{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:05:25Z","timestamp":1777489525957,"version":"3.51.4"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"International Science and Technology Cooperation Program of China","award":["2019YFE0100200"],"award-info":[{"award-number":["2019YFE0100200"]}]},{"name":"Tsinghua University-Toyota Joint Research Center for AI Technology of Automated Vehicle"},{"DOI":"10.13039\/501100001809","name":"NSF China","doi-asserted-by":"publisher","award":["51575293"],"award-info":[{"award-number":["51575293"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSF China","doi-asserted-by":"publisher","award":["U20A20334"],"award-info":[{"award-number":["U20A20334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSF China","doi-asserted-by":"publisher","award":["52202487"],"award-info":[{"award-number":["52202487"]}],"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":[[2023,9]]},"DOI":"10.1109\/tnnls.2022.3225090","type":"journal-article","created":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T22:32:24Z","timestamp":1670279544000},"page":"5255-5267","source":"Crossref","is-referenced-by-count":17,"title":["Policy-Iteration-Based Finite-Horizon Approximate Dynamic Programming for Continuous-Time Nonlinear Optimal Control"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0532-0030","authenticated-orcid":false,"given":"Ziyu","family":"Lin","sequence":"first","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3697-1576","authenticated-orcid":false,"given":"Jingliang","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4923-3633","authenticated-orcid":false,"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9943-0638","authenticated-orcid":false,"given":"Haitong","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3718-5593","authenticated-orcid":false,"given":"Jie","family":"Li","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0282-8621","authenticated-orcid":false,"given":"Jianyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"}]},{"given":"Bo","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9405-8232","authenticated-orcid":false,"given":"Jun","family":"Ma","sequence":"additional","affiliation":[{"name":"Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.08.017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053269"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/int.22491"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.08.004"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/19M1288802"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2461452"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2899594"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.905848"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.11.034"},{"key":"ref11","article-title":"Generalized policy iteration for optimal control in continuous time","author":"duan","year":"2019","journal-title":"arXiv 1909 05402"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ChiCC.2014.6896497"},{"key":"ref10","author":"howard","year":"1960","journal-title":"Dynamic Programming and Markov Processes"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2008.0288"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2904385"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2905715"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50815-3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.04.027"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2514\/6.2022-1584"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5350"},{"key":"ref46","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2511658"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2399020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1080\/00423114.2020.1717553"},{"key":"ref48","volume":"1","author":"kwakernaak","year":"1972","journal-title":"Linear Optimal Control Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2018.01.010"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-018-0139-4"},{"key":"ref25","article-title":"Local learning enabled iterative linear quadratic regulator for constrained trajectory planning","author":"ma","year":"2022","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCR49711.2021.9349412"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICUS50048.2020.9274944"},{"key":"ref41","first-page":"1675","article-title":"Gradient descent finds global minima of deep neural networks","author":"du","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2669944"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3010620"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2539366"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.4271\/870421"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2013.07.002"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.03.022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.09.021"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1002\/9780470182963","volume":"703","author":"powell","year":"2007","journal-title":"Approximate Dynamic Programming Solving the Curses of Dimensionality"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-44184-5_100063"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3094215"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3194571"},{"key":"ref6","article-title":"Approximate dynamic programming for realtime control and neural modeling","author":"werbos","year":"1992","journal-title":"Handbook of Intelligent Control Neural Fuzzy and Adaptive Approaches"},{"key":"ref5","volume":"1","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref40","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","author":"allen-zhu","year":"2019","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10237282\/09970403.pdf?arnumber=9970403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:27:04Z","timestamp":1695666424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9970403\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":48,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3225090","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}