{"id":"https://openalex.org/W4205137579","doi":"https://doi.org/10.1109/ccta48906.2021.9658641","title":"Decentralized Optimal Tracking Control for Large-scale Multi-Agent Systems under Complex Environment: A Constrained Mean Field Game with Reinforcement Learning Approach","display_name":"Decentralized Optimal Tracking Control for Large-scale Multi-Agent Systems under Complex Environment: A Constrained Mean Field Game with Reinforcement Learning Approach","publication_year":2021,"publication_date":"2021-08-09","ids":{"openalex":"https://openalex.org/W4205137579","doi":"https://doi.org/10.1109/ccta48906.2021.9658641"},"language":"en","primary_location":{"id":"doi:10.1109/ccta48906.2021.9658641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccta48906.2021.9658641","pdf_url":null,"source":{"id":"https://openalex.org/S4363608183","display_name":"2021 IEEE Conference on Control Technology and Applications (CCTA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Control Technology and Applications (CCTA)","raw_type":"proceedings-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/A5088809666","display_name":"Zejian Zhou","orcid":"https://orcid.org/0000-0002-0252-6765"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zejian Zhou","raw_affiliation_strings":["Department of Electrical and Biomedical Engineering, University of Nevada, Reno, NV, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Biomedical Engineering, University of Nevada, Reno, NV, USA","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100717012","display_name":"Hao Xu","orcid":"https://orcid.org/0000-0003-4130-7925"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Xu","raw_affiliation_strings":["Department of Electrical and Biomedical Engineering, University of Nevada, Reno, NV, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Biomedical Engineering, University of Nevada, Reno, NV, USA","institution_ids":["https://openalex.org/I134113660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I134113660"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21337947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"52","issue":null,"first_page":"111","last_page":"116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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/T10482","display_name":"Mathematical and Theoretical Epidemiology and Ecology Models","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.984499990940094,"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":0.8933478593826294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6918471455574036},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.6520964503288269},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.555616557598114},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.5436193346977234},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5434073209762573},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4962831139564514},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.494549959897995},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4794168174266815},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4461268484592438},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.445367693901062},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.43936747312545776},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4168534576892853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37156522274017334},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.3301197588443756},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17380386590957642}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8933478593826294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6918471455574036},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6520964503288269},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.555616557598114},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.5436193346977234},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5434073209762573},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4962831139564514},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.494549959897995},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4794168174266815},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4461268484592438},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.445367693901062},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.43936747312545776},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4168534576892853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37156522274017334},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.3301197588443756},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17380386590957642},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccta48906.2021.9658641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccta48906.2021.9658641","pdf_url":null,"source":{"id":"https://openalex.org/S4363608183","display_name":"2021 IEEE Conference on Control Technology and Applications (CCTA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Control Technology and Applications (CCTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W586490843","https://openalex.org/W1808956822","https://openalex.org/W1997001104","https://openalex.org/W2152161277","https://openalex.org/W2165726932","https://openalex.org/W2505182502","https://openalex.org/W2560814118","https://openalex.org/W2598824101","https://openalex.org/W2616325770","https://openalex.org/W2743823417","https://openalex.org/W2765867214","https://openalex.org/W2787070120","https://openalex.org/W2963995492","https://openalex.org/W3008803500","https://openalex.org/W3010742245","https://openalex.org/W3011347165","https://openalex.org/W3012085680","https://openalex.org/W3046072112","https://openalex.org/W3122983590","https://openalex.org/W3153042747","https://openalex.org/W6767797354"],"related_works":["https://openalex.org/W4214835929","https://openalex.org/W4226086326","https://openalex.org/W3119014777","https://openalex.org/W1570906179","https://openalex.org/W3212428133","https://openalex.org/W2145067550","https://openalex.org/W4282936078","https://openalex.org/W1607392272","https://openalex.org/W2236801283","https://openalex.org/W2110018584"],"abstract_inverted_index":{"In":[0,100],"this":[1,101],"paper,":[2,102],"the":[3,29,40,45,59,67,71,80,103,118,128,134,160,163],"optimal":[4,46],"tracking":[5],"control":[6,132],"for":[7,93],"large-scale":[8,35,61],"multi-agent":[9,36],"systems":[10],"(MAS)":[11],"under":[12],"constraints":[13,115],"has":[14,74,107],"been":[15,108],"investigated.":[16],"The":[17],"Mean":[18],"Field":[19],"Game":[20],"(MFG)":[21],"theory":[22,42,73,106],"is":[23,89,139],"an":[24],"emerging":[25],"technique":[26],"to":[27,97,126,144,158],"solve":[28,127],"“curse":[30],"of":[31,58,153,162],"dimensionality”":[32],"problem":[33],"in":[34,83],"decision-making":[37],"problems.":[38],"Specifically,":[39],"MFG":[41,72,105,130],"can":[43],"calculate":[44],"strategy":[47],"based":[48],"on":[49],"one":[50],"unified":[51],"fix-dimension":[52],"probability":[53],"density":[54,123],"function":[55],"(PDF)":[56],"instead":[57],"high-dimensional":[60],"MAS":[62],"information":[63],"collected":[64],"from":[65],"all":[66,79],"individual":[68],"agents.":[69],"However,":[70],"stringent":[75],"limitations":[76],"by":[77,110,117],"assuming":[78],"agents":[81],"operate":[82],"a":[84,145,151],"predefined":[85],"unlimited":[86],"space,":[87],"which":[88],"often":[90],"too":[91],"ideal":[92],"practical":[94,113],"applications":[95],"due":[96],"complex":[98],"environments.":[99],"original":[104],"extended":[109,129,143],"considering":[111],"two":[112],"state":[114],"caused":[116],"environment,":[119],"i.e.,":[120],"boundary":[121],"and":[122,141],"constraints.":[124],"Moreover,":[125],"type":[131],"online,":[133],"actor-critic":[135],"reinforcement":[136],"learning":[137],"mechanism":[138],"utilized":[140],"further":[142],"novel":[146],"actor-critic-mass":[147],"(ACM)":[148],"algorithm.":[149],"Finally,":[150],"series":[152],"numerical":[154],"simulations":[155],"are":[156],"conducted":[157],"demonstrate":[159],"effectiveness":[161],"developed":[164],"schemes.":[165]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}