{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T02:07:05Z","timestamp":1780625225388,"version":"3.54.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Major Program of National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72192830"],"award-info":[{"award-number":["72192830"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Major Program of National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72192831"],"award-info":[{"award-number":["72192831"]}],"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":["72002028"],"award-info":[{"award-number":["72002028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"111 Project","doi-asserted-by":"publisher","award":["B16009"],"award-info":[{"award-number":["B16009"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tnnls.2023.3244024","type":"journal-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T18:31:48Z","timestamp":1677090708000},"page":"5298-5309","source":"Crossref","is-referenced-by-count":3,"title":["Improvement of Reinforcement Learning With Supermodularity"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9504-3745","authenticated-orcid":false,"given":"Ying","family":"Meng","sequence":"first","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":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1689-5473","authenticated-orcid":false,"given":"Fengyuan","family":"Shi","sequence":"additional","affiliation":[{"name":"Key Laboratory of Data Analytics and Optimization for Smart Industry, Ministry of Education, Liaoning Engineering Laboratory of Data Analytics and Optimization for Smart Industry, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"given":"Defeng","family":"Sun","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":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"9861","article-title":"Reinforcement learning for solving the vehicle routing problem","author":"nazari","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BF00226291"},{"key":"ref12","first-page":"2692","article-title":"Pointer networks","volume":"28","author":"vinyals","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref15","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume":"48","author":"wang","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/BF01539705"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/S0305-0548(96)00082-2"},{"key":"ref31","author":"munkres","year":"2000","journal-title":"Topology"},{"key":"ref30","first-page":"1386","article-title":"A multi-task selected learning approach for solving 3D flexible bin packing problem","author":"duan","year":"2019","journal-title":"Proc 18th Int Conf Auto Agents Multiagent Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403356"},{"key":"ref33","first-page":"1","article-title":"Exact combinatorial optimization with graph convolutional neural networks","author":"gasse","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16512"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2016.09.012"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2013.2250977"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref39","first-page":"72","volume":"20","author":"schoenfield","year":"2002","journal-title":"Fast exact solution of open bin packing problems without linear programming Draft"},{"key":"ref16","first-page":"1","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc ICLR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1111\/j.1475-3995.1997.tb00093.x"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927227"},{"key":"ref18","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2939157"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s42524-020-0126-0"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2307\/2951479"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2900592"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084198"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2018.08.021"},{"key":"ref41","year":"2022","journal-title":"Gurobi Optimizer Reference Manual"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3080521"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3233888"},{"key":"ref28","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1515\/9781400822539"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16155"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref7","first-page":"1","article-title":"Playing atari with deep reinforcement learning","author":"volodymyr","year":"2013","journal-title":"Proc NIPS DEEP Learn Workshop"},{"key":"ref9","first-page":"1","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Proc NIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927737"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2854833"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1201\/9781439821091"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2022.3154416"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2016.04.030"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10237282\/10049751.pdf?arnumber=10049751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:27:47Z","timestamp":1695666467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10049751\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":43,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3244024","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}