{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:58:00Z","timestamp":1772906280330,"version":"3.50.1"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030858735","type":"print"},{"value":"9783030858742","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-85874-2_27","type":"book-chapter","created":{"date-parts":[[2021,8,31]],"date-time":"2021-08-31T17:02:37Z","timestamp":1630429357000},"page":"258-266","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Smart Short Term Capacity Planning: A Reinforcement Learning Approach"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4812-4665","authenticated-orcid":false,"given":"Manuel","family":"Schneckenreither","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastian","family":"Windmueller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2589-1367","authenticated-orcid":false,"given":"Stefan","family":"Haeussler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,31]]},"reference":[{"issue":"9\u201310","key":"27_CR1","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1016\/j.mcm.2009.07.010","volume":"50","author":"CS Chen","year":"2009","unstructured":"Chen, C.S., Mestry, S., Damodaran, P., Wang, C.: The capacity planning problem in make-to-order enterprises. Math. Comput. Model. 50(9\u201310), 1461\u20131473 (2009)","journal-title":"Math. Comput. Model."},{"issue":"4","key":"27_CR2","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1287\/mnsc.45.4.560","volume":"45","author":"TK Das","year":"1999","unstructured":"Das, T.K., Gosavi, A., Mahadevan, S., Marchalleck, N.: Solving semi-Markov decision problems using average reward reinforcement learning. Manag. Sci. 45(4), 560\u2013574 (1999)","journal-title":"Manag. Sci."},{"issue":"1","key":"27_CR3","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1080\/00207543.2011.571443","volume":"50","author":"T Gabel","year":"2012","unstructured":"Gabel, T., Riedmiller, M.: Distributed policy search reinforcement learning for job-shop scheduling tasks. Int. J. Prod. Res. 50(1), 41\u201361 (2012)","journal-title":"Int. J. Prod. Res."},{"issue":"12","key":"27_CR4","doi-asserted-by":"publisher","first-page":"3724","DOI":"10.1080\/00207543.2019.1634297","volume":"58","author":"S Haeussler","year":"2020","unstructured":"Haeussler, S., Netzer, P.: Comparison between rule-and optimization-based workload control concepts: a simulation optimization approach. Int. J. Prod. Res. 58(12), 3724\u20133743 (2020)","journal-title":"Int. J. Prod. Res."},{"issue":"13","key":"27_CR5","doi-asserted-by":"publisher","first-page":"1890","DOI":"10.1016\/j.ifacol.2019.11.478","volume":"52","author":"S Haeussler","year":"2019","unstructured":"Haeussler, S., Schneckenreither, M., Gerhold, C.: Adaptive order release planning with dynamic lead times. IFAC-PapersOnLine 52(13), 1890\u20131895 (2019)","journal-title":"IFAC-PapersOnLine"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Hessel, M., et al.: Rainbow: combining improvements in deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"27_CR7","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.cie.2017.03.012","volume":"107","author":"F Jaramillo","year":"2017","unstructured":"Jaramillo, F., Erkoc, M.: Minimizing total weighted tardiness and overtime costs for single machine preemptive scheduling. Comput. Ind. Eng. 107, 109\u2013119 (2017)","journal-title":"Comput. Ind. Eng."},{"key":"27_CR8","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"27_CR9","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1016\/j.procir.2019.02.101","volume":"79","author":"A Kuhnle","year":"2019","unstructured":"Kuhnle, A., R\u00f6hrig, N., Lanza, G.: Autonomous order dispatching in the semiconductor industry using reinforcement learning. Procedia CIRP 79, 391\u2013396 (2019). https:\/\/doi.org\/10.1016\/j.procir.2019.02.101. 12th CIRP Conference on Intelligent Computation in Manufacturing Engineering, 18-20 July 2018, Gulf of Naples, Italy","journal-title":"Procedia CIRP"},{"key":"27_CR10","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1016\/j.procir.2019.03.041","volume":"81","author":"A Kuhnle","year":"2019","unstructured":"Kuhnle, A., Sch\u00e4fer, L., Stricker, N., Lanza, G.: Design, implementation and evaluation of reinforcement learning for an adaptive order dispatching in job shop manufacturing systems. Procedia CIRP 81, 234\u2013239 (2019)","journal-title":"Procedia CIRP"},{"key":"27_CR11","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/j.ijpe.2015.07.007","volume":"168","author":"MJ Land","year":"2015","unstructured":"Land, M.J., Stevenson, M., Th\u00fcrer, M., Gaalman, G.J.: Job shop control: in search of the key to delivery improvements. Int. J. Prod. Econ. 168, 257\u2013266 (2015)","journal-title":"Int. J. Prod. Econ."},{"key":"27_CR12","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937. PMLR (2016)"},{"issue":"7540","key":"27_CR13","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"2","key":"27_CR14","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/S0925-5273(99)00098-5","volume":"69","author":"J Olhager","year":"2001","unstructured":"Olhager, J., Rudberg, M., Wikner, J.: Long-term capacity management: linking the perspectives from manufacturing strategy and sales and operations planning. Int. J. Prod. Econ. 69(2), 215\u2013225 (2001)","journal-title":"Int. J. Prod. Econ."},{"issue":"24","key":"27_CR15","doi-asserted-by":"publisher","first-page":"5363","DOI":"10.1080\/00207540600600106","volume":"44","author":"A Ornek","year":"2006","unstructured":"Ornek, A., Cengiz, O.: Capacitated lot sizing with alternative routings and overtime decisions. Int. J. Prod. Res. 44(24), 5363\u20135389 (2006)","journal-title":"Int. J. Prod. Res."},{"issue":"1","key":"27_CR16","first-page":"65","volume":"33","author":"CD Paternina-Arboleda","year":"2001","unstructured":"Paternina-Arboleda, C.D., Das, T.K.: Intelligent dynamic control policies for serial production lines. IIE Trans. 33(1), 65\u201377 (2001)","journal-title":"IIE Trans."},{"issue":"5","key":"27_CR17","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.simpat.2004.12.003","volume":"13","author":"CD Paternina-Arboleda","year":"2005","unstructured":"Paternina-Arboleda, C.D., Das, T.K.: A multi-agent reinforcement learning approach to obtaining dynamic control policies for stochastic lot scheduling problem. Simul. Model. Pract. Theory 13(5), 389\u2013406 (2005)","journal-title":"Simul. Model. Pract. Theory"},{"key":"27_CR18","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.procir.2016.11.011","volume":"57","author":"S Qu","year":"2016","unstructured":"Qu, S., Wang, J., Govil, S., Leckie, J.O.: Optimized adaptive scheduling of a manufacturing process system with multi-skill workforce and multiple machine types: an ontology-based, multi-agent reinforcement learning approach. Procedia CIRP 57, 55\u201360 (2016)","journal-title":"Procedia CIRP"},{"key":"27_CR19","volume-title":"Artificial Intelligence: A Modern Approach","author":"S Russell","year":"2002","unstructured":"Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice Hall, Upper Saddle River (2002)"},{"key":"27_CR20","unstructured":"Schneckenreither, M.: Average reward adjusted discounted reinforcement learning: near-blackwell-optimal policies for real-world applications. arXiv preprint arXiv:2004.00857 (2020)"},{"key":"27_CR21","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1007\/978-3-030-13709-0_46","volume-title":"Machine Learning, Optimization, and Data Science","author":"M Schneckenreither","year":"2019","unstructured":"Schneckenreither, M., Haeussler, S.: Reinforcement learning methods for operations research applications: the order release problem. In: Nicosia, G., Pardalos, P., Giuffrida, G., Umeton, R., Sciacca, V. (eds.) LOD 2018. LNCS, vol. 11331, pp. 545\u2013559. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-13709-0_46"},{"issue":"11","key":"27_CR22","doi-asserted-by":"publisher","first-page":"3285","DOI":"10.1080\/00207543.2020.1859634","volume":"59","author":"M Schneckenreither","year":"2021","unstructured":"Schneckenreither, M., Haeussler, S., Gerhold, C.: Order release planning with predictive lead times: a machine learning approach. Int. J. Prod. Res. 59(11), 3285\u20133303 (2021)","journal-title":"Int. J. Prod. Res."},{"key":"27_CR23","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897. PMLR (2015)"},{"key":"27_CR24","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"27_CR25","volume-title":"Introduction to Reinforcement Learning","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G., et al.: Introduction to Reinforcement Learning, vol. 135. MIT Press, Cambridge (1998)"},{"issue":"3\u20134","key":"27_CR26","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/s00170-006-0465-y","volume":"33","author":"YC Wang","year":"2007","unstructured":"Wang, Y.C., Usher, J.M.: A reinforcement learning approach for developing routing policies in multi-agent production scheduling. Int. J. Adv. Manuf. Technol. 33(3\u20134), 323\u2013333 (2007)","journal-title":"Int. J. Adv. Manuf. Technol."},{"issue":"2","key":"27_CR27","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1080\/09537289608930335","volume":"7","author":"J Wortman","year":"1996","unstructured":"Wortman, J., Euwe, M., Taal, M., Wiers, V.: A review of capacity planning techniques within standard software packages. Prod. Plan. Control 7(2), 117\u2013128 (1996)","journal-title":"Prod. Plan. Control"},{"issue":"8","key":"27_CR28","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1016\/S0305-0548(03)00080-7","volume":"31","author":"B Yang","year":"2004","unstructured":"Yang, B., Geunes, J., O\u2019Brien, W.J.: A heuristic approach for minimizing weighted tardiness and overtime costs in single resource scheduling. Comput. Oper. Res. 31(8), 1273\u20131301 (2004)","journal-title":"Comput. Oper. Res."},{"issue":"20","key":"27_CR29","doi-asserted-by":"publisher","first-page":"6105","DOI":"10.1080\/00207543.2015.1073859","volume":"54","author":"R Yuan","year":"2016","unstructured":"Yuan, R., Graves, S.C.: Setting optimal production lot sizes and planned lead times in a job shop. Int. J. Prod. Res. 54(20), 6105\u20136120 (2016)","journal-title":"Int. J. Prod. Res."},{"key":"27_CR30","first-page":"1114","volume":"95","author":"W Zhang","year":"1995","unstructured":"Zhang, W., Dietterich, T.G.: A reinforcement learning approach to job-shop scheduling. IJCAI 95, 1114\u20131120 (1995)","journal-title":"IJCAI"},{"key":"27_CR31","unstructured":"Zhang, W., Dietterich, T.G.: High-performance job-shop scheduling with a time-delay TD ($$\\lambda $$) network. In: Advances in Neural Information Processing Systems, pp. 1024\u20131030 (1996)"}],"container-title":["IFIP Advances in Information and Communication Technology","Advances in Production Management Systems. Artificial Intelligence for Sustainable and Resilient Production Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-85874-2_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T22:03:41Z","timestamp":1756591421000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-85874-2_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030858735","9783030858742"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-85874-2_27","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"value":"1868-4238","type":"print"},{"value":"1868-422X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"31 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APMS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Advances in Production Management Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nantes","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apms2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conftool","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"529","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"378","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"71% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}