{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T17:51:06Z","timestamp":1761760266156,"version":"build-2065373602"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Major Program of National Natural Science Foundation of China","award":["72192830","72192831"],"award-info":[{"award-number":["72192830","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. Contr. Syst. Technol."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tcst.2025.3552543","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T19:32:07Z","timestamp":1743449527000},"page":"1586-1600","source":"Crossref","is-referenced-by-count":1,"title":["Deep Reinforcement Learning With Integer Optimization for Dynamic Slab Assignment Problem"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0219-7321","authenticated-orcid":false,"given":"Tianyang","family":"Li","sequence":"first","affiliation":[{"name":"National Frontiers Science Center for Industrial Intelligence and Systems Optimization, 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, 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"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0480-9621","authenticated-orcid":false,"given":"Yuxuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Data Analytics and Optimization for Smart Industry, Ministry of Education and Liaoning Engineering Laboratory of Data Analytics and Optimization for Smart Industry, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s42524-020-0126-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.4028\/www.scientific.net\/AMM.442.549"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2355\/isijinternational.54.1324"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3934\/jimo.2011.7.31"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2013.788796"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.106982"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1287\/opre.48.4.505.12425"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/opre.51.1.94.12791"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/00207540801968625"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/opre.46.1.17"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.42.12.1706"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1287\/opre.49.1.26.11185"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10756-9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2495145"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3007167"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2362139"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2021.3075557"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2024.3377876"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2021.3102476"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref23","first-page":"2692","article-title":"Pointer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Vinyals"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neucom.2019.06.111","article-title":"A pointer network based deep learning algorithm for unconstrained binary quadratic programming problem","volume":"390","author":"Gu","year":"2020","journal-title":"Neurocomputing"},{"key":"ref25","article-title":"Neural combinatorial optimization with reinforcement learning","author":"Bello","year":"2016","journal-title":"arXiv:1611.09940"},{"key":"ref26","article-title":"Deep reinforcement learning for multi-resource multi-machine job scheduling","author":"Chen","year":"2017","journal-title":"arXiv:1711.07440"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2018.03.212"},{"key":"ref28","first-page":"22","article-title":"A note on learning algorithms for quadratic assignment with graph neural networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","volume":"1050","author":"Nowak"},{"key":"ref29","article-title":"Solving a new 3D bin packing problem with deep reinforcement learning method","author":"Hu","year":"2017","journal-title":"arXiv:1708.05930"},{"key":"ref30","first-page":"9861","article-title":"Reinforcement learning for solving the vehicle routing problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Nazari"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1080\/09720510.2017.1395182"},{"key":"ref34","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016","journal-title":"arXiv:1602.01783"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref36","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref37","article-title":"Variance reduction for policy gradient with action-dependent factorized baselines","author":"Wu","year":"2018","journal-title":"arXiv:1803.07246"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3330332"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-18500-8_40"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-0237-4"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"}],"container-title":["IEEE Transactions on Control Systems Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/87\/11134587\/10945997.pdf?arnumber=10945997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T17:48:40Z","timestamp":1761760120000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10945997\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":41,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcst.2025.3552543","relation":{},"ISSN":["1063-6536","1558-0865","2374-0159"],"issn-type":[{"type":"print","value":"1063-6536"},{"type":"electronic","value":"1558-0865"},{"type":"electronic","value":"2374-0159"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}