{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:12:43Z","timestamp":1775913163434,"version":"3.50.1"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":["61333002"],"award-info":[{"award-number":["61333002"]}],"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":["61873028"],"award-info":[{"award-number":["61873028"]}],"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":["61473032"],"award-info":[{"award-number":["61473032"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["FRF-TP-18-031A1"],"award-info":[{"award-number":["FRF-TP-18-031A1"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["FRF-BD-17-002A"],"award-info":[{"award-number":["FRF-BD-17-002A"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2018M641197"],"award-info":[{"award-number":["2018M641197"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1850851"],"award-info":[{"award-number":["CNS-1850851"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Mary K. Finley Endowment"},{"DOI":"10.13039\/100014575","name":"Intelligent Systems Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014575","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-18-2-0260"],"award-info":[{"award-number":["W911NF-18-2-0260"]}],"id":[{"id":"10.13039\/100006754","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":[[2019,12]]},"DOI":"10.1109\/tnnls.2019.2897814","type":"journal-article","created":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T19:56:16Z","timestamp":1551470176000},"page":"3735-3747","source":"Crossref","is-referenced-by-count":88,"title":["Data-Driven Robust Control of Discrete-Time Uncertain Linear Systems via Off-Policy Reinforcement Learning"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3144-8604","authenticated-orcid":false,"given":"Yongliang","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5967-1058","authenticated-orcid":false,"given":"Zhishan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyi","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1201-7785","authenticated-orcid":false,"given":"Da-Wei","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6056-8878","authenticated-orcid":false,"given":"Yixin","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9726-9051","authenticated-orcid":false,"given":"Donald C.","family":"Wunsch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1002\/0471459100"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2626967"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.07.004"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.05.017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2803059"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.12.009"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139020411"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/MCS.2016.2621461","article-title":"Game theory-based control system algorithms with real-time reinforcement learning: How to solve multiplayer games online","volume":"37","author":"vamvoudakis","year":"2017","journal-title":"IEEE Control Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2018.2794336"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/9780470059579"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"ref12","first-page":"493","article-title":"Approximate dynamic programming for real-time control and neural modeling","author":"werbos","year":"1992","journal-title":"Handbook of Intelligent Control"},{"key":"ref13","author":"werbos","year":"1994","journal-title":"The Roots of Backpropagation From Ordered Derivatives to Neural Networks and Political Forecasting"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.05.031"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2247627"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2654324"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281663"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2441749"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2582747"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.096"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/9781119113072"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1981.1102555"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2319577"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2018.2849701"},{"key":"ref8","author":"boyd","year":"1991","journal-title":"Linear Controller Design Limits of Performance"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1981.1102603"},{"key":"ref2","volume":"36","author":"dullerud","year":"2013","journal-title":"A Course in Robust Control Theory A Convex Approach"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/9.29425"},{"key":"ref1","author":"zhou","year":"1998","journal-title":"Essentials of Robust Control"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.09.019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2511658"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2276571"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref23","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511794797"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/8930649\/8657370-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8930649\/08657370.pdf?arnumber=8657370","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:49:29Z","timestamp":1657745369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8657370\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":39,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2019.2897814","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12]]}}}