{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:08:17Z","timestamp":1740132497055,"version":"3.37.3"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2018YFA0703800"],"award-info":[{"award-number":["2018YFA0703800"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173191","61973175"],"award-info":[{"award-number":["62173191","61973175"]}],"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":[[2024,8]]},"DOI":"10.1109\/tac.2023.3344870","type":"journal-article","created":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T20:01:18Z","timestamp":1703102478000},"page":"5200-5215","source":"Crossref","is-referenced-by-count":0,"title":["Probabilistic Framework of Howard's Policy Iteration: BML Evaluation and Robust Convergence Analysis"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0984-9777","authenticated-orcid":false,"given":"Yutian","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3984-3120","authenticated-orcid":false,"given":"Yuan-Hua","family":"Ni","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nankai University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1415-4073","authenticated-orcid":false,"given":"Zengqiang","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nankai University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0656-2886","authenticated-orcid":false,"given":"Ji-Feng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Systems and Control, Academy of Mathematics and Systems Science,Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"volume-title":"Dynamic Programming and Markov Processes","year":"1960","author":"Howard","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1287\/moor.4.1.60"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012902399824"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109421"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-015-5462-z"},{"key":"ref7","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton","year":"1999"},{"key":"ref8","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver","year":"2014"},{"key":"ref9","first-page":"1531","article-title":"A natural policy gradient","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kakade","year":"2001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1968.1098829"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/11085267X"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-018-9602-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-018-9865-9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/19M1236758"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3085510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.11.034"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1137\/0305004"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6544\/ac337f"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3905379"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0949-2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1718942115"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.spa.2004.01.001"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1214\/105051605000000412"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-019-00908-3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-018-00903-0"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1214\/07-AAP448"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1466-3"},{"volume-title":"Probability and Potentials","year":"1966","author":"Meyer","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.2307\/1999343"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref34","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"Theodorou","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-013-4954-y"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2414811"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2547979"},{"key":"ref38","article-title":"Novas: Non-convex optimization via adaptive stochastic search for end-to-end learning and control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Exarchos","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-1665-8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89500-8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91578-4"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.09.004"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-022-01979-5"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1137\/s0036144500378302"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref46","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sutskever","year":"2013"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-6051-6"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10614334\/10366876.pdf?arnumber=10366876","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T05:03:03Z","timestamp":1722315783000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10366876\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":47,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tac.2023.3344870","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"type":"print","value":"0018-9286"},{"type":"electronic","value":"1558-2523"},{"type":"electronic","value":"2334-3303"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}