.01.003"},{"key":"CIT0054","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6777-9_10"},{"key":"CIT0055","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2015.01.007"},{"key":"CIT0056","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2020.103239"},{"key":"CIT0057","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2011.592158"},{"key":"CIT0058","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2010.06.011"},{"key":"CIT0059","unstructured":"Zahavy, Tom, Matan Haroush, Nadav Merlis, Daniel J. Mankowitz, and Shie Mannor. 2018. \u201cLearn What Not to Learn: Action Elimination with Deep Reinforcement Learning.\u201d Preprint arXiv:1809.02121, 1\u201312."}],"container-title":["International Journal of Production Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207543.2022.2056540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T04:57:11Z","timestamp":1678078631000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207543.2022.2056540"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,7]]},"references-count":59,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,3,19]]}},"alternative-id":["10.1080\/00207543.2022.2056540"],"URL":"https:\/\/doi.org\/10.1080\/00207543.2022.2056540","relation":{},"ISSN":["0020-7543","1366-588X"],"issn-type":[{"value":"0020-7543","type":"print"},{"value":"1366-588X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,7]]},"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":"2021-03-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}