{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:09:09Z","timestamp":1778051349319,"version":"3.51.4"},"reference-count":59,"publisher":"Informa UK Limited","issue":"13","content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Production Research"],"published-print":{"date-parts":[[2022,7,3]]},"DOI":"10.1080\/00207543.2022.2058432","type":"journal-article","created":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T03:10:31Z","timestamp":1649646631000},"page":"4049-4069","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":257,"title":["Deep reinforcement learning for dynamic scheduling of a flexible job shop"],"prefix":"10.1080","volume":"60","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4375-9140","authenticated-orcid":false,"given":"Renke","family":"Liu","sequence":"first","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University","place":["Singapore, Singapore"]}]},{"given":"Rajesh","family":"Piplani","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University","place":["Singapore, Singapore"]}]},{"given":"Carlos","family":"Toro","sequence":"additional","affiliation":[{"name":"Vicomtech Research Centre","place":["San Sebastian, Spain"]}]}],"member":"301","published-online":{"date-parts":[[2022,4,11]]},"reference":[{"key":"e_1_3_3_2_1","volume-title":"MOSIM\u201908: 7th Conference Internationale de Modelisation et Simulation","author":"Aissani N.","year":"2008","unstructured":"Aissani, N., B. Beldjilali, and D. Trentesaux. 2008. \u201cEfficient and effective reactive scheduling of manufacturing system using Sarsa-multi-objective agents\". MOSIM\u201908: 7th Conference Internationale de Modelisation et Simulation."},{"key":"e_1_3_3_3_1","doi-asserted-by":"crossref","unstructured":"Baer Schirin Jupiter Bakakeu Richard Meyes and Tobias Meisen. 2019. Multi-Agent Reinforcement Learning for Job Shop Scheduling in Flexible Manufacturing Systems. Paper presented at the 2019 s International Conference on Artificial Intelligence for Industries (AI4I) 25-27 Sept. 2019.","DOI":"10.1109\/AI4I46381.2019.00014"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.2354"},{"key":"e_1_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"e_1_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.06.053"},{"key":"e_1_3_3_8_1","article-title":"Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks","author":"Foerster Jakob N.","year":"2016","unstructured":"Foerster, Jakob N., Yannis M. Assael, Nando de Freitas, and Shimon Whiteson. 2016. \u201cLearning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks.\u201d arXiv preprint\u00a0arXiv:1602.02672\u00a0.","journal-title":"arXiv preprint\u00a0arXiv:1602.02672\u00a0"},{"key":"e_1_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2011.571443"},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207541003794884"},{"key":"e_1_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1080\/01605682.2019.1621220"},{"key":"e_1_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2006.04.007"},{"key":"e_1_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-5273(96)00068-0"},{"key":"e_1_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.106982"},{"key":"e_1_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2019.1581954"},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2019.02.101"},{"key":"e_1_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2019.03.041"},{"key":"e_1_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/WSC48552.2020.9383997"},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-55305-3_18"},{"key":"e_1_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2908210"},{"key":"e_1_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2987820"},{"key":"e_1_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEM.2017.2712611"},{"key":"e_1_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106208"},{"key":"e_1_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1975057"},{"key":"e_1_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cirp.2020.04.001"},{"key":"e_1_3_3_27_1","unstructured":"Matloff Norm. 2008. Introduction to discrete-event simulation and the simpy language."},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2020.100314"},{"key":"e_1_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2009.03.008"},{"key":"e_1_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpe.2010.06.004"},{"key":"e_1_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10951-008-0090-8"},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1870013"},{"key":"e_1_3_3_34_1","unstructured":"Paszke Adam Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein and Luca Antiga. 2019. Pytorch: An imperative style high-performance deep learning library. Paper presented at the Advances in neural information processing systems."},{"key":"e_1_3_3_35_1","doi-asserted-by":"crossref","unstructured":"Pickardt Christoph Jurgen Branke Torsten Hildebrandt Jens Heger and Bernd Scholz-Reiter. 2010. Generating dispatching rules for semiconductor manufacturing to minimize weighted tardiness. Paper presented at the 2010 Winter Simulation Conference.","DOI":"10.1109\/WSC.2010.5678946"},{"key":"e_1_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1080\/08839510903549606"},{"key":"e_1_3_3_37_1","doi-asserted-by":"crossref","unstructured":"Qu Shuhui Jie Wang and Juergen Jasperneite. 2019. \"Dynamic scheduling in modern processing systems using expert-guided distributed reinforcement learning.\" In 2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) 459-66.","DOI":"10.1109\/ETFA.2019.8869023"},{"key":"e_1_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1968526"},{"key":"e_1_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2011.611539"},{"key":"e_1_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1717008"},{"key":"e_1_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207540701846236"},{"key":"e_1_3_3_42_1","article-title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","author":"Sunehag Peter","year":"2017","unstructured":"Sunehag, Peter, Guy Lever, Audrunas Gruslys, Wojciech Marian Czarnecki, Vinicius Zambaldi, Max Jaderberg, Marc Lanctot, et al. 2017. \u201cValue-Decomposition Networks For Cooperative Multi-Agent Learning.\u201d arXiv preprint\u00a0 arXiv:1706.05296.","journal-title":"arXiv preprint\u00a0 arXiv:1706.05296"},{"key":"e_1_3_3_43_1","article-title":"Instance Normalization: The Missing Ingredient for Fast Stylization","author":"Ulyanov Dmitry","year":"2016","unstructured":"Ulyanov, Dmitry, Andrea Vedaldi, and Victor Lempitsky. 2016. \u201cInstance Normalization: The Missing Ingredient for Fast Stylization.\u201d arXiv preprint\u00a0arXiv:1607.06450.","journal-title":"arXiv preprint\u00a0arXiv:1607.06450"},{"key":"e_1_3_3_44_1","doi-asserted-by":"crossref","unstructured":"Van Hasselt Hado Arthur Guez and David Silver. 2016. Deep reinforcement learning with double q-learning. Paper presented at the Thirtieth AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"e_1_3_3_45_1","volume-title":"Reinforcement Learning and Markov Decision Processes, Reinforcement Learning: State-of-the-art","author":"van Otterlo Martijn","year":"2012","unstructured":"van Otterlo, Martijn, and Marco Wiering. 2012. Reinforcement Learning and Markov Decision Processes, Reinforcement Learning: State-of-the-art. Berlin: Springer Berlin Heidelberg."},{"key":"e_1_3_3_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-018-1454-3"},{"key":"e_1_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1794075"},{"key":"e_1_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2004.08.018"},{"key":"e_1_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2018.03.212"},{"key":"e_1_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-008-0073-9"},{"key":"e_1_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2016.07.030"},{"key":"e_1_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1943037"},{"key":"e_1_3_3_53_1","doi-asserted-by":"crossref","unstructured":"Yska Daniel Yi Mei and Mengjie Zhang. 2018. Genetic programming hyper-heuristic with cooperative coevolution for dynamic flexible job shop scheduling. Paper presented at the European Conference on Genetic Programming Cham.","DOI":"10.1007\/978-3-319-77553-1_19"},{"key":"e_1_3_3_54_1","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/7172842"},{"key":"e_1_3_3_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3024849"},{"key":"e_1_3_3_56_1","doi-asserted-by":"crossref","unstructured":"Zhang Fangfang Yi Mei and Mengjie Zhang. 2018. Genetic programming with multi-tree representation for dynamic flexible job shop scheduling. Paper presented at the Australasian Joint Conference on Artificial Intelligence.","DOI":"10.1007\/978-3-030-03991-2_43"},{"key":"e_1_3_3_57_1","doi-asserted-by":"crossref","unstructured":"Zhang Fangfang Yi Mei and Mengjie Zhang. 2019. \"A two-stage genetic programming hyper-heuristic approach with feature selection for dynamic flexible job shop scheduling.\" In Proceedings of the Genetic and Evolutionary Computation Conference 347\u201355. Prague Czech Republic: Association for Computing Machinery.","DOI":"10.1145\/3321707.3321790"},{"key":"e_1_3_3_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2944247"},{"key":"e_1_3_3_59_1","doi-asserted-by":"crossref","unstructured":"Zhang Tao Shufang Xie and Oliver Rose. 2017. Real-time job shop scheduling based on simulation and Markov decision processes. Paper presented at the 2017 Winter Simulation Conference (WSC) Las Vegas Nevada.","DOI":"10.1109\/WSC.2017.8248100"},{"key":"e_1_3_3_60_1","unstructured":"Zhou MengChu. 2012. Petri Nets in Flexible and Agile Automation. Vol. 310. Springer Science & Business Media."}],"container-title":["International Journal of Production Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207543.2022.2058432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T16:58:58Z","timestamp":1770397138000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207543.2022.2058432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,11]]},"references-count":59,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2022,7,3]]}},"alternative-id":["10.1080\/00207543.2022.2058432"],"URL":"https:\/\/doi.org\/10.1080\/00207543.2022.2058432","relation":{},"ISSN":["0020-7543","1366-588X"],"issn-type":[{"value":"0020-7543","type":"print"},{"value":"1366-588X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,11]]},"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":"2021-03-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}