{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T13:05:45Z","timestamp":1793451945256,"version":"4.5.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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-037"}],"funder":[{"name":"Natural Science Foundation of Shanghai Municipality","award":["23ZR1425400"],"award-info":[{"award-number":["23ZR1425400"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tcds.2025.3627812","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:13:37Z","timestamp":1761930817000},"page":"888-903","source":"Crossref","is-referenced-by-count":5,"title":["Learning Expressive Task Embeddings and Sample-Efficient Exploration for Context Shift Reduction in Offline Meta-Reinforcement Environment"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9575-7345","authenticated-orcid":false,"given":"Haoyu","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai University of Engineering Science","place":["Shanghai, China"],"department":["School of Electronic and Electrical Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3555-7143","authenticated-orcid":false,"given":"Xiaoyu","family":"Tan","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7063-3880","authenticated-orcid":false,"given":"Tianliang","family":"Yao","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University","place":["Shanghai, China"],"department":["Department of Control Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8563-5678","authenticated-orcid":false,"given":"Zhijun","family":"Fang","sequence":"additional","affiliation":[{"name":"Shanghai University of Engineering Science","place":["Shanghai, China"],"department":["School of Electronic and Electrical Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0514-9464","authenticated-orcid":false,"given":"Peng","family":"Qi","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University","place":["Shanghai, China"],"department":["Department of Control Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4024-925X","authenticated-orcid":false,"given":"Xihe","family":"Qiu","sequence":"additional","affiliation":[{"name":"Shanghai University of Engineering Science","place":["Shanghai, China"],"department":["School of Electronic and Electrical Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0961"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3302804"},{"key":"ref3","article-title":"Representation matters: Offline pretraining for sequential decision making","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610563"},{"key":"ref5","first-page":"4933","article-title":"Offline RL without off-policy evaluation","volume":"34","author":"Brandfonbrener","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSUSC.2023.3251302"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29658"},{"key":"ref8","article-title":"Provably improved context-based offline meta-RL with attention and contrastive learning","author":"Li","year":"2021"},{"key":"ref9","article-title":"Offline meta-reinforcement learning with online self-supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Pong","year":"2022"},{"key":"ref10","first-page":"4607","article-title":"Offline meta reinforcement learning\u2013identifiability challenges and effective data collection strategies","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dorfman","year":"2021"},{"key":"ref11","article-title":"Offline meta-reinforcement learning with advantage weighting","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Mitchell","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812312"},{"key":"ref13","article-title":"Robust task representations for offline meta-reinforcement learning via contrastive learning","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Yuan","year":"2022"},{"key":"ref14","article-title":"Skill-based meta-reinforcement learning","author":"Nam","year":"2022"},{"key":"ref15","article-title":"A survey of meta-reinforcement learning","author":"Beck","year":"2023"},{"issue":"289","key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102836"},{"key":"ref18","article-title":"Decoupling exploration and exploitation for meta-reinforcement learning without sacrifices","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Liu","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.03.108"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3380"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10723-023-09663-0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1017\/s0140525x23003266"},{"key":"ref23","article-title":"Efficient online reinforcement learning with offline data","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Ball","year":"2023"},{"key":"ref24","article-title":"Offline meta reinforcement learning with in-distribution online adaptation","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Wang","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.65109\/RXJW7650"},{"key":"ref26","article-title":"MetaDiffuser: Diffusion model as conditional planner for offline meta-RL","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Ni","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2408"},{"key":"ref28","article-title":"Offline RL policies should be trained to be adaptive","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Ghosh","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1875"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/9781118557426.ch1"},{"key":"ref31","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2016"},{"key":"ref32","article-title":"Conservative q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2020"},{"key":"ref33","article-title":"Mastering Atari with discrete world models","author":"Hafner","year":"2020"},{"key":"ref34","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Janner","year":"2021"},{"key":"ref35","first-page":"23983","article-title":"Snowflake: Scaling GNNs to high-dimensional continuous control via parameter freezing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Blake","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3394554"},{"key":"ref37","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Finn","year":"2017"},{"key":"ref38","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Rakelly","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3505"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274989\/11653483\/11223248.pdf?arnumber=11223248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T19:04:53Z","timestamp":1786647893000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11223248\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":39,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2025.3627812","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}