{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:16:45Z","timestamp":1784906205969,"version":"3.55.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS-1501044"],"award-info":[{"award-number":["ECCS-1501044"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["EPCN-1903781"],"award-info":[{"award-number":["EPCN-1903781"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1109\/tac.2022.3172250","type":"journal-article","created":{"date-parts":[[2022,5,3]],"date-time":"2022-05-03T19:57:53Z","timestamp":1651607873000},"page":"2383-2390","source":"Crossref","is-referenced-by-count":51,"title":["Reinforcement Learning for Adaptive Optimal Stationary Control of Linear Stochastic Systems"],"prefix":"10.1109","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4359-2937","authenticated-orcid":false,"given":"Bo","family":"Pang","sequence":"first","affiliation":[{"name":"Control and Networks Lab, Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4868-9359","authenticated-orcid":false,"given":"Zhong-Ping","family":"Jiang","sequence":"additional","affiliation":[{"name":"Control and Networks Lab, Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref2","first-page":"1814","article-title":"Multiagent rollout and policy iteration for POMDP with application to multi-robot repair problems","volume-title":"Conf. Robot Learn.","volume":"155","author":"Bhattacharya","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2927177"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01260"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-014-0613-7"},{"key":"ref6","volume-title":"Adaptive Control","author":"strm","year":"1995"},{"key":"ref7","volume-title":"Adaptive Optimal Control: The Thinking Mans GPC","author":"Bitmead","year":"1990"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1979.4310229"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/37.126844"},{"key":"ref10","volume-title":"Reinforcement Learning and Optimal Control","author":"Bertsekas","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/9781119132677"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-78384-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2018.09.005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_3"},{"key":"ref16","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1561\/2600000023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-1323-7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/0305028"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/0306044"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/0311030"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/0309016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1969.1099303"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-011-1005-3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2006.887288"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814402"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4497"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/9.788532"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/18M1214147"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3848428"},{"key":"ref31","first-page":"295","article-title":"Reinforcement learning applied to linear quadratic regulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bradtke","year":"1993"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8795815"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2165729"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2550518"},{"key":"ref35","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"Lagoudakis","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(76)90029-7"},{"key":"ref37","first-page":"59","article-title":"On the convergence of optimistic policy iteration","volume":"3","author":"Tsitsiklis","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1969.1099206"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(97)00008-X"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WCICA.2006.1712310"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1137\/0312009"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68829-7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.2307\/3213455"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2018.09.001"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3172250"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.096"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3085510"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1080\/00207178408933251"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/140"},{"key":"ref50","volume-title":"Matrix Differential Calculus With Applications in Statistics and Economerices","author":"Magnus","year":"2007"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139020411"},{"issue":"3\/4","key":"ref52","first-page":"163","article-title":"On continuity of the MoorePenrose and Drazin inverses","volume":"49","author":"Rakoevi","year":"1997","journal-title":"Mat. Vesn."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17122"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/9\/10084346\/9767669-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10084346\/09767669.pdf?arnumber=9767669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:39:33Z","timestamp":1705963173000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9767669\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":53,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tac.2022.3172250","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":[[2023,4]]}}}