{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T21:21:16Z","timestamp":1782854476999,"version":"3.54.5"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012246","name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012246","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576233"],"award-info":[{"award-number":["62576233"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134276","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T16:24:44Z","timestamp":1781627084000},"page":"134276","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Skill extraction facilitated by meta-policy fine-tuned with multi-task"],"prefix":"10.1016","volume":"698","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5504-744X","authenticated-orcid":false,"given":"Hang","family":"Ren","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2226-2859","authenticated-orcid":false,"given":"Fei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1762-1757","authenticated-orcid":false,"given":"Bangjun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134276_bib0005","series-title":"International Conference on Machine Learning","first-page":"27225","article-title":"Controllability-aware unsupervised skill discovery","author":"Park","year":"2023"},{"key":"10.1016\/j.neucom.2026.134276_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110629","article-title":"MetaTKG++: learning evolving factor enhanced meta-knowledge for temporal knowledge graph reasoning","author":"Xia","year":"2024","journal-title":"Pattern Recognit."},{"issue":"4","key":"10.1016\/j.neucom.2026.134276_bib0015","doi-asserted-by":"crossref","first-page":"3918","DOI":"10.1109\/LRA.2024.3371260","article-title":"Data-efficient task generalization via probabilistic model-based meta reinforcement learning","volume":"9","author":"Bhardwaj","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.134276_bib0020","article-title":"Train hard, fight easy: robust meta reinforcement learning","volume":"36","author":"Greenberg","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134276_bib0025","series-title":"2024 IEEE 13th Data Driven Control and Learning Systems Conference (DDCLS)","first-page":"1780","article-title":"Adaptive multi-agent coordination among different team attribute tasks via contextual meta-reinforcement learning","author":"Huang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134276_bib0030","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.patrec.2023.11.023","article-title":"MVSSC: meta-reinforcement learning based visual indoor navigation using multi-view semantic spatial context","volume":"177","author":"Zhang","year":"2024","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.neucom.2026.134276_bib0035","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"11633","article-title":"Meta-reinforcement learning via exploratory task clustering","volume":"vol. 38","author":"Chu","year":"2024"},{"issue":"3","key":"10.1016\/j.neucom.2026.134276_bib0040","first-page":"3476","article-title":"Meta-reinforcement learning in non-stationary and dynamic environments","volume":"45","author":"Bing","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134276_bib0045","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"12358","article-title":"Decoupling meta-reinforcement learning with Gaussian task contexts and skills","volume":"vol. 38","author":"He","year":"2024"},{"key":"10.1016\/j.neucom.2026.134276_bib0050","series-title":"International Conference on Machine Learning","first-page":"17811","article-title":"Offline meta-reinforcement learning with online self-supervision","author":"Pong","year":"2022"},{"key":"10.1016\/j.neucom.2026.134276_bib0055","series-title":"International Conference on Machine Learning","first-page":"10461","article-title":"Meta-learning parameterized skills","author":"Fu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134276_bib0060","series-title":"Proceedings of the 8th International Conference on Learning Representations (ICLR 2020)","article-title":"Sharing knowledge in multi-task deep reinforcement learning","author":"DEramo","year":"2020"},{"key":"10.1016\/j.neucom.2026.134276_bib0065","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"12376","article-title":"Not all tasks are equally difficult: multi-task deep reinforcement learning with dynamic depth routing","volume":"vol. 38","author":"He","year":"2024"},{"key":"10.1016\/j.neucom.2026.134276_bib0070","series-title":"International Conference on Machine Learning","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","author":"Sodhani","year":"2021"},{"key":"10.1016\/j.neucom.2026.134276_bib0075","first-page":"11501","article-title":"Conservative data sharing for multi-task offline reinforcement learning","volume":"34","author":"Yu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134276_bib0080","series-title":"Robotics Science and Systems","article-title":"Robust and versatile bipedal jumping control through reinforcement learning","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.134276_bib0085","series-title":"International Conference on Machine Learning","first-page":"6925","article-title":"Decoupling exploration and exploitation for meta-reinforcement learning without sacrifices","author":"Liu","year":"2021"},{"issue":"3","key":"10.1016\/j.neucom.2026.134276_bib0090","doi-asserted-by":"crossref","first-page":"1454","DOI":"10.1109\/TNNLS.2021.3105407","article-title":"Meta-reinforcement learning with dynamic adaptiveness distillation","volume":"34","author":"Hu","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"289","key":"10.1016\/j.neucom.2026.134276_bib0095","first-page":"1","article-title":"Varibad: variational Bayes-adaptive deep RL via meta-learning","volume":"22","author":"Zintgraf","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.134276_bib0100","series-title":"International Conference on Machine Learning","first-page":"15340","article-title":"Transformers are meta-reinforcement learners","author":"Melo","year":"2022"},{"key":"10.1016\/j.neucom.2026.134276_bib0105","author":"Kirsch"},{"key":"10.1016\/j.neucom.2026.134276_bib0110","series-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","first-page":"26519","article-title":"On the effectiveness of fine-tuning versus meta-reinforcement learning","author":"Mandi","year":"2022"},{"key":"10.1016\/j.neucom.2026.134276_bib0115","author":"Zeng"},{"key":"10.1016\/j.neucom.2026.134276_bib0120","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.134276_bib0125","series-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"2887","article-title":"Projected task-specific layers for multi-task reinforcement learning","author":"Roberts","year":"2024"},{"key":"10.1016\/j.neucom.2026.134276_bib0130","series-title":"International Conference on Machine Learning","first-page":"1317","article-title":"Explore, discover and learn: unsupervised discovery of state-covering skills","author":"Campos","year":"2020"},{"key":"10.1016\/j.neucom.2026.134276_bib0135","series-title":"International Conference on Machine Learning","first-page":"19185","article-title":"Unsupervised skill discovery for learning shared structures across changing environments","author":"Lee","year":"2023"},{"key":"10.1016\/j.neucom.2026.134276_bib0140","series-title":"Intrinsically-Motivated and Open-Ended Learning Workshop@ NeurIPS2023","article-title":"Skill-based reinforcement learning with intrinsic reward matching","author":"Adeniji","year":"2022"},{"key":"10.1016\/j.neucom.2026.134276_bib0145","author":"Berseth"},{"key":"10.1016\/j.neucom.2026.134276_bib0150","first-page":"729","article-title":"Demonstration-guided reinforcement learning with learned skills","volume":"164","author":"Pertsch","year":"2021","journal-title":"Proc. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.134276_bib0155","series-title":"Conference on Robot Learning","first-page":"188","article-title":"Accelerating reinforcement learning with learned skill priors","author":"Pertsch","year":"2021"},{"key":"10.1016\/j.neucom.2026.134276_bib0160","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Skill-based meta-reinforcement learning","author":"Nam","year":"2022"},{"key":"10.1016\/j.neucom.2026.134276_bib0165","series-title":"Conference on Robot Learning","first-page":"1025","article-title":"Relay policy learning: solving long-horizon tasks via imitation and reinforcement learning","author":"Gupta","year":"2020"},{"key":"10.1016\/j.neucom.2026.134276_bib0170","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","volume":"33","author":"Yang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134276_bib0175","series-title":"International Conference on Machine Learning","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","author":"Rakelly","year":"2019"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226016747?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226016747?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T20:23:34Z","timestamp":1782851014000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226016747"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":35,"alternative-id":["S0925231226016747"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134276","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Skill extraction facilitated by meta-policy fine-tuned with multi-task","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134276","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":"134276"}}