{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:19:08Z","timestamp":1768281548023,"version":"3.49.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/501100013314","name":"Higher Education Discipline Innovation 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":[[2026,1]]},"DOI":"10.1109\/tnnls.2025.3603165","type":"journal-article","created":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T17:54:06Z","timestamp":1756922046000},"page":"219-232","source":"Crossref","is-referenced-by-count":0,"title":["A Decomposition Optimization-Based Multiobjective Reinforcement Learning Algorithm for Obtaining Nonconvex Pareto Fronts"],"prefix":"10.1109","volume":"37","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 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\/0000-0002-9504-3745","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\/TASE.2023.3244331"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s42524-020-0126-0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2022.106026"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3384405"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2014.2358639"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2023.105253"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107381"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2023.2240433"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3283537"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/11672142_26"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126986"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34068"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2016.2608507"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.15702"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref17","first-page":"34883","article-title":"Efficient discovery of Pareto front for multi-objective reinforcement learning","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3528944"},{"key":"ref19","first-page":"1","article-title":"Multi-objective reinforcement learning: Convexity, stationarity and Pareto optimality","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Lu"},{"key":"ref20","first-page":"1","article-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29148"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3987"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.biosystems.2023.104989"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2019.03.019"},{"key":"ref25","article-title":"Smooth tchebycheff scalarization for multi-objective optimization","author":"Lin","year":"2024","journal-title":"arXiv:2402.19078"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-022-09552-y"},{"key":"ref27","first-page":"1","article-title":"Multi-objective reinforcement learning for the expected utility of the return","volume-title":"Proc. Adapt. Learn. Agents Workshop FAIM","author":"Roijers"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/EVCO_a_00109"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2403131"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2015.2457616"},{"key":"ref31","article-title":"Traversing Pareto optimal policies: Provably efficient multi-objective reinforcement learning","author":"Qiu","year":"2024","journal-title":"arXiv:2407.17466"},{"key":"ref32","article-title":"The optimal reward baseline for gradient-based reinforcement learning","author":"Weaver","year":"2013","journal-title":"arXiv:1301.2315"},{"key":"ref33","article-title":"Sample efficient policy gradient methods with recursive variance reduction","author":"Xu","year":"2019","journal-title":"arXiv:1909.08610"},{"issue":"9","key":"ref34","first-page":"1471","article-title":"Variance reduction techniques for gradient estimates in reinforcement learning","volume":"5","author":"Greensmith","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","article-title":"Variance reduction for policy gradient with action-dependent factorized baselines","author":"Wu","year":"2018","journal-title":"arXiv:1803.07246"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3330332"},{"key":"ref37","first-page":"4026","article-title":"Stochastic variance-reduced policy gradient","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Papini"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2007.892759"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5232-5"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09433-x"},{"key":"ref41","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton"},{"key":"ref42","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2020.2992387"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2021.3117702"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-1360(199801)7:1<34::AID-MCDA161>3.0.CO;2-6"},{"key":"ref46","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref47","article-title":"Sample-efficient multi-objective learning via generalized policy improvement prioritization","author":"Alegre","year":"2023","journal-title":"arXiv:2301.07784"},{"key":"ref48","first-page":"1110","article-title":"Pareto conditioned networks","volume-title":"Proc. 21st Int. Conf. Auto. Agents Multiagent Syst.","author":"Reymond"},{"issue":"1","key":"ref49","first-page":"3483","article-title":"Multi-objective reinforcement learning using sets of Pareto dominating policies","volume":"15","author":"Moffaert","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6615007"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2003.810761"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-31880-4_5"},{"key":"ref53","first-page":"23671","article-title":"A toolkit for reliable benchmarking and research in multi-objective reinforcement learning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Felten"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11339259\/11147177.pdf?arnumber=11147177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:57Z","timestamp":1768255317000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11147177\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":53,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3603165","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}