{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:13:04Z","timestamp":1740132784057,"version":"3.37.3"},"reference-count":22,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"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":["62172097"],"award-info":[{"award-number":["62172097"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005270","name":"Fujian Provincial Department of Science and Technology","doi-asserted-by":"publisher","award":["2020H6011"],"award-info":[{"award-number":["2020H6011"]}],"id":[{"id":"10.13039\/501100005270","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tce.2024.3360211","type":"journal-article","created":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T18:46:13Z","timestamp":1706640373000},"page":"3762-3769","source":"Crossref","is-referenced-by-count":0,"title":["RelTrans: An Enhancing Offline Reinforcement Learning Model for the Complex Hand Gesture Decision-Making Task"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9159-9785","authenticated-orcid":false,"given":"Xiangwei","family":"Chen","sequence":"first","affiliation":[{"name":"College of Computer and Cyber Security, Fujian Normal University, Fuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixia","family":"Zeng","sequence":"additional","affiliation":[{"name":"College of Computer and Cyber Security, Fujian Normal University, Fuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2173-4612","authenticated-orcid":false,"given":"Ruliang","family":"Xiao","sequence":"additional","affiliation":[{"name":"College of Computer and Cyber Security, Fujian Normal University, Fuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2789-5070","authenticated-orcid":false,"given":"Imad","family":"Rida","sequence":"additional","affiliation":[{"name":"Laboratoire Biomécanique et Bioingénierie UMR 7338, Centre de Recherches de Royallieu, Université de Technologie de Compiégne, Compiégne, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shi","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer and Cyber Security, Fujian Normal University, Fuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2017.014971"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/03772063.2020.1739569"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118559"},{"key":"ref4","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref5","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref6","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"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.06.022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05337-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-021-00876-0"},{"key":"ref10","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fujimoto"},{"key":"ref11","first-page":"5774","article-title":"Offline reinforcement learning with fisher divergence critic regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kostrikov"},{"key":"ref12","first-page":"1","article-title":"Offline RL with no OOD actions: In-sample learning via implicit value regularization","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref13","first-page":"1","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref14","first-page":"1","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Sohn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26130"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00926"},{"key":"ref19","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"issue":"8","key":"ref20","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref21","article-title":"AWAC: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020","journal-title":"arXiv:2006.09359"},{"key":"ref22","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/30\/10510045\/10416876.pdf?arnumber=10416876","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T18:48:30Z","timestamp":1714762110000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10416876\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":22,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tce.2024.3360211","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"type":"print","value":"0098-3063"},{"type":"electronic","value":"1558-4127"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}