{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T10:54:48Z","timestamp":1782298488561,"version":"3.54.5"},"reference-count":52,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72271138"],"award-info":[{"award-number":["72271138"]}],"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":["71932006"],"award-info":[{"award-number":["71932006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Eng. Manage."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tem.2025.3535771","type":"journal-article","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T13:36:17Z","timestamp":1739453777000},"page":"573-590","source":"Crossref","is-referenced-by-count":8,"title":["A Deep Reinforcement Learning Method Solving Bilevel Optimization for Product Design Considering Remanufacturing"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5607-4696","authenticated-orcid":false,"given":"Yujie","family":"Ma","sequence":"first","affiliation":[{"name":"Department of Industrial Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2910-7778","authenticated-orcid":false,"given":"Xin","family":"Xia","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8319-524X","authenticated-orcid":false,"given":"Jie","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4767-9597","authenticated-orcid":false,"given":"Chen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1115\/1.4002308"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2014.01.028"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2015.12.008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2011.06.019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1115\/1.4052389"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2017.05.157"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2016.12.005"},{"key":"ref8","article-title":"Reinforcement learning for combinatorial optimization: A survey","volume-title":"Comput. Oper. Res.","volume":"134","author":"Mazyavkina","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/00207540701450138"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1504\/IJPD.2008.020406"},{"key":"ref11","first-page":"14","article-title":"Remanufacturing: A key enabler to sustainable product systems","volume-title":"Rochester Inst. Technol.","volume":"23","author":"Nasr","year":"2006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-007-0003-2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.7232\/iems.2015.14.2.159"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/0305215x.2010.482990"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpe.2018.12.010"},{"key":"ref16","volume-title":"Product Design and Development","author":"Ulrich","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-019-01463-2"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2020.124548"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2019.02.007"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1287\/opre.21.1.37"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2836-1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2015.04.022"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2022.105557","article-title":"Bi-level optimization of charging scheduling of a battery swap station based on deep reinforcement learning","volume":"118","author":"Tan","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1016\/j.ejco.2021.100007","article-title":"A survey on mixed-integer programming techniques in bilevel optimization","volume":"9","author":"Kleinert","year":"2021","journal-title":"EURO J. Comput. Optim."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020410"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/0911017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2712906"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2016.1264397"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2016.7744017"},{"issue":"2","key":"ref30","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1016\/j.ejor.2016.08.027","article-title":"Evolutionary algorithm for bilevel optimization using approximations of the lower level optimal solution mapping","volume":"257","author":"Sinha","year":"2017","journal-title":"Eur. J. Oper. Res."},{"key":"ref31","first-page":"1","article-title":"Learning combinatorial optimization algorithms over graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Khalil","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1051\/ro\/1994280100011"},{"issue":"9","key":"ref33","doi-asserted-by":"crossref","first-page":"3405","DOI":"10.1007\/s00170-019-03612-6","article-title":"A review of leader-follower joint optimization problems and mathematical models for product design and development","volume":"103","author":"Du","year":"2019","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TEM.2020.2966649"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106479"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2020.106778","article-title":"A self-learning genetic algorithm based on reinforcement learning for flexible job-shop scheduling problem","volume":"149","author":"Chen","year":"2020","journal-title":"Comput. Ind. Eng."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref38","first-page":"9633","article-title":"A deep reinforcement learning framework for column generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Chi","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2936142"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2020.2984614"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2022.3168700"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2295"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1090.1058"},{"issue":"9","key":"ref44","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1080\/07408170590917011","article-title":"Product portfolio planning with customer-engineering interaction","volume":"37","author":"Jiao","year":"2005","journal-title":"IIE Trans."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-021-01812-0"},{"issue":"1","key":"ref46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/BF01580266","article-title":"Quantitative evaluation of product disassembly for recycling","volume":"10","author":"Kroll","year":"1998","journal-title":"Res. Eng. Des."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TEM.2010.2048909"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/s0004-3702(99)00052-1"},{"key":"ref49","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Haarnoja","year":"2018"},{"issue":"6","key":"ref50","doi-asserted-by":"crossref","first-page":"3601","DOI":"10.1287\/opre.2021.2226","article-title":"Scalable reinforcement learning for multiagent networked systems","volume":"70","author":"Qu","year":"2022","journal-title":"Oper. Res."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1177\/002224299005400402"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"}],"container-title":["IEEE Transactions on Engineering Management"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/17\/10821517\/10886978.pdf?arnumber=10886978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T20:39:53Z","timestamp":1770323993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10886978\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/tem.2025.3535771","relation":{},"ISSN":["0018-9391","1558-0040"],"issn-type":[{"value":"0018-9391","type":"print"},{"value":"1558-0040","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}