{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T15:31:26Z","timestamp":1780759886020,"version":"3.54.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"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":["12171279"],"award-info":[{"award-number":["12171279"]}],"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":["11801317"],"award-info":[{"award-number":["11801317"]}],"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":["11971409"],"award-info":[{"award-number":["11971409"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2019MA013"],"award-info":[{"award-number":["ZR2019MA013"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016697","name":"Youth Innovation Technology Project of Higher School in Shandong Province","doi-asserted-by":"publisher","award":["2019KJI011"],"award-info":[{"award-number":["2019KJI011"]}],"id":[{"id":"10.13039\/100016697","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Grants Council of Hong Kong","award":["15213218"],"award-info":[{"award-number":["15213218"]}]},{"name":"Research Grants Council of Hong Kong","award":["15215319"],"award-info":[{"award-number":["15215319"]}]},{"name":"Research Grants Council of Hong Kong","award":["15216720"],"award-info":[{"award-number":["15216720"]}]},{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","award":["1-TA03"],"award-info":[{"award-number":["1-TA03"]}],"id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","award":["4-ZZKR"],"award-info":[{"award-number":["4-ZZKR"]}],"id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hong Kong RGC","award":["15202421"],"award-info":[{"award-number":["15202421"]}]},{"name":"Hong Kong RGC","award":["15202817"],"award-info":[{"award-number":["15202817"]}]},{"name":"PolyU-SDU Joint Research Center on Financial Mathematics"},{"name":"CAS AMSS-POLYU Joint Laboratory of Applied Mathematics"},{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1109\/tac.2022.3181248","type":"journal-article","created":{"date-parts":[[2022,6,14]],"date-time":"2022-06-14T20:10:32Z","timestamp":1655237432000},"page":"5009-5016","source":"Crossref","is-referenced-by-count":53,"title":["Stochastic Linear Quadratic Optimal Control Problem: A Reinforcement Learning Method"],"prefix":"10.1109","volume":"67","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4293-515X","authenticated-orcid":false,"given":"Na","family":"Li","sequence":"first","affiliation":[{"name":"School of Statistics and Mathematics, Shandong University of Finance and Economics, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0493-417X","authenticated-orcid":false,"given":"Xun","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8965-9108","authenticated-orcid":false,"given":"Jing","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6824-1634","authenticated-orcid":false,"given":"Zuo Quan","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/9.863597"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374604"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-6097-2","volume-title":"Optimal Control Theory","author":"Berkovitz","year":"1974"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1994.735224"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012996310478"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-29724-3_10"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911390"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/9.788532"},{"key":"ref9","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fazel","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/S0027763000020742"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2414811"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.07.001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109421"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109267"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2751018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2477810"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0076-5392(08)60497-X"},{"key":"ref19","first-page":"1","article-title":"Learning the model-free linear quadratic regulator via random search","volume-title":"Proc. 2nd Annu. Conf. Learn. Dyn. Control: Proc. Mach. Learn. Res.","author":"Mohammadi","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2002.801727"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)66174-3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2870075"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00245-017-9402-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1991.4791776"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/140979940"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/002071798221849"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.08.017"},{"key":"ref29","first-page":"1","article-title":"Reinforcement learning in continuous time and space: A stochastic control approach","volume":"21","author":"Wang","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1111\/mafi.12281"},{"key":"ref31","article-title":"Learning from delayed rewards","volume-title":"Ph.D. dissertation","author":"Watkins","year":"1989"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1989.70114"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/oca.915"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.10.038"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1466-3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1137\/0330016"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/9870073\/09792231.pdf?arnumber=9792231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T02:35:18Z","timestamp":1706754918000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9792231\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":36,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tac.2022.3181248","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":[[2022,9]]}}}