{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T10:27:39Z","timestamp":1782728859402,"version":"3.54.5"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62001359"],"award-info":[{"award-number":["62001359"]}],"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":["ZYTS23163"],"award-info":[{"award-number":["ZYTS23163"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["22102240014"],"award-info":[{"award-number":["22102240014"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["232102211059"],"award-info":[{"award-number":["232102211059"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["232102211047"],"award-info":[{"award-number":["232102211047"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s10489-023-05184-1","type":"journal-article","created":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T12:02:06Z","timestamp":1701777726000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Safe optimal robust control of nonlinear systems with asymmetric input constraints using reinforcement learning"],"prefix":"10.1007","volume":"54","author":[{"given":"Dehua","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaijun","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linlin","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,12,5]]},"reference":[{"issue":"1","key":"5184_CR1","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TSMC.2020.3042876","volume":"51","author":"D Liu","year":"2020","unstructured":"Liu D, Xue S, Zhao B, Luo B, Wei Q (2020) Adaptive dynamic programming for control: a survey and recent advances. IEEE Transactions on Systems, Man, and Cybernetics: Systems 51(1):142\u2013160","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"issue":"8","key":"5184_CR2","doi-asserted-by":"publisher","first-page":"7362","DOI":"10.1109\/TIE.2020.3001840","volume":"68","author":"D Wang","year":"2020","unstructured":"Wang D, Ha M, Qiao J (2020) Data-driven iterative adaptive critic control toward an urban wastewater treatment plant. IEEE Trans Industr Electron 68(8):7362\u20137369","journal-title":"IEEE Trans Industr Electron"},{"issue":"1","key":"5184_CR3","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1109\/TCYB.2020.2977318","volume":"52","author":"D Wang","year":"2020","unstructured":"Wang D, Qiao J, Cheng L (2020) An approximate neuro-optimal solution of discounted guaranteed cost control design. IEEE Transactions on Cybernetics 52(1):77\u201386","journal-title":"IEEE Transactions on Cybernetics"},{"key":"5184_CR4","doi-asserted-by":"crossref","unstructured":"Wang D, Li X, Zhao M, Qiao J (2023) Adaptive critic control design with knowledge transfer for wastewater treatment applications. IEEE Transactions on industrial informatics","DOI":"10.1109\/TII.2023.3278875"},{"key":"5184_CR5","doi-asserted-by":"crossref","unstructured":"Wei Q, Zhou T, Lu J, Liu Y, Su S, Xiao J (2023) Continuous-time stochastic policy iteration of adaptive dynamic programming. IEEE Transactions on Systems, Man, and Cybernetics: Systems","DOI":"10.1109\/TSMC.2023.3284612"},{"key":"5184_CR6","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/j.neucom.2022.07.072","volume":"506","author":"C Qin","year":"2022","unstructured":"Qin C, Wang J, Zhu H, Zhang J, Hu S, Zhang D (2022) Neural network-based safe optimal robust control for affine nonlinear systems with unmatched disturbances. Neurocomputing 506:228\u2013239","journal-title":"Neurocomputing"},{"issue":"1","key":"5184_CR7","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/TSMC.2022.3173275","volume":"53","author":"R Song","year":"2022","unstructured":"Song R, Liu L, Xia L, Lewis FL (2022) Online optimal event-triggered h$$\\infty $$ control for nonlinear systems with constrained state and input. IEEE Transactions on Systems, Man, and Cybernetics: Systems 53(1):131\u2013141","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"issue":"3731","key":"5184_CR8","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1126\/science.153.3731.34","volume":"153","author":"R Bellman","year":"1966","unstructured":"Bellman R (1966) Dynamic programming. Science 153(3731):34\u201337","journal-title":"Science"},{"key":"5184_CR9","unstructured":"Werbos P (1977) Advanced forecasting methods for global crisis warning and models of intelligence. Gen Syst Yearb 25\u201338"},{"key":"5184_CR10","doi-asserted-by":"crossref","unstructured":"Chauhan S, Singh M, Aggarwal AK (2023) Designing of optimal digital IIR filter in the multi-objective framework using an evolutionary algorithm. Eng Appl Artif Intell 119:105803","DOI":"10.1016\/j.engappai.2022.105803"},{"key":"5184_CR11","doi-asserted-by":"crossref","unstructured":"Chauhan S, Singh M, Aggarwal AK (2021) Experimental analysis of effect of tuning parameters on the performance of diversity-driven multi-parent evolutionary algorithm. In:2021 IEEE 2Nd International conference on electrical power and energy systems (ICEPES). IEEE, pp 1\u20136","DOI":"10.1109\/ICEPES52894.2021.9699655"},{"key":"5184_CR12","doi-asserted-by":"crossref","unstructured":"Chauhan S, Singh M, Aggarwal AK (2023) Investigative analysis of different mutation on diversity-driven multi-parent evolutionary algorithm and its application in area coverage optimization of WSN. Soft Comput 1\u201327","DOI":"10.1007\/s00500-023-08090-3"},{"key":"5184_CR13","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.neucom.2021.04.133","volume":"484","author":"N Wang","year":"2022","unstructured":"Wang N, Gao Y, Yang C, Zhang X (2022) Reinforcement learning-based finite-time tracking control of an unknown unmanned surface vehicle with input constraints. Neurocomputing 484:26\u201337","journal-title":"Neurocomputing"},{"key":"5184_CR14","unstructured":"Sun J, Zhang H, Yan Y, Xu S, Fan X (2021) Optimal regulation strategy for nonzero-sum games of the immune system using adaptive dynamic programming. IEEE Transactions on cybernetics"},{"key":"5184_CR15","doi-asserted-by":"publisher","first-page":"756","DOI":"10.1016\/j.ins.2021.08.062","volume":"580","author":"H Zhang","year":"2021","unstructured":"Zhang H, Wang H, Niu B, Zhang L, Ahmad AM (2021) Sliding-mode surface-based adaptive actor-critic optimal control for switched nonlinear systems with average dwell time. Inf Sci 580:756\u2013774","journal-title":"Inf Sci"},{"issue":"5","key":"5184_CR16","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1016\/j.automatica.2010.02.018","volume":"46","author":"KG Vamvoudakis","year":"2010","unstructured":"Vamvoudakis KG, Lewis FL (2010) Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem. Automatica 46(5):878\u2013888","journal-title":"Automatica"},{"key":"5184_CR17","doi-asserted-by":"crossref","unstructured":"Li D, Dong J (2022) Fuzzy control based on reinforcement learning and subsystem error derivatives for strict-feedback systems with an observer. IEEE Transactions on Fuzzy Systems","DOI":"10.1109\/TFUZZ.2022.3227993"},{"key":"5184_CR18","doi-asserted-by":"crossref","unstructured":"Li D, Dong J (2023) Fuzzy weight-based reinforcement learning for event-triggered optimal backstepping control of fractional-order nonlinear systems. IEEE Transactions on Fuzzy Systems","DOI":"10.1109\/TFUZZ.2023.3294928"},{"issue":"12","key":"5184_CR19","doi-asserted-by":"publisher","first-page":"7466","DOI":"10.1109\/TSMC.2020.2970040","volume":"51","author":"X Huang","year":"2020","unstructured":"Huang X, Dong J (2020) ADP-based robust resilient control of partially unknown nonlinear systems via cooperative interaction design. IEEE Transactions on Systems, Man, and Cybernetics: Systems 51(12):7466\u20137474","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"5184_CR20","doi-asserted-by":"crossref","unstructured":"Wang K, Mu C, Ni Z, Liu D (2023) Safe reinforcement learning and adaptive optimal control with applications to obstacle avoidance problem. IEEE Transactions on Automation Science and Engineering","DOI":"10.1109\/TASE.2023.3299275"},{"key":"5184_CR21","doi-asserted-by":"crossref","unstructured":"Farzanegan B, Jagannathan S (2023) Continual reinforcement learning formulation for zero-sum game-based constrained optimal tracking. IEEE Transactions on Systems, Man, and Cybernetics: Systems","DOI":"10.1109\/TSMC.2023.3299556"},{"issue":"6","key":"5184_CR22","doi-asserted-by":"publisher","first-page":"1923","DOI":"10.1002\/rnc.5132","volume":"31","author":"Z Marvi","year":"2021","unstructured":"Marvi Z, Kiumarsi B (2021) Safe reinforcement learning: a control barrier function optimization approach. Int J Robust Nonlinear Control 31(6):1923\u20131940","journal-title":"Int J Robust Nonlinear Control"},{"key":"5184_CR23","doi-asserted-by":"crossref","unstructured":"Qin C, Zhang Z, Shang Z, Zhang J, Zhang D (2023) Adaptive optimal safety tracking control for multiplayer mixed zero-sum games of continuous-time systems. Appl Intell 1\u201316","DOI":"10.1007\/s10489-022-04348-9"},{"key":"5184_CR24","doi-asserted-by":"crossref","unstructured":"Shi L, Wang X, Cheng Y (2023) Safe reinforcement learning-based robust approximate optimal control for hypersonic flight vehicles. IEEE Transactions on vehicular technology","DOI":"10.1109\/TVT.2023.3264243"},{"key":"5184_CR25","doi-asserted-by":"crossref","unstructured":"Qin C, Qiao X, Wang J, Zhang D, Hou Y, Hu, S (2023) Barrier-Critic adaptive robust control of nonzero-sum differential games for uncertain nonlinear systems with state constraints. IEEE Transactions on Systems, Man, and Cybernetics: Systems","DOI":"10.1109\/TSMC.2023.3302656"},{"key":"5184_CR26","unstructured":"Zhang Y, Zhao B, Liu D, Zhang S (2022) Adaptive dynamic programming-based event-triggered robust control for multiplayer nonzero-sum games with unknown dynamics1-4mmplease verify and confirm the term \u201cmulti-player\u201d has been changed to \u201cmultiplayer\u201d in the title of this article. IEEE Transactions on Cybernetics"},{"key":"5184_CR27","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.neucom.2021.10.081","volume":"471","author":"J Zhao","year":"2022","unstructured":"Zhao J, Na J, Gao G (2022) Robust tracking control of uncertain nonlinear systems with adaptive dynamic programming. Neurocomputing 471:21\u201330","journal-title":"Neurocomputing"},{"key":"5184_CR28","doi-asserted-by":"crossref","unstructured":"Yang X, Xu M, Wei Q (2023) Adaptive dynamic programming for nonlinear-constrained h$$\\infty $$ control. IEEE Transactions on Systems, Man, and Cybernetics: Systems","DOI":"10.1109\/TSMC.2023.3247888"},{"key":"5184_CR29","doi-asserted-by":"crossref","unstructured":"Ji R, Ge SS, Li D (2023) Saturation-tolerant prescribed control for nonlinear systems with unknown control directions and external disturbances. IEEE Transactions on Cybernetics","DOI":"10.1109\/TCYB.2023.3244988"},{"key":"5184_CR30","doi-asserted-by":"crossref","unstructured":"Xu S, He B (2023) Robust adaptive fuzzy fault tolerant control of robot manipulators with unknown parameters. IEEE Transactions on fuzzy systems","DOI":"10.1109\/TFUZZ.2023.3244189"},{"key":"5184_CR31","doi-asserted-by":"crossref","unstructured":"Yang M, Ma H, Li X, Shang C, Shen Q (2022) Bus bridging for rail disruptions: a distributionally robust fuzzy optimization approach. IEEE Transactions on Fuzzy Systems","DOI":"10.1109\/TFUZZ.2022.3224789"},{"key":"5184_CR32","doi-asserted-by":"crossref","unstructured":"Gutierrez-Oribio D, Orlov Y, Stefanou I, Plestan F (2022) Robust tracking for the diffusion equation using sliding-mode boundary control. In: 2022 IEEE 61st Conference on decision and control (CDC). IEEE, pp 6076\u20136081","DOI":"10.1109\/CDC51059.2022.9992664"},{"key":"5184_CR33","doi-asserted-by":"crossref","unstructured":"Chen J, Lyu L, Fei Z, Xia W, Sun X-M (2023) Event-triggered adaptive robust control for a class of uncertain nonlinear systems with application to mechatronic system. IEEE Transactions on Industrial Informatics","DOI":"10.1109\/TII.2023.3252543"},{"issue":"2","key":"5184_CR34","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1109\/TII.2019.2923715","volume":"16","author":"N Sun","year":"2019","unstructured":"Sun N, Liang D, Wu Y, Chen Y, Qin Y, Fang Y (2019) Adaptive control for pneumatic artificial muscle systems with parametric uncertainties and unidirectional input constraints. IEEE Trans Industr Inf 16(2):969\u2013979","journal-title":"IEEE Trans Industr Inf"},{"issue":"5","key":"5184_CR35","doi-asserted-by":"publisher","first-page":"4101","DOI":"10.1109\/TIE.2016.2597763","volume":"64","author":"Y Zhu","year":"2016","unstructured":"Zhu Y, Zhao D, He H, Ji J (2016) Event-triggered optimal control for partially unknown constrained-input systems via adaptive dynamic programming. IEEE Trans Industr Electron 64(5):4101\u20134109","journal-title":"IEEE Trans Industr Electron"},{"key":"5184_CR36","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1016\/j.neunet.2022.10.025","volume":"157","author":"Q Wu","year":"2023","unstructured":"Wu Q, Zhao B, Liu D, Polycarpou MM (2023) Event-triggered adaptive dynamic programming for decentralized tracking control of input constrained unknown nonlinear interconnected systems. Neural Netw 157:336\u2013349","journal-title":"Neural Netw"},{"key":"5184_CR37","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.neucom.2018.09.097","volume":"396","author":"S Xue","year":"2020","unstructured":"Xue S, Luo B, Liu D, Li Y (2020) Adaptive dynamic programming based event-triggered control for unknown continuous-time nonlinear systems with input constraints. Neurocomputing 396:191\u2013200","journal-title":"Neurocomputing"},{"issue":"2","key":"5184_CR38","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1109\/JAS.2020.1003063","volume":"7","author":"X Yang","year":"2020","unstructured":"Yang X, Zhao B (2020) Optimal neuro-control strategy for nonlinear systems with asymmetric input constraints. IEEE\/CAA Journal of Automatica Sinica 7(2):575\u2013583","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"issue":"3","key":"5184_CR39","first-page":"1735","volume":"51","author":"L Kong","year":"2019","unstructured":"Kong L, He W, Dong Y, Cheng L, Yang C, Li Z (2019) Asymmetric bounded neural control for an uncertain robot by state feedback and output feedback. IEEE Transactions on Systems, Man, and Cybernetics: Systems 51(3):1735\u20131746","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"5184_CR40","doi-asserted-by":"crossref","unstructured":"Zhao Y, Wang H, Xu N, Zong G, Zhao X (2023) Reinforcement learning-based decentralized fault tolerant control for constrained interconnected nonlinear systems. Chaos, Solitons & Fractals 167:113034","DOI":"10.1016\/j.chaos.2022.113034"},{"key":"5184_CR41","doi-asserted-by":"crossref","unstructured":"Qiao J, Li M, Wang D (2022) Asymmetric constrained optimal tracking control with critic learning of nonlinear multiplayer zero-sum games. IEEE Transactions on Neural Networks and Learning Systems","DOI":"10.1109\/TNNLS.2022.3208611"},{"issue":"1","key":"5184_CR42","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1109\/TNNLS.2020.2976787","volume":"32","author":"X Yang","year":"2020","unstructured":"Yang X, Wei Q (2020) Adaptive critic learning for constrained optimal event-triggered control with discounted cost. IEEE Transactions on Neural Networks and Learning Systems 32(1):91\u2013104","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"5","key":"5184_CR43","doi-asserted-by":"publisher","first-page":"2741","DOI":"10.1002\/rnc.5520","volume":"32","author":"Y Sun","year":"2022","unstructured":"Sun Y, Li C, Qin H, Deng Z, Chen Z (2022) Robust neural network-based tracking control for unmanned surface vessels under deferred asymmetric constraints. Int J Robust Nonlinear Control 32(5):2741\u20132759","journal-title":"Int J Robust Nonlinear Control"},{"key":"5184_CR44","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.neunet.2022.11.012","volume":"158","author":"X Yang","year":"2023","unstructured":"Yang X, Zhou Y, Gao Z (2023) Reinforcement learning for robust stabilization of nonlinear systems with asymmetric saturating actuators. Neural Netw 158:132\u2013141","journal-title":"Neural Netw"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-05184-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-023-05184-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-05184-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T10:10:52Z","timestamp":1705140652000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-023-05184-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,5]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["5184"],"URL":"https:\/\/doi.org\/10.1007\/s10489-023-05184-1","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,5]]},"assertion":[{"value":"16 November 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}]}}