{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:54:36Z","timestamp":1755798876417},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Syst Sci Complex"],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1007\/s11424-023-1352-4","type":"journal-article","created":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T22:02:26Z","timestamp":1681941746000},"page":"591-612","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Optimal Control of Unknown Discrete-Time Linear Systems with Additive Noise"],"prefix":"10.1007","volume":"36","author":[{"given":"Xue","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,19]]},"reference":[{"key":"1352_CR1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631","volume-title":"Optimal Control","author":"F L Lewis","year":"2012","unstructured":"Lewis F L, Vrabie D L, and Syrmos V L, Optimal Control, John Wiley & Sons Inc., Hoboken, 2012."},{"issue":"6","key":"1352_CR2","doi-asserted-by":"publisher","first-page":"1041","DOI":"10.1007\/s11424-012-1257-0","volume":"25","author":"J Guo","year":"2012","unstructured":"Guo J, Zhang J F, and Zhao Y L, Adaptive tracking of a class of first-order systems with binary-valued observations and fixed thresholds, Journal of Systems Science and Complexity, 2012, 25(6): 1041\u20131051.","journal-title":"Journal of Systems Science and Complexity"},{"issue":"2","key":"1352_CR3","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11424-015-3310-2","volume":"28","author":"Y Jiang","year":"2015","unstructured":"Jiang Y and Jiang Z P, A robust adaptive dynamic programming principle for sensorimotor control with signal-dependent noise, Journal of Systems Science and Complexity, 2015, 28(2): 261\u2013288.","journal-title":"Journal of Systems Science and Complexity"},{"issue":"3","key":"1352_CR4","first-page":"315","volume":"16","author":"H F Chen","year":"2003","unstructured":"Chen H F, Noisy observation based stabilization and optimization for unknown systems, Journal of Systems Science and Complexity, 2003, 16(3): 315\u2013326.","journal-title":"Journal of Systems Science and Complexity"},{"issue":"3","key":"1352_CR5","first-page":"254","volume":"4","author":"Q Y Tang","year":"1991","unstructured":"Tang Q Y and Chen H F, Optimal adaptive control with constraint for ARMAX model, Journal of Systems Science and Complexity, 1991, 4(3): 254\u2013263.","journal-title":"Journal of Systems Science and Complexity"},{"issue":"12","key":"1352_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-018-9865-9","volume":"62","author":"X X Li","year":"2019","unstructured":"Li X X, Peng Z H, Jiao L, et al., Online adaptive Q-learning method for fully cooperative linear quadratic dynamic games, Science China Information Sciences, 2019, 62(12): 1\u201314.","journal-title":"Science China Information Sciences"},{"key":"1352_CR7","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.automatica.2016.12.009","volume":"78","author":"B Kiumarsi","year":"2017","unstructured":"Kiumarsi B, Lewis F L, and Jiang Z P, H\u221e control of linear discrete-time systems: Off-policy reinforcement learning, Automatica, 2017, 78: 144\u2013152.","journal-title":"Automatica"},{"issue":"1","key":"1352_CR8","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TSMCB.2010.2043839","volume":"41","author":"F L Lewis","year":"2010","unstructured":"Lewis F L and Vamvoudakis K G, Reinforcement learning for partially observable dynamic processes: Adaptive dynamic programming using measured output data, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2010, 41(1): 14\u201325.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)"},{"issue":"5","key":"1352_CR9","doi-asserted-by":"publisher","first-page":"1523","DOI":"10.1109\/TNNLS.2018.2870075","volume":"30","author":"S A A Rizvi","year":"2018","unstructured":"Rizvi S A A and Lin Z L, Output feedback Q-learning control for the discrete-time linear quadratic regulator problem, IEEE Transactions on Neural Networks and Learning Systems, 2018, 30(5): 1523\u20131536.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"4","key":"1352_CR10","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.1016\/j.automatica.2014.02.015","volume":"50","author":"B Kiumarsi","year":"2014","unstructured":"Kiumarsi B, Lewis F L, Modares H, et al., Reinforcement Q-learning for optimal tracking control of linear discrete-time systems with unknown dynamics, Automatica, 2014, 50(4): 1167\u20131175.","journal-title":"Automatica"},{"issue":"10","key":"1352_CR11","doi-asserted-by":"publisher","first-page":"4607","DOI":"10.1109\/TNNLS.2017.2771459","volume":"29","author":"Y Jiang","year":"2017","unstructured":"Jiang Y, Fan J L, Chai T Y, et al., Tracking control for linear discrete-time networked control systems with unknown dynamics and dropout, IEEE Transactions on Neural Networks and Learning Systems, 2017, 29(10): 4607\u20134620.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"1","key":"1352_CR12","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1109\/TSMCB.2004.840124","volume":"35","author":"P He","year":"2005","unstructured":"He P and Jagannathan S, Reinforcement learning-based output feedback control of nonlinear systems with input constraints, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2005, 35(1): 150\u2013154.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)"},{"issue":"12","key":"1352_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-015-5462-z","volume":"58","author":"Q L Wei","year":"2015","unstructured":"Wei Q L and Liu D R, A novel policy iteration based deterministic Q-learning for discrete-time nonlinear systems, Science China Information Sciences, 2015, 58(12): 1\u201315.","journal-title":"Science China Information Sciences"},{"issue":"5","key":"1352_CR14","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1109\/TSMC.2015.2466191","volume":"46","author":"D Wang","year":"2015","unstructured":"Wang D, Liu D R, Li H L, et al., An approximate optimal control approach for robust stabilization of a class of discrete-time nonlinear systems with uncertainties, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2015, 46(5): 713\u2013717.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"1352_CR15","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.neucom.2017.12.007","volume":"282","author":"R R Liu","year":"2018","unstructured":"Liu R R, Li Y, and Liu X K, Linear-quadratic optimal control for unknown mean-field stochastic discrete-time system via adaptive dynamic programming approach, Neurocomputing, 2018, 282: 16\u201324.","journal-title":"Neurocomputing"},{"issue":"2","key":"1352_CR16","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1002\/asjc.2276","volume":"23","author":"X K Liu","year":"2021","unstructured":"Liu X K, Liu R R, and Li Y, Infinite time linear quadratic stackelberg game problem for unknown stochastic discrete-time systems via adaptive dynamic programming approach, Asian Journal of Control, 2021, 23(2): 937\u2013948.","journal-title":"Asian Journal of Control"},{"issue":"1","key":"1352_CR17","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1109\/LCSYS.2020.3001883","volume":"5","author":"B Gravell","year":"2020","unstructured":"Gravell B, Ganapathy K, and Summers T, Policy iteration for linear quadratic games with stochastic parameters, IEEE Control Systems Letters, 2020, 5(1): 307\u2013312.","journal-title":"IEEE Control Systems Letters"},{"issue":"7","key":"1352_CR18","doi-asserted-by":"publisher","first-page":"1977","DOI":"10.1109\/TCYB.2017.2726004","volume":"48","author":"J S Wang","year":"2017","unstructured":"Wang J S and Yang G H, Output-feedback control of unknown linear discrete-time systems with stochastic measurement and process noise via approximate dynamic programming, IEEE Transactions on Cybernetics, 2017, 48(7): 1977\u20131988.","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"13","key":"1352_CR19","doi-asserted-by":"publisher","first-page":"5280","DOI":"10.1016\/j.jfranklin.2017.06.017","volume":"354","author":"K Z Han","year":"2017","unstructured":"Han K Z, Feng J, and Yao Y, An integrated data-driven Markov parameters sequence identification and adaptive dynamic programming method to design fault-tolerant optimal tracking control for completely unknown model systems, Journal of the Franklin Institute, 2017, 354(13): 5280\u20135301.","journal-title":"Journal of the Franklin Institute"},{"issue":"4","key":"1352_CR20","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1002\/oca.915","volume":"31","author":"W C Wong","year":"2010","unstructured":"Wong W C and Lee J H, A reinforcement learning-based scheme for direct adaptive optimal control of linear stochastic systems, Optimal Control Applications and Methods, 2010, 31(4): 365\u2013374.","journal-title":"Optimal Control Applications and Methods"},{"key":"1352_CR21","first-page":"6510","volume-title":"Using reinforcement learning for model-free linear quadratic control with process and measurement noises","author":"F A Yaghmaie","year":"2019","unstructured":"Yaghmaie F A and Gustafsson F, Using reinforcement learning for model-free linear quadratic control with process and measurement noises, Proceedings of the 58th IEEE Conference on Decision and Control (CDC), Nice, France, Dec. 11\u201313, 2019, 6510\u20136517."},{"key":"1352_CR22","first-page":"3108","volume-title":"Model-free linear quadratic control via reduction to expert prediction","author":"Y Abbasi-Yadkori","year":"2019","unstructured":"Abbasi-Yadkori Y, Lazi\u0107 N, and Szepesv\u00e1ri C, Model-free linear quadratic control via reduction to expert prediction, Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), Okinawa, Japan, Apr. 16\u201318, 2019, 3108\u20133117."},{"issue":"12","key":"1352_CR23","doi-asserted-by":"publisher","first-page":"6202","DOI":"10.1109\/TNNLS.2018.2820019","volume":"29","author":"X Xu","year":"2018","unstructured":"Xu X, Chen H, Lian C Q, et al., Learning-based predictive control for discrete-time nonlinear systems with stochastic disturbances, IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(12): 6202\u20136213.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"11","key":"1352_CR24","doi-asserted-by":"publisher","first-page":"3972","DOI":"10.1109\/TSMC.2019.2907991","volume":"50","author":"M M Liang","year":"2019","unstructured":"Liang M M, Wang D, and Liu D R, Neuro-optimal control for discrete stochastic processes via a novel policy iteration algorithm, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019, 50(11): 3972\u20133985.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"1352_CR25","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.neunet.2020.01.004","volume":"124","author":"M M Liang","year":"2020","unstructured":"Liang M M, Wang D, and Liu D R, Improved value iteration for neural-network-based stochastic optimal control design, Neural Networks, 2020, 124: 280\u2013295.","journal-title":"Neural Networks"},{"issue":"2","key":"1352_CR26","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1142\/S1465876301000337","volume":"2","author":"F M\u2019sahli","year":"2001","unstructured":"M\u2019sahli F, Fayeche C, Abdennour R B, et al., Application of adaptive controllers for the temperature control of a semi-batch reactor, International Journal of Computational Engineering Science, 2001, 2(2): 287\u2013307.","journal-title":"International Journal of Computational Engineering Science"},{"issue":"1","key":"1352_CR27","doi-asserted-by":"publisher","first-page":"19","DOI":"10.4310\/CIS.2003.v3.n1.a2","volume":"3","author":"S M Haas","year":"2003","unstructured":"Haas S M, Frei M G, Osorio I, et al., EEG ocular artifact removal through ARMAX model system identification using extended least squares, Communications in Information and Systems, 2003, 3(1): 19\u201340.","journal-title":"Communications in Information and Systems"},{"issue":"2","key":"1352_CR28","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1109\/TPAMI.2013.218","volume":"37","author":"M P Deisenroth","year":"2013","unstructured":"Deisenroth M P, Fox D, and Rasmussen C E, Gaussian processes for data-efficient learning in robotics and control, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 37(2): 408\u2013423.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"1352_CR29","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1023\/A:1008256409920","volume":"8","author":"S P Sethi","year":"1998","unstructured":"Sethi S P, Suo W, Taksar M I, et al., Optimal production planning in a multi-product stochastic manufacturing system with long-run average cost, Discrete Event Dynamic Systems, 1998, 8(1): 37\u201354.","journal-title":"Discrete Event Dynamic Systems"},{"key":"1352_CR30","doi-asserted-by":"crossref","unstructured":"Borkar V S, Ergodic control of diffusion processes, Proceedings of the International Congress of Mathematicians (ICM), Madrid, Spain, 2006: 1299\u20131309.","DOI":"10.4171\/022-3\/62"},{"issue":"3","key":"1352_CR31","doi-asserted-by":"publisher","first-page":"869","DOI":"10.1080\/00207178608933508","volume":"43","author":"H F Chen","year":"1986","unstructured":"Chen H F and Guo L, Optimal stochastic adaptive control with quadratic index, International Journal of Control, 1986, 43(3): 869\u2013881.","journal-title":"International Journal of Control"},{"issue":"4","key":"1352_CR32","first-page":"289","volume":"7","author":"H F Chen","year":"1987","unstructured":"Chen H F and Guo L, Stochastic adaptive control for a general quadratic cost, Journal of Systems Science and Mathematical Sciences, 1987, 7(4): 289\u2013302.","journal-title":"Journal of Systems Science and Mathematical Sciences"},{"issue":"1","key":"1352_CR33","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1109\/9.481609","volume":"41","author":"L Guo","year":"1996","unstructured":"Guo L, Self-convergence of weighted least-squares with applications to stochastic adaptive control, IEEE Transactions on Automatic Control, 1996, 41(1): 79\u201389.","journal-title":"IEEE Transactions on Automatic Control"},{"issue":"2","key":"1352_CR34","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1109\/37.126844","volume":"12","author":"R S Sutton","year":"1992","unstructured":"Sutton R S, Barto A G, and Williams R J, Reinforcement learning is direct adaptive optimal control, IEEE Control Systems Magazine, 1992, 12(2): 19\u201322.","journal-title":"IEEE Control Systems Magazine"},{"issue":"3","key":"1352_CR35","first-page":"464","volume":"27","author":"C Q Ma","year":"2007","unstructured":"Ma C Q, Li T, and Zhang J F, Linear quadratic decentralized dynamic games for large population discrete-time stochastic multi-agent systems, Journal of Systems Science and Mathematical Sciences, 2007, 27(3): 464\u2013480.","journal-title":"Journal of Systems Science and Mathematical Sciences"},{"key":"1352_CR36","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0429-9","volume-title":"Identification and Stochastic Adaptive Control","author":"H F Chen","year":"1991","unstructured":"Chen H F and Guo L, Identification and Stochastic Adaptive Control, Springer Science & Business Media, New York, 1991."},{"key":"1352_CR37","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.automatica.2016.05.008","volume":"72","author":"W N Gao","year":"2016","unstructured":"Gao W N, Jiang Y, Jiang Z P, et al., Output-feedback adaptive optimal control of interconnected systems based on robust adaptive dynamic programming, Automatica, 2016, 72: 37\u201345.","journal-title":"Automatica"},{"key":"1352_CR38","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198537953.001.0001","volume-title":"Algebraic Riccati Equations","author":"P Lancaster","year":"1995","unstructured":"Lancaster P and Rodman L, Algebraic Riccati Equations, Oxford University Press Inc., New York, 1995."}],"container-title":["Journal of Systems Science and Complexity"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11424-023-1352-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11424-023-1352-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11424-023-1352-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T00:33:13Z","timestamp":1702254793000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11424-023-1352-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":38,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["1352"],"URL":"https:\/\/doi.org\/10.1007\/s11424-023-1352-4","relation":{},"ISSN":["1009-6124","1559-7067"],"issn-type":[{"value":"1009-6124","type":"print"},{"value":"1559-7067","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4]]},"assertion":[{"value":"18 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}