{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:23:32Z","timestamp":1781972612507,"version":"3.54.5"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB4703500"],"award-info":[{"award-number":["2022YFB4703500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62273328"],"award-info":[{"award-number":["62273328"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20489"],"award-info":[{"award-number":["U21A20489"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Fundamental Research Program","award":["2021B151513003"],"award-info":[{"award-number":["2021B151513003"]}]},{"name":"Guangdong Fundamental Research Program","award":["2021B1515120011"],"award-info":[{"award-number":["2021B1515120011"]}]},{"name":"Guangdong Fundamental Research Program","award":["2023A1515030130"],"award-info":[{"award-number":["2023A1515030130"]}]},{"DOI":"10.13039\/501100017607","name":"Key Fundamental Research Program of Shenzhen","doi-asserted-by":"publisher","award":["JCYJ20200109115201707"],"award-info":[{"award-number":["JCYJ20200109115201707"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011259","name":"Joint Fund of State Key Laboratory of Robotics","doi-asserted-by":"publisher","award":["2022-KF-22-07"],"award-info":[{"award-number":["2022-KF-22-07"]}],"id":[{"id":"10.13039\/501100011259","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"CAS Key Laboratory of Human\u2013Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tsmc.2023.3305498","type":"journal-article","created":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T17:31:06Z","timestamp":1693589466000},"page":"156-169","source":"Crossref","is-referenced-by-count":15,"title":["Efficient Incremental Offline Reinforcement Learning With Sparse Broad Critic Approximation"],"prefix":"10.1109","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3377-1509","authenticated-orcid":false,"given":"Liang","family":"Yao","sequence":"first","affiliation":[{"name":"Department of Electromechanical Engineering, University of Macau, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8157-5951","authenticated-orcid":false,"given":"Baoliang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3238-745X","authenticated-orcid":false,"given":"Xin","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0688-3564","authenticated-orcid":false,"given":"Ziwen","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7623-6904","authenticated-orcid":false,"given":"Pak Kin","family":"Wong","sequence":"additional","affiliation":[{"name":"Department of Electromechanical Engineering, University of Macau, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3807-3649","authenticated-orcid":false,"given":"Ying","family":"Hu","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101964"},{"key":"ref4","first-page":"21810","article-title":"MOReL: Model-based offline reinforcement learning: Model-based offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kidambi"},{"key":"ref5","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"Lagoudakis","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2712561"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2013.08.037"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1309"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2019.04.001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.2966631"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2505084"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2716952"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2866622"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2956022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2935033"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103476"},{"key":"ref18","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2926806"},{"issue":"98","key":"ref20","first-page":"3041","article-title":"Finite-sample analysis of least-squares policy iteration","volume":"13","author":"Lazaric","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2980198"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0736"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3167029"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808203"},{"key":"ref27","first-page":"1609","article-title":"A convergent o(n) temporal-difference algorithm for off-policy learning with linear function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"21","author":"Sutton"},{"key":"ref28","first-page":"1070","article-title":"Hamming distance metric learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Norouzi"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3204967"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2021.3072190"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2004.824320"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1984.4788393"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.01.009"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2924696"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3107357"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3043147"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/10364887\/10237048.pdf?arnumber=10237048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T03:48:20Z","timestamp":1705031300000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10237048\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":37,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2023.3305498","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}