{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T05:01:21Z","timestamp":1780117281318,"version":"3.54.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["T2121002"],"award-info":[{"award-number":["T2121002"]}],"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":["62173003"],"award-info":[{"award-number":["62173003"]}],"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":["62473195"],"award-info":[{"award-number":["62473195"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tac.2025.3649291","type":"journal-article","created":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T18:40:05Z","timestamp":1767120005000},"page":"4035-4042","source":"Crossref","is-referenced-by-count":0,"title":["Model-Free Offline Reinforcement Learning for Linear Quadratic Control"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0171-5345","authenticated-orcid":false,"given":"Haoran","family":"Ma","sequence":"first","affiliation":[{"name":"State Key Laboratory of Power Grid Safety, China Electric Power Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2630-9690","authenticated-orcid":false,"given":"Zhengen","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9243-0045","authenticated-orcid":false,"given":"Dingguo","family":"Liang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Turbulence and Complex Systems, Department of Mechanics and Engineering Science, College of Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6327-631X","authenticated-orcid":false,"given":"Ying","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Turbulence and Complex Systems, Department of Mechanics and Engineering Science, College of Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-007-2300-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2012.07.014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3045664"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2021.09.005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15858-2_2"},{"key":"ref7","first-page":"295","article-title":"Reinforcement learning applied to linear quadratic regulation","volume-title":"Proc. 6th Int. Conf. Neural Inf. Process. Syst.","author":"Bradtke","year":"1992"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1994.735224"},{"key":"ref9","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"Lagoudakis","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Fazel","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2025.3569597"},{"key":"ref13","first-page":"5005","article-title":"Least-squares temporal difference learning for the linear quadratic regulator","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Tu","year":"2018"},{"key":"ref14","first-page":"3036","article-title":"The gap between model-based and model-free methods on the linear quadratic regulator: An asymptotic viewpoint","volume-title":"Proc. 32nd Conf. Learn. Theory","author":"Tu","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029916"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-062922-090153"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3145632"},{"key":"ref18","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3235967"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992636"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2023.110876"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2024.3422105"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-019-09426-y"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2959924"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2966717"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.110060"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109548"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3253787"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3148374"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.2986991"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.09.003"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-58223-3_10"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970760"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.23943\/9781400890088"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511802256"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3073860"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1017\/9781108627771"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS54457.2022.00029"},{"key":"ref39","article-title":"CVX: MATLAB software for disciplined convex programming, version 2.1","author":"Grant","year":"2014"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.11.021"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9\/11539063\/11318864.pdf?arnumber=11318864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T04:15:42Z","timestamp":1780114542000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11318864\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":40,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tac.2025.3649291","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}