{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T12:26:37Z","timestamp":1763727997492,"version":"3.44.0"},"reference-count":33,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Mathematics and Computation"],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1016\/j.amc.2021.126451","type":"journal-article","created":{"date-parts":[[2021,6,27]],"date-time":"2021-06-27T05:37:30Z","timestamp":1624772250000},"page":"126451","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":19,"special_numbering":"C","title":["Optimal consensus control for unknown second-order multi-agent systems: Using model-free reinforcement learning method"],"prefix":"10.1016","volume":"410","author":[{"given":"Jun","family":"Li","sequence":"first","affiliation":[]},{"given":"Lianghao","family":"Ji","sequence":"additional","affiliation":[]},{"given":"Huaqing","family":"Li","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"9","key":"10.1016\/j.amc.2021.126451_bib0001","doi-asserted-by":"crossref","first-page":"7879","DOI":"10.1109\/TIE.2019.2946545","article-title":"Optimized formation control using simplified reinforcement learning for a class of multiagent systems with unknown dynamics","volume":"67","author":"Wen","year":"2020","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"8","key":"10.1016\/j.amc.2021.126451_bib0002","doi-asserted-by":"crossref","first-page":"1469","DOI":"10.1109\/TAC.2007.902752","article-title":"Stable flocking of multiple inertial agents on balanced graphs","volume":"52","author":"Lee","year":"2007","journal-title":"IEEE Trans. Autom. Control"},{"issue":"1","key":"10.1016\/j.amc.2021.126451_bib0003","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.sysconle.2012.10.012","article-title":"Distributed finite-time tracking control for multi-agent systems: an observer-based approach","volume":"62","author":"Zhao","year":"2013","journal-title":"Syst. Control Lett."},{"issue":"8","key":"10.1016\/j.amc.2021.126451_bib0004","doi-asserted-by":"crossref","first-page":"2259","DOI":"10.1109\/TCYB.2017.2731601","article-title":"Scaled group consensus in multiagent systems with first\/second order continuous dynamics","volume":"48","author":"Yu","year":"2018","journal-title":"IEEE Trans. Cybern."},{"issue":"3","key":"10.1016\/j.amc.2021.126451_bib0005","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1002\/rnc.2904","article-title":"Group consensus control for double-integrator dynamic multiagent systems with fixed communication topology","volume":"24","author":"Feng","year":"2014","journal-title":"Robust Nonlinear Control"},{"issue":"1","key":"10.1016\/j.amc.2021.126451_bib0006","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-012-4689-1","article-title":"Cluster synchronization of a class of multi-agent systems with a bipartite graph topology","volume":"57","author":"Wang","year":"2014","journal-title":"Sci. China Inf. Sci."},{"issue":"14","key":"10.1016\/j.amc.2021.126451_bib0007","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1080\/00207721.2013.862582","article-title":"Group consensus of multi-agent systems in directed networks with noises and time delays","volume":"46","author":"Shang","year":"2015","journal-title":"Int. J. Syst. Sci."},{"key":"10.1016\/j.amc.2021.126451_bib0008","first-page":"1859","article-title":"A survey of consensus problems in multi-agent coordination","volume":"3","author":"Ren","year":"2005","journal-title":"Proc. Am. Control Conf. USA"},{"issue":"2","key":"10.1016\/j.amc.2021.126451_bib0009","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1109\/9.481532","article-title":"On global existence of solutions to coupled matrix Riccati equations in closed loop Nash games","volume":"41","author":"Freiling","year":"2002","journal-title":"IEEE Trans. Autom. Control"},{"issue":"8","key":"10.1016\/j.amc.2021.126451_bib0010","doi-asserted-by":"crossref","first-page":"1556","DOI":"10.1016\/j.automatica.2011.03.005","article-title":"Multi-player non-zero-sum games: online adaptive learning solution of coupled Hamilton\u2013Jacobi equations","volume":"47","author":"Vamvoudakis","year":"2011","journal-title":"Automatica"},{"issue":"12","key":"10.1016\/j.amc.2021.126451_bib0011","doi-asserted-by":"crossref","first-page":"2226","DOI":"10.1109\/TNN.2011.2168538","article-title":"Data-driven robust approximate optimal tracking control for unknown general nonlinear systems using adaptive dynamic programming method","volume":"22","author":"Zhang","year":"2011","journal-title":"IEEE Trans. Neural Netw."},{"issue":"2","key":"10.1016\/j.amc.2021.126451_bib0012","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1016\/j.jfranklin.2017.12.001","article-title":"Trajectory tracking control for rotary steerable systems using interval type-2 fuzzy logic and reinforcement learning","volume":"355","author":"Zhang","year":"2018","journal-title":"J. Frankl. Inst."},{"year":"1998","series-title":"Reinforcement Learningian Introduction","author":"Sutton","key":"10.1016\/j.amc.2021.126451_bib0013"},{"issue":"12","key":"10.1016\/j.amc.2021.126451_bib0014","doi-asserted-by":"crossref","first-page":"3038","DOI":"10.1016\/j.automatica.2014.10.047","article-title":"Multi-agent discrete-time graphical games and reinforcement learning solutions","volume":"50","author":"Abouheaf","year":"2014","journal-title":"Automatica"},{"issue":"2","key":"10.1016\/j.amc.2021.126451_bib0015","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1109\/72.914523","article-title":"Online learning control by association and reinforcement","volume":"12","author":"Si","year":"2001","journal-title":"IEEE Trans. Neural Netw."},{"issue":"3","key":"10.1016\/j.amc.2021.126451_bib0016","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1109\/TASE.2014.2303139","article-title":"Neural-network-based constrained optimal control scheme for discrete-time switched nonlinear system using dual heuristic programming","volume":"11","author":"Zhang","year":"2014","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"issue":"1","key":"10.1016\/j.amc.2021.126451_bib0017","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1109\/TNNLS.2014.2358227","article-title":"Actor-critic-based optimal tracking for partially unknown nonlinear discrete-time systems","volume":"26","author":"Kiumarsi","year":"2015","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"25","key":"10.1016\/j.amc.2021.126451_bib0018","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1016\/j.neucom.2013.06.037","article-title":"Dual heuristic dynamic programming for nonlinear discrete-time uncertain systems with state delay","volume":"134","author":"Wang","year":"2014","journal-title":"Neurocomputing"},{"issue":"12","key":"10.1016\/j.amc.2021.126451_bib0019","doi-asserted-by":"crossref","first-page":"10951","DOI":"10.1109\/TIE.2019.2958277","article-title":"Optimal model-free output synchronization of heterogeneous multi-agent systems under switching topologies","volume":"67","author":"Mu","year":"2019","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"1","key":"10.1016\/j.amc.2021.126451_bib0020","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1109\/TAC.2010.2090575","article-title":"Further results on exponential estimates of Markovian jump systems with mode-dependent time-varying delays","volume":"56","author":"Gao","year":"2011","journal-title":"IEEE Trans. Autom. Control"},{"issue":"5\u20136","key":"10.1016\/j.amc.2021.126451_bib0021","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1016\/j.neunet.2009.06.014","article-title":"Optimal control of unknown affine nonlinear discrete-time systems using offline-trained neural networks with proof of convergence","volume":"22","author":"Dierks","year":"2009","journal-title":"Neural Netw."},{"issue":"13","key":"10.1016\/j.amc.2021.126451_bib0022","doi-asserted-by":"crossref","first-page":"1460","DOI":"10.1002\/rnc.1760","article-title":"Online solution of nonlinear twoplayer zero-sum games using synchronous policy iteration","volume":"22","author":"Vamvoudakis","year":"2012","journal-title":"Int. J. Robust Nonlinear Control"},{"issue":"9","key":"10.1016\/j.amc.2021.126451_bib0023","doi-asserted-by":"crossref","first-page":"7879","DOI":"10.1109\/TIE.2019.2946545","article-title":"Optimized formation control using simplified reinforcement learning for a class of multiagent systems with unknown dynamics","volume":"67","author":"Wen","year":"2020","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"7","key":"10.1016\/j.amc.2021.126451_bib0024","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1109\/TCYB.2014.2350511","article-title":"Distributed cooperative optimal control for multiagent systems on directed graphs: an inverse optimal approach","volume":"45","author":"Zhang","year":"2014","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.amc.2021.126451_bib0025","series-title":"Proc. 52nd IEEE Conf. Decis. Control Italy","first-page":"5803","article-title":"Multi-agent differential graphical games: Nash online adaptive learning solutions","author":"Abouheaf","year":"2013"},{"issue":"1","key":"10.1016\/j.amc.2021.126451_bib0026","article-title":"Distributed optimal consensus control algorithm for continuous-time multi-agent systems","volume":"1","author":"Wang","year":"2019","journal-title":"IEEE Trans. Circuits Syst. II"},{"issue":"5","key":"10.1016\/j.amc.2021.126451_bib0027","doi-asserted-by":"crossref","first-page":"878","DOI":"10.1016\/j.automatica.2010.02.018","article-title":"Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem","volume":"46","author":"Vamvoudakis","year":"2010","journal-title":"Automatica"},{"issue":"9","key":"10.1016\/j.amc.2021.126451_bib0028","doi-asserted-by":"crossref","first-page":"1490","DOI":"10.1109\/TNN.2009.2027233","article-title":"Neural-network-based near-optimal control for a class of discrete-time affine nonlinear systems with control constraints","volume":"20","author":"Zhang","year":"2009","journal-title":"IEEE Trans. Neural Netw."},{"year":"2016","series-title":"Consensus Problem of Delayed Linear Multi-Agent Systems: Analysis and Design","author":"Liu","key":"10.1016\/j.amc.2021.126451_bib0029"},{"issue":"3","key":"10.1016\/j.amc.2021.126451_bib0030","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1109\/TNNLS.2013.2281663","article-title":"Policy iteration adaptive dynamic programming algorithm for discrete-time nonlinear systems","volume":"25","author":"Liu","year":"2014","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"5","key":"10.1016\/j.amc.2021.126451_bib0031","doi-asserted-by":"crossref","first-page":"4091","DOI":"10.1109\/TIE.2016.2542134","article-title":"Data-driven optimal consensus control for discrete-time multi-agent systems with unknown dynamics using reinforcement learning method","volume":"64","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"9","key":"10.1016\/j.amc.2021.126451_bib0032","first-page":"2143","article-title":"Containment control for second-order multiagent systems communicating over heterogeneous networks","volume":"28","author":"Qin","year":"2017","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.amc.2021.126451_bib0033","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1016\/j.neucom.2015.10.060","article-title":"Dynamical group consensus of heterogeneous multi-agent systems with input time delays","volume":"175","author":"Wen","year":"2016","journal-title":"Neurocomputing"}],"container-title":["Applied Mathematics and Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0096300321005403?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0096300321005403?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T16:42:19Z","timestamp":1758818539000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0096300321005403"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":33,"alternative-id":["S0096300321005403"],"URL":"https:\/\/doi.org\/10.1016\/j.amc.2021.126451","relation":{},"ISSN":["0096-3003"],"issn-type":[{"type":"print","value":"0096-3003"}],"subject":[],"published":{"date-parts":[[2021,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Optimal consensus control for unknown second-order multi-agent systems: Using model-free reinforcement learning method","name":"articletitle","label":"Article Title"},{"value":"Applied Mathematics and Computation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.amc.2021.126451","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"126451"}}