{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T00:55:02Z","timestamp":1775868902863,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Major Program of the National Natural Science Foundation of China","award":["72192830"],"award-info":[{"award-number":["72192830"]}]},{"name":"Major Program of the National Natural Science Foundation of China","award":["72192831"],"award-info":[{"award-number":["72192831"]}]},{"DOI":"10.13039\/501100001809","name":"111 Project","doi-asserted-by":"publisher","award":["B16009"],"award-info":[{"award-number":["B16009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2025.3585108","type":"journal-article","created":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T13:47:51Z","timestamp":1751464071000},"page":"17734-17748","source":"Crossref","is-referenced-by-count":1,"title":["A Hybrid Method Based on Multi-Agent Reinforcement Learning and Integer Programming for Dynamic Slab Design Problems in Steel Industry"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0784-8983","authenticated-orcid":false,"given":"Baiyang","family":"He","sequence":"first","affiliation":[{"name":"National Frontiers Science Center for Industrial Intelligence and Systems Optimization and Liaoning Engineering Laboratory of Data Analytics and Optimization for Smart Industry, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9504-3745","authenticated-orcid":false,"given":"Ying","family":"Meng","sequence":"additional","affiliation":[{"name":"National Frontiers Science Center for Industrial Intelligence and Systems Optimization and the Key Laboratory of Data Analytics and Optimization for Smart Industry, Ministry of Education, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9950-5169","authenticated-orcid":false,"given":"Lixin","family":"Tang","sequence":"additional","affiliation":[{"name":"National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2009.2014960"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1287\/inte.1040.0077"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.jors.2602274"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.47.6.864.9809"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/24725854.2023.2204316"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICAL.2007.4338864"},{"key":"ref7","article-title":"Attend2Pack: Bin packing through deep reinforcement learning with attention","author":"Zhang","year":"2021","journal-title":"arXiv:2107.04333"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN46459.2019.8956393"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3235742"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2021.110846"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2022.124822"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6377(93)90093-V"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1057\/jors.1993.113"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.jors.2600910"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68155-7_41"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/00207540801968625"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74970-7_8"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2013.788796"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/00207540903317523"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1111\/j.1475-3995.2000.tb00194.x"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2010.493535"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2005.11.068"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/S0305-0548(00)00095-2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1287\/opre.49.1.26.11185"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28840"},{"key":"ref26","first-page":"2692","article-title":"Pointer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Vinyals"},{"key":"ref27","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1287\/opre.45.5.758"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-015-0294-3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00291-020-00610-z"},{"key":"ref31","first-page":"4385","article-title":"Asynchronous actor-critic for multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xiao"},{"key":"ref32","first-page":"20580","article-title":"Divergence-regularized multi-agent actor-critic","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Su"},{"key":"ref33","first-page":"1698","article-title":"LDSA: Learning dynamic subtask assignment in cooperative multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yang"},{"key":"ref34","first-page":"1989","article-title":"Scaling multi-agent reinforcement learning with selective parameter sharing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Christianos"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23860\/diss-li-hepfeng-2023"},{"key":"ref36","article-title":"Solving steel mill slab problems with branch and price","author":"Heinz","year":"2009"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/11062884.pdf?arnumber=11062884","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T05:16:27Z","timestamp":1752210987000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11062884\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3585108","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}