{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:38:02Z","timestamp":1784212682190,"version":"3.55.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Plan of China","doi-asserted-by":"publisher","award":["2021ZD0112002"],"award-info":[{"award-number":["2021ZD0112002"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1913204"],"award-info":[{"award-number":["U1913204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61991411"],"award-info":[{"award-number":["61991411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["ZR2020JQ29"],"award-info":[{"award-number":["ZR2020JQ29"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Project for Self-Developed Innovation Team of Jinan City","award":["2021GXRC038"],"award-info":[{"award-number":["2021GXRC038"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tase.2023.3235742","type":"journal-article","created":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T14:24:09Z","timestamp":1673879049000},"page":"939-950","source":"Crossref","is-referenced-by-count":61,"title":["Heuristics Integrated Deep Reinforcement Learning for Online 3D Bin Packing"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3126-8021","authenticated-orcid":false,"given":"Shuo","family":"Yang","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9423-5198","authenticated-orcid":false,"given":"Shuai","family":"Song","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shilei","family":"Chu","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1344-4415","authenticated-orcid":false,"given":"Ran","family":"Song","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8063-2547","authenticated-orcid":false,"given":"Jiyu","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5906-5074","authenticated-orcid":false,"given":"Yibin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4960-3190","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.48.2.256.12386"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/1475-3995.00400"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2016.12.001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.3024291"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3097261"},{"issue":"5","key":"ref6","first-page":"263","article-title":"A three-dimensional bin packing algorithm","volume":"27","author":"Scheithauer","year":"1991","journal-title":"Elektronische Informationsverarbeitung Und Kybernetik"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1070.0250"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1111\/j.1475-3995.2009.00703.x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920916531"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062300"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3176207"},{"key":"ref13","article-title":"Solving a new 3D bin packing problem with deep reinforcement learning method","author":"Hu","year":"2017","journal-title":"arXiv:1708.05930"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16155"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635914"},{"key":"ref16","article-title":"Learning efficient online 3D bin packing on packing configuration trees","volume-title":"Proc. ICLR","author":"Zhao"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1057\/jors.1992.101"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3348-6"},{"key":"ref19","first-page":"46","article-title":"Approximation algorithms for bin packing: A survey","volume-title":"Approximation Algorithms for NP-Hard Problems","author":"Coffman","year":"1996"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912438781"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2012.07.036"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/bf00226291"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30198-1_45"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2007.06.063"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-1665-5_11"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1400421"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55792-2_10"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10732-008-9081-3"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2010.07.017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2012.12.006"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.15.3.267.16080"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.4028\/www.scientific.net\/AMM.143-144.279"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.23919\/ICCAS52745.2021.9649790"},{"key":"ref34","article-title":"A multi-task selected learning approach for solving 3D flexible bin packing problem","author":"Duan","year":"2018","journal-title":"arXiv:1804.06896"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794049"},{"key":"ref36","article-title":"Ranked reward: Enabling self-play reinforcement learning for combinatorial optimization","author":"Laterre","year":"2018","journal-title":"arXiv:1807.01672"},{"key":"ref37","first-page":"1548","article-title":"Solving 3D bin packing problem via multimodal deep reinforcement learning","volume-title":"Proc. 20th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Jiang"},{"key":"ref38","article-title":"A generalized reinforcement learning algorithm for online 3D bin-packing","author":"Verma","year":"2020","journal-title":"arXiv:2007.00463"},{"key":"ref39","article-title":"Attention, learn to solve routing problems!","author":"Kool","year":"2018","journal-title":"arXiv:1803.08475"},{"key":"ref40","first-page":"9839","article-title":"Reinforcement learning for solving the vehicle routing problem","volume-title":"Proc. NeurIPS","volume":"31","author":"Nazari"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004787"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3057424"},{"key":"ref43","article-title":"Neural combinatorial optimization with reinforcement learning","author":"Bello","year":"2016","journal-title":"arXiv:1611.09940"},{"key":"ref44","article-title":"A generalized reinforcement learning algorithm for online 3D bin-packing","volume-title":"Proc. AAAI Workshop","author":"Verma"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2005.12.047"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.04.053"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3177422"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref49","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593516"},{"key":"ref52","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"issue":"267","key":"ref54","first-page":"1","article-title":"Tianshou: A highly modularized deep reinforcement learning library","volume":"23","author":"Weng","year":"2022","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8856\/10381526\/10018146.pdf?arnumber=10018146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:50:00Z","timestamp":1755546600000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10018146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":54,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tase.2023.3235742","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}