{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T19:59:58Z","timestamp":1780516798896,"version":"3.54.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":["62206288"],"award-info":[{"award-number":["62206288"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Scientists Fund of The State Key Laboratory of Multimodal Artificial Intelligence Systems"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/lra.2025.3601029","type":"journal-article","created":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:44:10Z","timestamp":1755715450000},"page":"10338-10345","source":"Crossref","is-referenced-by-count":1,"title":["Zero-Shot Adaptation at Task-Level via Coarse-to-Fine Policy Refinement and Holistic-Local Contrastive Representation"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1100-1040","authenticated-orcid":false,"given":"Zhengwei","family":"Li","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1361-4824","authenticated-orcid":false,"given":"Zhenyang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0022-7219","authenticated-orcid":false,"given":"Yurou","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6240-5300","authenticated-orcid":false,"given":"Lu","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2148-1846","authenticated-orcid":false,"given":"Zhiyong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2021.3116231"},{"key":"ref2","first-page":"21007","article-title":"Zero-shot reinforcement learning via function encoders","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Ingebrand","year":"2024"},{"key":"ref3","first-page":"25747","article-title":"Robust task representations for offline meta-reinforcement learning via contrastive learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yuan","year":"2022"},{"key":"ref4","first-page":"80024","article-title":"Context shift reduction for offline meta-reinforcement learning","volume":"36","author":"Gao","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref5","first-page":"26519","article-title":"On the effectiveness of fine-tuning versus meta-reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhao","year":"2022"},{"key":"ref6","first-page":"562","article-title":"Octo: An open-source generalist robot policy","volume-title":"Proc. Robot. Sci. Syst.","author":"Team","year":"2024"},{"key":"ref7","first-page":"43356","article-title":"Parameterizing non-parametric meta-reinforcement learning tasks via subtask decomposition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lee","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160626"},{"key":"ref9","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref10","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly","year":"2019"},{"key":"ref11","first-page":"1","article-title":"VariBAD: A very good method for Bayes-adaptive deep RL via meta-learning","author":"Zintgraf","year":"2020","journal-title":"Int. Conf. Learn. Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29482"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231201196"},{"key":"ref14","first-page":"2616","article-title":"Probabilistic movement primitives","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Paraschos","year":"2013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3583136"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v30i1.6739"},{"key":"ref17","article-title":"Rl$^{2}$: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9338-y"},{"key":"ref19","article-title":"Learning to compose skills","author":"Sahni","year":"2017"},{"key":"ref20","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yang","year":"2020"},{"key":"ref21","first-page":"1","article-title":"Multi-task reinforcement learning with mixture of orthogonal experts","volume-title":"Proc. Twelfth Int. Conf. Learn. Representations","author":"Hendawy","year":"2024"},{"key":"ref22","first-page":"36507","article-title":"Contrastive modules with temporal attention for multi-task reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lan","year":"2023,"},{"key":"ref23","first-page":"38520","article-title":"Mixtures of experts unlock parameter scaling for deep RL","volume-title":"Proc. 41st Int. Conf. Mach. Learn. ser. Res.","volume":"235","author":"Obando-Ceron","year":"2024"},{"key":"ref24","first-page":"6197","article-title":"Multi-task batch reinforcement learning with metric learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Li","year":"2020"},{"key":"ref25","first-page":"17175","article-title":"FOCAL: Efficient fully-offline meta-reinforcement learning via distance metric learning and behavior regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26210"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112767"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"ref29","volume-title":"Optimal Learning: Computational Procedures for Bayes-Adaptive Markov Decision Processes","author":"Duff","year":"2002"},{"key":"ref30","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/500"},{"key":"ref32","first-page":"27222","article-title":"Improving generalization in meta-RL with imaginary tasks from latent dynamics mixture","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lee","year":"2021"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11125679\/11130903.pdf?arnumber=11130903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T18:11:04Z","timestamp":1756404664000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11130903\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":32,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3601029","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}