{"id":"https://openalex.org/W4399768262","doi":"https://doi.org/10.1109/tsmc.2024.3406777","title":"Dynamic Leader\u2013Follower Output Containment Control of Heterogeneous Multiagent Systems Using Reinforcement Learning","display_name":"Dynamic Leader\u2013Follower Output Containment Control of Heterogeneous Multiagent Systems Using Reinforcement Learning","publication_year":2024,"publication_date":"2024-06-18","ids":{"openalex":"https://openalex.org/W4399768262","doi":"https://doi.org/10.1109/tsmc.2024.3406777"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2024.3406777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2024.3406777","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020669784","display_name":"Huaipin Zhang","orcid":"https://orcid.org/0000-0001-6405-1382"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huaipin Zhang","raw_affiliation_strings":["Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434523","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0001-8045-2549"},"institutions":[{"id":"https://openalex.org/I137056471","display_name":"Nanjing University of Finance and Economics","ror":"https://ror.org/031y8am81","country_code":"CN","type":"education","lineage":["https://openalex.org/I137056471"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["College of Information Engineering, Nanjing University of Finance and Economics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Information Engineering, Nanjing University of Finance and Economics, Nanjing, China","institution_ids":["https://openalex.org/I137056471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066409796","display_name":"Xiangpeng Xie","orcid":"https://orcid.org/0000-0003-4822-3134"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangpeng Xie","raw_affiliation_strings":["Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100727487","display_name":"Dong Yue","orcid":"https://orcid.org/0000-0001-7810-9338"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yue","raw_affiliation_strings":["Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020669784"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":8.0628,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.97895827,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"54","issue":"9","first_page":"5307","last_page":"5316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11347","display_name":"Neural Networks Stability and Synchronization","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8026368618011475},{"id":"https://openalex.org/keywords/containment","display_name":"Containment (computer programming)","score":0.6178515553474426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5801360011100769},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5568057894706726},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5556271076202393},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5521218776702881},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24503862857818604},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17100045084953308}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8026368618011475},{"id":"https://openalex.org/C2777019822","wikidata":"https://www.wikidata.org/wiki/Q390066","display_name":"Containment (computer programming)","level":2,"score":0.6178515553474426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5801360011100769},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5568057894706726},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5556271076202393},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5521218776702881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24503862857818604},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17100045084953308},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2024.3406777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2024.3406777","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G451589156","display_name":null,"funder_award_id":"2018YFA0702200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G493782230","display_name":null,"funder_award_id":"62203208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7261126740","display_name":null,"funder_award_id":"62373196","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1834394711","https://openalex.org/W2007453291","https://openalex.org/W2072302088","https://openalex.org/W2109987654","https://openalex.org/W2148993855","https://openalex.org/W2740197008","https://openalex.org/W2765454702","https://openalex.org/W2789789879","https://openalex.org/W2793914020","https://openalex.org/W2794471171","https://openalex.org/W2904350153","https://openalex.org/W2916013785","https://openalex.org/W2963793879","https://openalex.org/W2981216110","https://openalex.org/W2981394297","https://openalex.org/W3020342559","https://openalex.org/W3086757439","https://openalex.org/W3112239567","https://openalex.org/W3157467180","https://openalex.org/W3210830506","https://openalex.org/W3217797984","https://openalex.org/W4205968151","https://openalex.org/W4283262276","https://openalex.org/W4296343631","https://openalex.org/W4296708564","https://openalex.org/W4312936291","https://openalex.org/W4315489542","https://openalex.org/W4317821566","https://openalex.org/W4321609161","https://openalex.org/W4322706993","https://openalex.org/W4361029943","https://openalex.org/W4366957391","https://openalex.org/W4376154660","https://openalex.org/W4378802548","https://openalex.org/W4386162561","https://openalex.org/W4387934934"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W4252941105","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291"],"abstract_inverted_index":{"This":[0],"article":[1],"addresses":[2],"the":[3,20,40,44,48,53,57,60,73,94,133,136],"optimal":[4,61,68,117],"containment":[5,62],"problem":[6,63],"of":[7,22,135],"heterogeneous":[8],"multiagent":[9],"systems":[10],"(MASs)":[11],"with":[12],"dynamic":[13],"leaders":[14],"via":[15],"reinforcement":[16],"learning":[17],"(RL),":[18],"where":[19],"dynamics":[21,42],"all":[23,26],"agents":[24],"are":[25,77],"completely":[27],"unknown.":[28],"A":[29],"distributed":[30],"model-free":[31,87],"observer":[32],"is":[33,64,90,129],"constructed":[34],"for":[35,109],"each":[36,110],"follower":[37,111],"to":[38,79,92,112,131],"estimate":[39,116],"leaders\u2019":[41],"and":[43,115,120],"output":[45],"trajectories":[46],"inside":[47],"convex":[49],"hull":[50],"formed":[51],"by":[52],"leaders.":[54],"Based":[55],"on":[56],"designed":[58],"observers,":[59],"formulated":[65],"as":[66],"an":[67],"tracking":[69],"control":[70,118],"issue.":[71],"Then":[72],"discounted":[74],"performance":[75],"functions":[76],"introduced":[78],"obtain":[80],"algebraic":[81],"Riccati":[82],"equations":[83],"(AREs).":[84],"And":[85],"a":[86,103,126],"RL":[88],"algorithm":[89],"developed":[91],"learn":[93],"AREs":[95],"online.":[96],"To":[97],"implement":[98],"this":[99],"algorithm,":[100],"we":[101],"design":[102],"single":[104],"critic":[105],"neural":[106],"network":[107],"structure":[108],"approximate":[113],"Q-function,":[114],"policy":[119],"worst-case":[121],"adversarial":[122],"input":[123],"policy.":[124],"Finally,":[125],"numerical":[127],"simulation":[128],"provided":[130],"demonstrate":[132],"effectiveness":[134],"proposed":[137],"algorithm.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
