{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:50:07Z","timestamp":1758271807033,"version":"3.37.3"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"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":["62273234"],"award-info":[{"award-number":["62273234"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tsmc.2023.3327450","type":"journal-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T19:04:08Z","timestamp":1699643048000},"page":"1489-1501","source":"Crossref","is-referenced-by-count":4,"title":["Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear Systems With Trajectory-Based Initial Control Policy"],"prefix":"10.1109","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4058-0447","authenticated-orcid":false,"given":"Jiahui","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4277-1263","authenticated-orcid":false,"given":"Jingcheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7467-4898","authenticated-orcid":false,"given":"Jun","family":"Rao","sequence":"additional","affiliation":[{"name":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9856-2148","authenticated-orcid":false,"given":"Shunyu","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4361-9378","authenticated-orcid":false,"given":"Yanjiu","family":"Zhong","sequence":"additional","affiliation":[{"name":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.096"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3004717"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3001715"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3183991"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-022-07459-7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2916146"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-021-06177-3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3001840"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977318"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.38.8.716"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICIST.2013.6747522"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2645699"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2821369"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.032"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-021-0473-6"},{"key":"ref17","first-page":"1587","article-title":"Addressing function approximation error in actor\u2013critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref18","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Stat.","author":"Glorot"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/asjc.2552"},{"key":"ref20","first-page":"1","article-title":"What matters for on-policy deep actor\u2013critic methods? A large-scale study","volume-title":"Proc. ICLR","author":"Andrychowicz"},{"key":"ref21","first-page":"146","article-title":"Input convex neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amos"},{"key":"ref22","first-page":"136","article-title":"OptNet: Differentiable optimization as a layer in neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amos"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.546"},{"key":"ref24","first-page":"1","article-title":"End-to-end differentiable physics for learning and control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"de Avila Belbute-Peres"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2020.104847"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-8232-3"},{"volume-title":"Elementary Differential Equations and Boundary Value Problems","year":"2021","author":"Boyce","key":"ref27"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3106402"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109687"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3105663"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3108034"},{"volume-title":"Gurobi Optimizer Reference Manual","year":"2022","key":"ref34"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/10438110\/10314539.pdf?arnumber=10314539","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T17:12:39Z","timestamp":1709399559000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10314539\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":34,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2023.3327450","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"type":"print","value":"2168-2216"},{"type":"electronic","value":"2168-2232"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}