{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T03:51:17Z","timestamp":1793245877390,"version":"4.5.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2016,5,1]],"date-time":"2016-05-01T00:00:00Z","timestamp":1462060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61304079"],"award-info":[{"award-number":["61304079"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61374105"],"award-info":[{"award-number":["61374105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61433004"],"award-info":[{"award-number":["61433004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"crossref","award":["4132078"],"award-info":[{"award-number":["4132078"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"crossref","award":["4143065"],"award-info":[{"award-number":["4143065"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002858","name":"China Post-Doctoral Science Foundation","doi-asserted-by":"publisher","award":["2013M530527"],"award-info":[{"award-number":["2013M530527"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["FRF-TP-14-119A2"],"award-info":[{"award-number":["FRF-TP-14-119A2"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Open Research Project from The State Key Laboratory of Management and Control for Complex Systems","award":["20120106"],"award-info":[{"award-number":["20120106"]}]},{"name":"Open Research Project from The State Key Laboratory of Management and Control for Complex Systems","award":["20150104"],"award-info":[{"award-number":["20150104"]}]},{"DOI":"10.13039\/100000148","name":"NSF","doi-asserted-by":"publisher","award":["ECCS-1128050"],"award-info":[{"award-number":["ECCS-1128050"]}],"id":[{"id":"10.13039\/100000148","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-13-1-0562"],"award-info":[{"award-number":["N00014-13-1-0562"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Air Force Office of Scientific Research through the European Office of Aerospace Research and Development","award":["13-3055"],"award-info":[{"award-number":["13-3055"]}],"id":[{"id":"https:\/\/ror.org\/04krhg278","id-type":"ROR","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000183","name":"U.S. Army Research Office","doi-asserted-by":"crossref","award":["W911NF-11-D-0001"],"award-info":[{"award-number":["W911NF-11-D-0001"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"China National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61120106011"],"award-info":[{"award-number":["61120106011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"China Education Ministry Project 111","award":["B08015"],"award-info":[{"award-number":["B08015"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2016,5]]},"DOI":"10.1109\/tcyb.2015.2421338","type":"journal-article","created":{"date-parts":[[2015,4,28]],"date-time":"2015-04-28T14:37:14Z","timestamp":1430231834000},"page":"1041-1050","source":"Crossref","is-referenced-by-count":225,"title":["Off-Policy Actor-Critic Structure for Optimal Control of Unknown Systems With Disturbances"],"prefix":"10.1109","volume":"46","author":[{"given":"Ruizhuo","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frank L.","family":"Lewis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinglai","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaguang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.11.034"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(97)00128-3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2013.2271276"},{"key":"ref31","author":"sutton","year":"2005","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5718152"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2294968"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.096"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2319577"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2300532"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2247627"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1979.4310171"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2012.0486"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.027"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2354377"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2168538"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.03.038"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2313915"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2284545"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2303139"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426987"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.09.019"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1109\/TSMCB.2012.2216523","article-title":"Finite-approximation-error-based optimal control approach for discrete-time nonlinear systems","volume":"43","author":"liu","year":"2013","journal-title":"IEEE Trans Cybern"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2012.2214134"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920269"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2010.07.005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-011-0166-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2227339"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2236354"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2399020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.10.033"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2401334"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2012.2213353"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2010.2043839"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2263131"},{"key":"ref42","author":"lewis","year":"1999","journal-title":"Neural Network Control of Robot Manipulators and Nonlinear Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.008"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1262"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2306201"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/9.119645"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.08.017"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1109\/TNNLS.2013.2281663","article-title":"Policy iteration adaptive dynamic programming algorithm for discrete-time nonlinear systems","volume":"25","author":"liu","year":"2014","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.02.015"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/7452443\/07097024.pdf?arnumber=7097024","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T10:58:51Z","timestamp":1641985131000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7097024\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,5]]},"references-count":44,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2015.2421338","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,5]]}}}