{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T17:47:20Z","timestamp":1763142440898,"version":"3.41.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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":["62273320","62033012"],"award-info":[{"award-number":["62273320","62033012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tnnls.2025.3558738","type":"journal-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T17:34:08Z","timestamp":1745861648000},"page":"11640-11649","source":"Crossref","is-referenced-by-count":1,"title":["Value Iteration for Stochastic LQR With Convergence Guarantees"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9920-0066","authenticated-orcid":false,"given":"Jing","family":"Lai","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Automation, Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0128-4960","authenticated-orcid":false,"given":"Junlin","family":"Xiong","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8706-3252","authenticated-orcid":false,"given":"Yu","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Dynamic Programming and Optimal Control","year":"1995","author":"Bertsekas","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmachtools.2020.103541"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3064535"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/2600000023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2016.2621461"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3287131"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2897814"},{"key":"ref10","first-page":"9429","article-title":"Inverse optimal control adapted to the noise characteristics of the human sensorimotor system","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schultheis"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2023.3301063"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref13","first-page":"8512","article-title":"Finite-time analysis of approximate policy iteration for the linear quadratic regulator","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"32","author":"Krauth"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3145632"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-023-00163-w"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110685"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110253"},{"key":"ref18","first-page":"1304","article-title":"Online policy gradient for model free learning of linear quadratic regulators with \u221aT regret","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cassel"},{"issue":"222","key":"ref19","first-page":"1","article-title":"Single time-scale actor-critic method to solve the linear quadratic regulator with convergence guarantees","volume":"24","author":"Zhou","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref20","first-page":"8351","article-title":"Provably global convergence of actor-critic: A case for linear quadratic regulator with ergodic cost","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3047577"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2959924"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110537"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3137524"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.06.053"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.12.007"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2020.02.019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110850"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.2981478"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10384286"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2024.3399630"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2025.112121"},{"key":"ref33","first-page":"702","article-title":"Primal-dual learning for the model-free risk-constrained linear quadratic regulator","volume-title":"Proc. 3rd Conf. Learn. Dyn. Control","author":"Zhao"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2616644"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2024.105731"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1017\/9781108231596"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3180898"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1088\/0951-7715\/21\/4\/011"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.05.003"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.2986991"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110486"},{"key":"ref42","first-page":"1","article-title":"Learning stabilizing controllers of linear systems via discount policy gradient","volume":"144","author":"Zhao","year":"2022","journal-title":"Proc. Mach. Learn. Res."},{"volume-title":"Adapt. Control","year":"2013","author":"\u00c5str\u00f6m","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2012.2183450"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3098985"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2023.3247734"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3220537"},{"key":"ref48","first-page":"5005","article-title":"Least-squares temporal difference learning for the linear quadratic regulator","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.jde.2014.01.024"},{"key":"ref50","volume":"5","author":"Rivasplata","year":"2012","journal-title":"Subgaussian Random Variables: An Expository Note"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11022714\/10977962.pdf?arnumber=10977962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T17:57:39Z","timestamp":1749059859000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10977962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":50,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3558738","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}