{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:57:27Z","timestamp":1781024247629,"version":"3.54.1"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.asoc.2026.115418","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T10:05:02Z","timestamp":1778580302000},"page":"115418","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Goal-set-conditioned dynamic multi-objective reinforcement learning algorithm for learning time-varying pareto optimal policies"],"prefix":"10.1016","volume":"200","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6441-2210","authenticated-orcid":false,"given":"Haofang","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7323-2959","authenticated-orcid":false,"given":"Hongchuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7331-9130","authenticated-orcid":false,"given":"Yanyan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.asoc.2026.115418_bib0005","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1007\/s10458-022-09552-y","article-title":"A practical guide to multi-objective reinforcement learning and planning","volume":"36","author":"Hayes","year":"2022","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"10.1016\/j.asoc.2026.115418_bib0010","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1613\/jair.3987","article-title":"A survey of multi-objective sequential decision-making","volume":"48","author":"Roijers","year":"2013","journal-title":"J. Artif. Intell. Res."},{"issue":"5","key":"10.1016\/j.asoc.2026.115418_bib0015","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.1109\/JAS.2023.123378","article-title":"Towards energy-efficient autonomous driving: a multi-objective reinforcement learning approach","volume":"10","author":"He","year":"2023","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.asoc.2026.115418_bib0020","article-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","volume":"32","author":"Yang","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"10.1016\/j.asoc.2026.115418_bib0025","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s10458-023-09604-x","article-title":"Actor-critic multi-objective reinforcement learning for non-linear utility functions","volume":"37","author":"Reymond","year":"2023","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"10.1016\/j.asoc.2026.115418_bib0030","series-title":"Proceedings of the Adaptive and Learning Agents Workshop at FAIM","article-title":"Multi-objective reinforcement learning for the expected utility of the return","volume":"vol. 2018","author":"Roijers","year":"2018"},{"key":"10.1016\/j.asoc.2026.115418_bib0035","series-title":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","first-page":"191","article-title":"Scalarized multi-objective reinforcement learning: novel design techniques","author":"Van Moffaert","year":"2013"},{"issue":"3","key":"10.1016\/j.asoc.2026.115418_bib0040","doi-asserted-by":"crossref","first-page":"40570","DOI":"10.1109\/ACCESS.2021.3065384","article-title":"An improved Penalty-Based boundary intersection approach for irregular problems","volume":"9","author":"Yang","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.asoc.2026.115418_bib0045","series-title":"ECAI 2010","first-page":"969","article-title":"On finding compromise solutions in multiobjective markov decision processes","author":"Perny","year":"2010"},{"key":"10.1016\/j.asoc.2026.115418_bib0050","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.engappai.2019.08.014","article-title":"Dynamic multi-objective optimisation using deep reinforcement learning: benchmark, algorithm and an application to identify vulnerable zones based on water quality","volume":"86","author":"Hasan","year":"2019","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.asoc.2026.115418_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2021.107230","article-title":"Path planning optimization of indoor mobile robot based on adaptive ant colony algorithm","volume":"156","author":"Miao","year":"2021","journal-title":"Comput. Ind. Eng."},{"key":"10.1016\/j.asoc.2026.115418_bib0060","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1016\/j.apm.2019.05.009","article-title":"A dynamic multi-objective optimization model with interactivity and uncertainty for real-time reservoir flood control operation","volume":"74","author":"Yang","year":"2019","journal-title":"Appl. Math. Model."},{"key":"10.1016\/j.asoc.2026.115418_bib0065","series-title":"Service Robots in Health Care: the Evolution of Mechanical Solutions to Human Resource Problems","first-page":"1","author":"Bauer","year":"2003"},{"issue":"1","key":"10.1016\/j.asoc.2026.115418_bib0070","first-page":"36","article-title":"Dynamic evolutionary multiobjective optimization for raw ore allocation in mineral processing","volume":"3","author":"Ding","year":"2018","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"issue":"6","key":"10.1016\/j.asoc.2026.115418_bib0075","doi-asserted-by":"crossref","first-page":"1891","DOI":"10.1109\/TCBB.2017.2685320","article-title":"Robust dynamic multi-objective vehicle routing optimization method","volume":"15","author":"Guo","year":"2017","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"issue":"5","key":"10.1016\/j.asoc.2026.115418_bib0080","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1109\/TEVC.2004.831456","article-title":"Dynamic multiobjective optimization problems: test cases, approximations, and applications","volume":"8","author":"Farina","year":"2004","journal-title":"IEEE Trans. Evol. Comput."},{"key":"10.1016\/j.asoc.2026.115418_bib0085","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2022.109717","article-title":"Multi-objective reinforcement learning framework for dynamic flexible job shop scheduling problem with uncertain events","volume":"131","author":"Wang","year":"2022","journal-title":"Appl. Soft Comput."},{"issue":"1","key":"10.1016\/j.asoc.2026.115418_bib0090","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1109\/TCYB.2015.2510698","article-title":"Evolutionary dynamic multiobjective optimization: benchmarks and algorithm comparisons","volume":"47","author":"Jiang","year":"2016","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.asoc.2026.115418_bib0095","series-title":"Proceedings of the 4th International Conference on Evolutionary Multi-Criterion Optimization","first-page":"803","article-title":"Dynamic multi-objective optimization and decision-making using modified NSGA-II: a case study on hydrothermal power scheduling","author":"Deb","year":"2007"},{"issue":"4","key":"10.1016\/j.asoc.2026.115418_bib0100","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1109\/TEVC.2017.2771451","article-title":"Transfer learning-based dynamic multiobjective optimization algorithms","volume":"22","author":"Jiang","year":"2017","journal-title":"IEEE Trans. Evol. Comput."},{"key":"10.1016\/j.asoc.2026.115418_bib0105","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1016\/j.ins.2023.03.094","article-title":"Dynamic multi-objective evolutionary algorithms in noisy environments","volume":"634","author":"Sahmoud","year":"2023","journal-title":"Inf. Sci."},{"key":"10.1016\/j.asoc.2026.115418_bib0110","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1016\/j.ins.2020.08.101","article-title":"A reinforcement learning approach for dynamic multi-objective optimization","volume":"546","author":"Zou","year":"2021","journal-title":"Inf. Sci."},{"issue":"4","key":"10.1016\/j.asoc.2026.115418_bib0115","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1109\/JAS.2023.123687","article-title":"Constrained multi-objective optimization with deep reinforcement learning assisted operator selection","volume":"11","author":"Ming","year":"2024","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.asoc.2026.115418_bib0120","series-title":"2019 22nd International Conference on Computer and Information Technology (ICCIT)","first-page":"1","article-title":"Design and development of a benchmark for dynamic multi-objective optimisation problem in the context of deep reinforcement learning","author":"Hasan","year":"2019"},{"key":"10.1016\/j.asoc.2026.115418_bib0125","doi-asserted-by":"crossref","first-page":"50377","DOI":"10.52202\/075280-2192","article-title":"A definition of continual reinforcement learning","volume":"36","author":"Abel","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.115418_bib0130","series-title":"International Conference on Machine Learning","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017"},{"key":"10.1016\/j.asoc.2026.115418_bib0135","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-016-0043-6","article-title":"A survey of transfer learning","volume":"3","author":"Weiss","year":"2016","journal-title":"J. Big Data"},{"key":"10.1016\/j.asoc.2026.115418_bib0140","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/BF01197559","article-title":"A closer look at drawbacks of minimizing weighted sums of objectives for pareto set generation in multicriteria optimization problems","volume":"14","author":"Das","year":"1997","journal-title":"Struct. Optim."},{"key":"10.1016\/j.asoc.2026.115418_bib0145","series-title":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","first-page":"645","article-title":"Inverted PBI in MOEA\/D and its impact on the search performance on multi and many-objective optimization","author":"Sato","year":"2014"},{"issue":"6","key":"10.1016\/j.asoc.2026.115418_bib0150","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1109\/TEVC.2007.892759","article-title":"MOEA\/D: a multiobjective evolutionary algorithm based on decomposition","volume":"11","author":"Zhang","year":"2007","journal-title":"IEEE Trans. Evol. Comput."},{"key":"10.1016\/j.asoc.2026.115418_bib0155","series-title":"International Conference on Machine Learning","first-page":"11","article-title":"Dynamic weights in multi-objective deep reinforcement learning","author":"Abels","year":"2019"},{"key":"10.1016\/j.asoc.2026.115418_bib0160","article-title":"Hindsight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.115418_bib0165","doi-asserted-by":"crossref","first-page":"1159","DOI":"10.1613\/jair.1.13554","article-title":"Autotelic agents with intrinsically motivated goal-conditioned reinforcement learning: a short survey","volume":"76","author":"Colas","year":"2022","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.asoc.2026.115418_bib0170","series-title":"AI 2008: Advances in Artificial Intelligence: 21st Australasian Joint Conference on Artificial Intelligence Auckland","first-page":"372","article-title":"On the limitations of scalarisation for multi-objective reinforcement learning of pareto fronts","author":"Vamplew","year":"2008"},{"key":"10.1016\/j.asoc.2026.115418_bib0175","series-title":"Proceedings of the 2000 Congress on Evolutionary Computation","first-page":"204","article-title":"On measuring multiobjective evolutionary algorithm performance","volume":"vol. 1","author":"Van Veldhuizen","year":"2000"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626008665?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626008665?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:01:08Z","timestamp":1781020868000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626008665"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":35,"alternative-id":["S1568494626008665"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115418","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Goal-set-conditioned dynamic multi-objective reinforcement learning algorithm for learning time-varying pareto optimal policies","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115418","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115418"}}