{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:26:02Z","timestamp":1740122762866,"version":"3.37.3"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T00:00:00Z","timestamp":1634601600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T00:00:00Z","timestamp":1634601600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin City","doi-asserted-by":"publisher","award":["20JCYBJC00880"],"award-info":[{"award-number":["20JCYBJC00880"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019062","name":"Tianjin Research Innovation Project for Postgraduate Students","doi-asserted-by":"crossref","award":["2020YJSB005"],"award-info":[{"award-number":["2020YJSB005"]}],"id":[{"id":"10.13039\/501100019062","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s11063-021-10641-4","type":"journal-article","created":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T08:21:53Z","timestamp":1634631713000},"page":"501-521","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Model-Free Optimal Consensus Control for Multi-agent Systems Based on DHP Algorithm"],"prefix":"10.1007","volume":"54","author":[{"given":"Haoen","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanghe","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1055-9513","authenticated-orcid":false,"given":"Chaoxu","family":"Mu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunkai","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,19]]},"reference":[{"key":"10641_CR1","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.conengprac.2015.10.001","volume":"46","author":"XW Dong","year":"2016","unstructured":"Dong XW, Zhou Y, Zhang R, Zhong YS (2016) Time-varying formation control for unmanned aerial vehicles with switching interaction topologies. Control Eng Pract 46:26\u201336","journal-title":"Control Eng Pract"},{"issue":"4","key":"10641_CR2","doi-asserted-by":"publisher","first-page":"3417","DOI":"10.1109\/TIE.2017.2752148","volume":"65","author":"XH Ge","year":"2018","unstructured":"Ge XH, Han QL, Zhang XM (2018) Achieving cluster formation of multi-agent systems under aperiodic sampling and communication delays. IEEE Trans Ind Electron 65(4):3417\u20133426","journal-title":"IEEE Trans Ind Electron"},{"issue":"1","key":"10641_CR3","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1016\/j.nonrwa.2012.06.010","volume":"14","author":"HS Su","year":"2013","unstructured":"Su HS, Zhang NZ, Chen MZQ, Wang HW, Wang XF (2013) Adaptive flocking with a virtual leader of multiple agents governed by locally Lipschitz nonlinearity. Nonlinear Anal Real World Appl 14(1):310\u2013325","journal-title":"Nonlinear Anal Real World Appl"},{"issue":"4","key":"10641_CR4","doi-asserted-by":"publisher","first-page":"1110","DOI":"10.1109\/TCYB.2017.2771560","volume":"48","author":"L Ding","year":"2018","unstructured":"Ding L, Han QL, Ge XH, Zhang XM (2018) An overview of recent advances in event-triggered consensus of multiagent systems. IEEE Trans Cybern 48(4):1110\u20131123","journal-title":"IEEE Trans Cybern"},{"key":"10641_CR5","doi-asserted-by":"crossref","unstructured":"Lin J, Morse AS, Anderson BDO (2004) The multi-agent rendezvous problem\u2014the asynchronous case. In: 43rd IEEE conference on decision and control, pp 1926\u20131931","DOI":"10.1109\/CDC.2004.1430329"},{"issue":"9","key":"10641_CR6","doi-asserted-by":"publisher","first-page":"1520","DOI":"10.1109\/TAC.2004.834113","volume":"49","author":"R Olfati-Saber","year":"2004","unstructured":"Olfati-Saber R, Murray RM (2004) Consensus problems in networks of agents with switching topology and time-delays. IEEE Trans Autom Control 49(9):1520\u20131533","journal-title":"IEEE Trans Autom Control"},{"issue":"1","key":"10641_CR7","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1109\/TII.2012.2219061","volume":"9","author":"YC Cao","year":"2013","unstructured":"Cao YC, Yu WW, Ren W, Chen GR (2013) An overview of recent progress in the study of distributed multi-agent coordination. IEEE Trans Ind Inf 9(1):427\u2013438","journal-title":"IEEE Trans Ind Inf"},{"issue":"12","key":"10641_CR8","doi-asserted-by":"publisher","first-page":"3038","DOI":"10.1016\/j.automatica.2014.10.047","volume":"50","author":"MI Abouheaf","year":"2014","unstructured":"Abouheaf MI, Lewis FL, Vamvoudakis KG, Haesaert S, Babuska R (2014) Multi-agent discrete-time graphical games and reinforcement learning solutions. Automatica 50(12):3038\u20133053","journal-title":"Automatica"},{"issue":"3","key":"10641_CR9","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/MCAS.2009.933854","volume":"9","author":"FL Lewis","year":"2009","unstructured":"Lewis FL, Vrabie D (2009) Reinforcement learning and adaptive dynamic programming for feedback control. IEEE Circuits Syst Mag 9(3):32\u201350","journal-title":"IEEE Circuits Syst Mag"},{"issue":"9","key":"10641_CR10","doi-asserted-by":"publisher","first-page":"1490","DOI":"10.1109\/TNN.2009.2027233","volume":"20","author":"HG Zhang","year":"2009","unstructured":"Zhang HG, Luo YH, Liu DR (2009) Neural-network-based near-optimal control for a class of discrete-time affine nonlinear systems with control constraints. IEEE Trans Neural Netw 20(9):1490\u20131503","journal-title":"IEEE Trans Neural Netw"},{"issue":"7","key":"10641_CR11","doi-asserted-by":"publisher","first-page":"1780","DOI":"10.1016\/j.automatica.2014.05.011","volume":"50","author":"H Modares","year":"2014","unstructured":"Modares H, Lewis FL (2014) Optimal tracking control of nonlinear partially-unknown constrained-input systems using integral reinforcement learning. Automatica 50(7):1780\u20131792","journal-title":"Automatica"},{"issue":"7","key":"10641_CR12","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1109\/TNN.2008.2000204","volume":"19","author":"M Abu-Khalaf","year":"2008","unstructured":"Abu-Khalaf M, Lewis FL (2008) Neuro dynamic programming and zero-sum games for constrained control systems. IEEE Trans Neural Netw 19(7):1243\u20131252","journal-title":"IEEE Trans Neural Netw"},{"key":"10641_CR13","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/j.neucom.2018.07.098","volume":"396","author":"J Shi","year":"2020","unstructured":"Shi J, Yue D, Xie XP, Karimpour A, Naghibi-Sistani MB (2020) Adaptive optimal tracking control for nonlinear continuous-time systems with time delay using value iteration algorithm. Neurocomputing 396:172\u2013178","journal-title":"Neurocomputing"},{"issue":"1","key":"10641_CR14","doi-asserted-by":"publisher","first-page":"121","DOI":"10.3724\/SP.J.1004.2010.00121","volume":"36","author":"QL Wei","year":"2010","unstructured":"Wei QL, Zhang HG, Liu DR (2010) An optimal control scheme for a class of discrete-time nonlinear systems with time delays using adaptive dynamic programming. Acta Autom Sin 36(1):121\u2013129","journal-title":"Acta Autom Sin"},{"issue":"12","key":"10641_CR15","doi-asserted-by":"publisher","first-page":"2770","DOI":"10.1109\/TCYB.2014.2384016","volume":"45","author":"B Kiumarsi","year":"2015","unstructured":"Kiumarsi B, Lewis FL, Naghibi-Sistani MB, Karimpour A (2015) Optimal tracking control of unknown discrete-time linear systems using input\u2013output measured data. IEEE Trans Cybern 45(12):2770\u20132779","journal-title":"IEEE Trans Cybern"},{"key":"10641_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.asoc.2019.105593","volume":"82","author":"CX Mu","year":"2019","unstructured":"Mu CX, Zhao Q, Sun CY, Gao ZK (2019) An ADDHP-based Q-learning algorithm for optimal tracking control of linear discrete-time systems with unknown dynamics. Appl Soft Comput 82:1\u201313","journal-title":"Appl Soft Comput"},{"issue":"4","key":"10641_CR17","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 FL, Modares H, Karimpour A, Naghibi-Sistani MB (2014) Reinforcement Q-learning for optimal tracking control of linear discrete-time systems with unknown dynamics. Automatica 50(4):1167\u20131175","journal-title":"Automatica"},{"issue":"2","key":"10641_CR18","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1109\/TNNLS.2015.2464080","volume":"27","author":"QL Wei","year":"2016","unstructured":"Wei QL, Song RZ, Yan PF (2016) Data-driven zero-sum neuro-optimal control for a class of continuous-time unknown nonlinear systems with disturbance using ADP. IEEE Trans Neural Netw 27(2):444\u2013458","journal-title":"IEEE Trans Neural Netw"},{"issue":"13","key":"10641_CR19","doi-asserted-by":"publisher","first-page":"1460","DOI":"10.1002\/rnc.1760","volume":"22","author":"K Vamvoudakis","year":"2012","unstructured":"Vamvoudakis K, Lewis FL (2012) Online solution of nonlinear two-player zero-sum games using synchronous policy iteration. Int J Robust Nonlinear Control 22(13):1460\u20131483","journal-title":"Int J Robust Nonlinear Control"},{"issue":"4","key":"10641_CR20","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1002\/oca.2597","volume":"41","author":"YL Wen","year":"2020","unstructured":"Wen YL, Zhang HG, Su HG, Ren H (2020) Optimal tracking control for non-zero-sum games of linear discrete-time systems via off-policy reinforcement learning. Opt Control Appl Methods 41(4):1233\u20131250","journal-title":"Opt Control Appl Methods"},{"issue":"1","key":"10641_CR21","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1109\/TSMCB.2012.2203336","volume":"43","author":"HG Zhang","year":"2013","unstructured":"Zhang HG, Cui LL, Luo YH (2013) Near-optimal control for nonzero-sum differential games of continuous-time nonlinear systems using single network ADP. IEEE Trans Cybern 43(1):206\u2013216","journal-title":"IEEE Trans Cybern"},{"key":"10641_CR22","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1016\/j.neucom.2016.06.059","volume":"214","author":"CX Mu","year":"2016","unstructured":"Mu CX, Sun CY, Song AG, Yu HL (2016) Iterative GDHP-based approxiamte optimal tracking control for a class of discrete-time nonlinear systems. Neurocomputing 214:775\u2013784","journal-title":"Neurocomputing"},{"issue":"7","key":"10641_CR23","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.1016\/j.automatica.2012.05.008","volume":"48","author":"HW Zhang","year":"2012","unstructured":"Zhang HW, Lewis FL (2012) Adaptive cooperative tracking control of higher-order nonlinear systems with unknown dynamics. Automatica 48(7):1432\u20131439","journal-title":"Automatica"},{"issue":"15","key":"10641_CR24","doi-asserted-by":"publisher","first-page":"6947","DOI":"10.1016\/j.jfranklin.2018.07.009","volume":"355","author":"K Zhang","year":"2018","unstructured":"Zhang K, Zhang HG, Gao ZY, Su HG (2018) Online adaptive policy iteration based fault-tolerant control algorithm for continuous-time nonlinear tracking systems with actuator failures. J Frankl Inst 355(15):6947\u20136968","journal-title":"J Frankl Inst"},{"key":"10641_CR25","doi-asserted-by":"crossref","unstructured":"Li MH, Gao X, Wen Y, Si J, Huang H (2019) Offline policy iteration based reinforcement learning controller for online robotic knee prosthesis parameter tuning. In: 2019 International conference on robotics and automation (ICRA), pp 2831\u20132837","DOI":"10.1109\/ICRA.2019.8794212"},{"issue":"8","key":"10641_CR26","doi-asserted-by":"publisher","first-page":"1598","DOI":"10.1016\/j.automatica.2012.05.074","volume":"48","author":"K Vamvoudakis","year":"2012","unstructured":"Vamvoudakis K, Lewis FL, Hudas G (2012) Multi-agent differential graphical games: online adaptive learning solution for synchronization with optimality. Automatica 48(8):1598\u20131611","journal-title":"Automatica"},{"key":"10641_CR27","doi-asserted-by":"crossref","unstructured":"Abouheaf M, Lewis FL (2013) Multi-agent differential graphical games: Nash online adaptive learning solutions. In: 52nd IEEE annual conference on decision and control (CDC), pp 5803\u20135809","DOI":"10.1109\/CDC.2013.6760804"},{"issue":"1","key":"10641_CR28","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1109\/TFUZZ.2014.2310238","volume":"23","author":"HG Zhang","year":"2015","unstructured":"Zhang HG, Zhang JL, Yang GH, Luo YH (2015) Leader-based optimal coordination control for the consensus problem of multiagent differential games via fuzzy adaptive dynamic programming. IEEE Trans Fuzzy Syst 23(1):152\u2013163","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"10641_CR29","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.ins.2015.04.044","volume":"317","author":"QL Wei","year":"2015","unstructured":"Wei QL, Liu DR, Lewis FL (2015) Optimal distributed synchronization control for continuous-time heterogeneous multi-agent differential graphical games. Inf Sci 317:96\u2013113","journal-title":"Inf Sci"},{"key":"10641_CR30","doi-asserted-by":"crossref","unstructured":"Abouheaf M, Lewis FL, Haesaert S, Babuska R, Vamvoudakis K (2013) Multi-agent discrete-time graphical games: interactive Nash equilibrium and value iteration solution. In: 2013 American control conference (ACC), pp 4189\u20134195","DOI":"10.1109\/ACC.2013.6580483"},{"issue":"1","key":"10641_CR31","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1016\/j.jfranklin.2016.09.019","volume":"354","author":"CY Wang","year":"2017","unstructured":"Wang CY, Zuo ZY, Sun JY, Yang J, Ding ZT (2017) Consensus disturbance rejection for Lipschitz nonlinear multi-agent systems with input delay: a DOBC approach. J Frankl Inst 354(1):298\u2013315","journal-title":"J Frankl Inst"},{"issue":"5","key":"10641_CR32","doi-asserted-by":"publisher","first-page":"4091","DOI":"10.1109\/TIE.2016.2542134","volume":"64","author":"HG Zhang","year":"2017","unstructured":"Zhang HG, Jiang H, Luo YH, Xiao GY (2017) Data-driven optimal consensus control for discrete-time multi-agent systems with unknown dynamics using reinforcement learning method. IEEE Trans Ind Electron 64(5):4091\u20134100","journal-title":"IEEE Trans Ind Electron"},{"issue":"12","key":"10641_CR33","doi-asserted-by":"publisher","first-page":"4441","DOI":"10.1109\/TCYB.2018.2868715","volume":"49","author":"J Zhang","year":"2019","unstructured":"Zhang J, Wang Z, Zhang H (2019) Data-based optimal control of multiagent systems: a reinforcement learning design approach. IEEE Trans Cybern 49(12):4441\u20134449","journal-title":"IEEE Trans Cybern"},{"issue":"13","key":"10641_CR34","doi-asserted-by":"publisher","first-page":"6946","DOI":"10.1016\/j.jfranklin.2019.06.007","volume":"356","author":"CX Mu","year":"2019","unstructured":"Mu CX, Zhao Q, Gao ZK, Sun CY (2019) Q-learning solution for optimal consensus control of discrete-time multiagent systems using reinforcement learning. J Frankl Inst Eng Appl Math 356(13):6946\u20136967","journal-title":"J Frankl Inst Eng Appl Math"},{"key":"10641_CR35","doi-asserted-by":"crossref","unstructured":"Abouheaf MI, Lewis FL, Mahmoud MS (2019) Action dependent dual heuristic programming solution for the dynamic graphical games. In: 2018 IEEE conference on decision and control (CDC), pp 2741\u20132746","DOI":"10.1109\/CDC.2018.8619012"},{"issue":"2","key":"10641_CR36","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1109\/TMECH.2009.2014057","volume":"14","author":"S Khoo","year":"2009","unstructured":"Khoo S, Xie L, Man Z (2009) Robust finite-time consensus tracking algorithm for multirobot systems. IEEE\/ASME Trans Mechatron 14(2):219\u2013228","journal-title":"IEEE\/ASME Trans Mechatron"},{"issue":"1","key":"10641_CR37","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/s11768-015-3203-x","volume":"13","author":"MI Abouheaf","year":"2015","unstructured":"Abouheaf MI, Lewis FL, Mahmoud MS, Mikulski DG (2015) Discrete-time dynamic graphical games: model-free reinforcement learning solution. Control Theory Technol 13(1):55\u201369","journal-title":"Control Theory Technol"},{"key":"10641_CR38","doi-asserted-by":"publisher","DOI":"10.1007\/978-93-86279-17-0","volume-title":"Introduction to game theory","author":"S Tijs","year":"2003","unstructured":"Tijs S (2003) Introduction to game theory. Hindustan Book Agency, Gurgaon"},{"issue":"10","key":"10641_CR39","doi-asserted-by":"publisher","first-page":"1513","DOI":"10.1109\/TNNLS.2013.2276571","volume":"24","author":"H Modares","year":"2013","unstructured":"Modares H, Lewis FL, Naghibi-Sistani M (2013) Adaptive optimal control of unknown constrained-input systems using policy iteration and neural networks. IEEE Trans Neural Netw Learn Syst 24(10):1513\u20131525","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10641_CR40","doi-asserted-by":"crossref","unstructured":"Rehan M, Ahn CK, Chadli M (2020) Consensus of one-sided lipschitz multi-agents under input saturation. IEEE Trans Circuits Syst II Exp 67(4):745\u2013749","DOI":"10.1109\/TCSII.2019.2923721"},{"issue":"12","key":"10641_CR41","doi-asserted-by":"publisher","first-page":"3267","DOI":"10.1109\/TCSII.2020.2986009","volume":"67","author":"MA Razaq","year":"2020","unstructured":"Razaq MA, Rehan M, Tufail M, Ahn CK (2020) Multiple Lyapunov functions approach for consensus of one-sided Lipschitz multi-agents over switching topologies and input saturation. IEEE Trans Circuits Syst II Exp 67(12):3267\u20133271","journal-title":"IEEE Trans Circuits Syst II Exp"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-021-10641-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-021-10641-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-021-10641-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,25]],"date-time":"2022-02-25T16:23:49Z","timestamp":1645806229000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-021-10641-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,19]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["10641"],"URL":"https:\/\/doi.org\/10.1007\/s11063-021-10641-4","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"type":"print","value":"1370-4621"},{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2021,10,19]]},"assertion":[{"value":"2 September 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 October 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}