{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T08:58:56Z","timestamp":1781168336955,"version":"3.54.1"},"reference-count":67,"publisher":"Informa UK Limited","issue":"11","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72192830, 72192831"],"award-info":[{"award-number":["72192830, 72192831"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018925","name":"111 center","doi-asserted-by":"crossref","award":["B16009"],"award-info":[{"award-number":["B16009"]}],"id":[{"id":"10.13039\/501100018925","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Production Research"],"published-print":{"date-parts":[[2026,6,3]]},"DOI":"10.1080\/00207543.2026.2626535","type":"journal-article","created":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T02:13:04Z","timestamp":1770862384000},"page":"4606-4634","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":0,"title":["A dynamic plate design problem via reinforcement learning"],"prefix":"10.1080","volume":"64","author":[{"given":"Fengyuan","family":"Shi","sequence":"first","affiliation":[{"name":"Northeastern University","place":["Shenyang, People's Republic of China"]},{"name":"Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University), Ministry of Education","place":["Shenyang, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Meng","sequence":"additional","affiliation":[{"name":"Northeastern University","place":["Shenyang, People's Republic of China"]},{"name":"Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University), Ministry of Education","place":["Shenyang, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixin","family":"Tang","sequence":"additional","affiliation":[{"name":"Northeastern University","place":["Shenyang, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengnan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Northeastern University","place":["Shenyang, People's Republic of China"]},{"name":"Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University), Ministry of Education","place":["Shenyang, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2026,2,11]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10732-024-09537-y"},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/635"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00453-021-00818-7"},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3393691.3394224"},{"key":"e_1_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-018-1325-x"},{"key":"e_1_3_3_7_1","volume-title":"Reinforcement Learning and Optimal Control","author":"Bertsekas Dimitri.","year":"2019","unstructured":"Bertsekas, Dimitri. 2019. Reinforcement Learning and Optimal Control. Nashua, NH: Athena Scientific."},{"key":"e_1_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00453-014-9955-8"},{"key":"e_1_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3321612"},{"key":"e_1_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2016.12.001"},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-7997-1_35"},{"key":"e_1_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.4324\/9780203774441"},{"key":"e_1_3_3_14_1","unstructured":"Darapuneni Yoga Jaideep. 2012. \u201cA Survey of Classical and Recent Results in Bin Packing Problem.\u201d Master's thesis University of Nevada Las Vegas."},{"key":"e_1_3_3_15_1","unstructured":"D\u00f3sa Gy\u00f6rgy and Jiri Sgall. 2013. \u201cFirst Fit Bin Packing: A Tight Analysis.\u201d In 30th International Symposium on Theoretical Aspects of Computer Science (STACS 2013) edited by Natacha Portier and Thomas Wilke Vol. 20 of Leibniz International Proceedings in Informatics (LIPIcs) 538\u2013549. Dagstuhl Germany: Schloss Dagstuhl\u2013Leibniz-Zentrum Fuer Informatik. http:\/\/drops.dagstuhl.de\/opus\/volltexte\/2013\/3963."},{"key":"e_1_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403356"},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1955995"},{"key":"e_1_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-2864-4_490"},{"key":"e_1_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01415672"},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7091-2748-3_8"},{"key":"e_1_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.9.6.849"},{"key":"e_1_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2018.07.053"},{"key":"e_1_3_3_23_1","unstructured":"Hasselt Hado van Arthur Guez and David Silver. 2016. \u201cDeep Reinforcement Learning with Double Q-Learning.\u201d In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence.\u00a0Phoenix Arizona USA."},{"key":"e_1_3_3_24_1","unstructured":"Irwan Bello Pham Hieu Quoc V. Le Norouzi Mohammad and Bengio Samy. 2017. \u201cNeural Combinatorial Optimization with Reinforcement Learning.\u201d In Workshop Proceedings of the 5th International Conference on Learning Representations ICLR '17 Toulon France."},{"key":"e_1_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3121542"},{"key":"e_1_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2019.1693659"},{"key":"e_1_3_3_27_1","unstructured":"Kool Wouter Herke van Hoof and Max Welling. 2019. \u201cAttention Learn to Solve Routing Problems!.\u201d In International Conference on Learning Representations.\u00a0New Orleans Louisiana USA."},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2023.1277"},{"key":"e_1_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN46459.2019.8956393"},{"key":"e_1_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1080\/0740817X.2012.725506"},{"key":"e_1_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1720923"},{"key":"e_1_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3103811"},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2018.2865414"},{"key":"e_1_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2010.501549"},{"key":"e_1_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2022.1195"},{"key":"e_1_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:JOCO.0000038915.62826.79"},{"key":"e_1_3_3_37_1","unstructured":"Ma Qiang Suwen Ge Danyang He Darshan Thaker and Iddo Drori. 2020. \u201cCombinatorial Optimization by Graph Pointer Networks and Hierarchical Reinforcement Learning.\u201d In AAAI Workshop on Deep Learning on Graphs: Methodologies and Applications.\u00a0New York USA."},{"key":"e_1_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2019.1652777"},{"key":"e_1_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.2307\/2951479"},{"key":"e_1_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.23919\/ICCAS52745.2021.9649790"},{"key":"e_1_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2021.1239"},{"key":"e_1_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-4655(02)00280-1"},{"key":"e_1_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48224-5_20"},{"key":"e_1_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08019-2_38"},{"key":"e_1_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2013.844374"},{"key":"e_1_3_3_46_1","unstructured":"Song Shuai Shuo Yang Ran Song Shilei Chu Yibin Li and Wei Zhang. 2022. \u201cTowards Online 3D Bin Packing: Learning Synergies between Packing and Unpacking via DRL.\u201d In 6th Conference on Robot Learning (CoRL 2022).\u00a0Auckland New Zealand."},{"key":"e_1_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2013.148"},{"key":"e_1_3_3_48_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton Richard S.","year":"2018","unstructured":"Sutton, Richard S., and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. Cambridge, MA: MIT Press."},{"key":"e_1_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2022.3165987"},{"key":"e_1_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42524-020-0126-0"},{"key":"e_1_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.42"},{"key":"e_1_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2023.2279129"},{"key":"e_1_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1515\/9781400822539"},{"key":"e_1_3_3_54_1","unstructured":"Veli\u010dkovi\u0107 Petar Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Lio and Yoshua Bengio. 2018. \u201cGraph Attention Networks.\u201d In Workshop Proceedings of the 6th International Conference on Learning Representations.\u00a0Vancouver BC Canada."},{"key":"e_1_3_3_55_1","unstructured":"Vinyals Oriol Meire Fortunato and Navdeep Jaitly. 2015. \u201cPointer Networks.\u201d In Advances in Neural Information Processing Systems.\u00a0Montreal Canada."},{"key":"e_1_3_3_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3534070"},{"key":"e_1_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/3159805"},{"key":"e_1_3_3_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2022.3154416"},{"key":"e_1_3_3_59_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207540903317523"},{"key":"e_1_3_3_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635914"},{"key":"e_1_3_3_61_1","unstructured":"Zhang Jingwei Bin Zi and Xiaoyu Ge. 2021. \u201cAttend2Pack: Bin Packing through Deep Reinforcement Learning with Attention.\u201d In Proceedings of the Workshop on Reinforcement Learning for Real Life (RL4RealLife) with the 38th International Conference on Machine Learning.\u00a0Online."},{"key":"e_1_3_3_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105905"},{"key":"e_1_3_3_63_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111990"},{"key":"e_1_3_3_64_1","unstructured":"Zhao Hang and Kai Xu. 2022. \u201cLearning Efficient Online 3D Bin Packing on Packing Configuration Trees.\u201d In International Conference on Learning Representations.\u00a0Online."},{"key":"e_1_3_3_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3348-6"},{"key":"e_1_3_3_66_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2043566"},{"key":"e_1_3_3_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481933"},{"key":"e_1_3_3_68_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2023.109814"}],"container-title":["International Journal of Production Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207543.2026.2626535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T08:15:17Z","timestamp":1781165717000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207543.2026.2626535"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,11]]},"references-count":67,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2026,6,3]]}},"alternative-id":["10.1080\/00207543.2026.2626535"],"URL":"https:\/\/doi.org\/10.1080\/00207543.2026.2626535","relation":{},"ISSN":["0020-7543","1366-588X"],"issn-type":[{"value":"0020-7543","type":"print"},{"value":"1366-588X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,11]]},"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":"2025-03-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}