{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:13:06Z","timestamp":1755792786351,"version":"3.44.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T00:00:00Z","timestamp":1480550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T00:00:00Z","timestamp":1480550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/ssci.2016.7849841","type":"proceedings-article","created":{"date-parts":[[2017,2,16]],"date-time":"2017-02-16T17:24:33Z","timestamp":1487265873000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Iterative Q-learning-based nonlinear optimal tracking control"],"prefix":"10.1109","author":[{"given":"Qinglai","family":"Wei","sequence":"first","affiliation":[{"name":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruizhuo","family":"Song","sequence":"additional","affiliation":[{"name":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, 100083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yancai","family":"Xu","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Derong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, 100083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.05.011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2276571"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2401334"},{"journal-title":"Improving the closed-loop performance of nonlinear systems","year":"1995","author":"beard","key":"ref36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2542923"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2014.2310238"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281663"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2354377"},{"key":"ref15","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 Transactions on Cybernetics"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2014.2301770"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2399020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2014.2361485"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2464080"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2015.04.044"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2002.801727"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2542923"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2012.2214134"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2492242"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-015-5462-z"},{"key":"ref5","article-title":"Off-policy actorcritic structure for optimal control of unknown systems with disturbances","author":"song","year":"2015","journal-title":"IEEE Transactions on Cybernetics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2203336"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2011.03.005"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"67","DOI":"10.7551\/mitpress\/4939.003.0007","article-title":"A menu of designs for reinforcement learning over time","author":"werbos","year":"1991","journal-title":"Neural Networks for Control"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.10.033"},{"key":"ref1","first-page":"25","article-title":"Advanced forecasting methods for global crisis warning and models of intelligence","volume":"22","author":"werbos","year":"1977","journal-title":"General Systems Yearbook"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2284545"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1088\/1674-1056\/24\/9\/090504"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.05.075"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2586082"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2593743"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2280974"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2014.2388198"}],"event":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","start":{"date-parts":[[2016,12,6]]},"location":"Athens, Greece","end":{"date-parts":[[2016,12,9]]}},"container-title":["2016 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7840087\/7849361\/07849841.pdf?arnumber=7849841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T18:44:04Z","timestamp":1755197044000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7849841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/ssci.2016.7849841","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}