{"id":"https://openalex.org/W3201576001","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534288","title":"Reinforcement Learning-based Decentralized Optimal Control for Large-Scale Multi-agent System by Using Neural Networks and Discrete-time Mean Field Games","display_name":"Reinforcement Learning-based Decentralized Optimal Control for Large-Scale Multi-agent System by Using Neural Networks and Discrete-time Mean Field Games","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3201576001","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534288","mag":"3201576001"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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":true,"raw_author_name":"Zejian Zhou","raw_affiliation_strings":["University of Nevada, Reno, NV, USA"],"affiliations":[{"raw_affiliation_string":"University of Nevada, Reno, NV, USA","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100777152","display_name":"Yuzhu Zhang","orcid":"https://orcid.org/0000-0002-0861-7289"},"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":"Yuzhu Zhang","raw_affiliation_strings":["University of Nevada, Reno, NV, USA"],"affiliations":[{"raw_affiliation_string":"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":["University of Nevada, Reno, NV, USA"],"affiliations":[{"raw_affiliation_string":"University of Nevada, Reno, NV, USA","institution_ids":["https://openalex.org/I134113660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088809666"],"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":0.17244705,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9993000030517578,"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":0.9993000030517578,"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/T11110","display_name":"Stability and Controllability of Differential Equations","score":0.965399980545044,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9607999920845032,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.7953740358352661},{"id":"https://openalex.org/keywords/hamilton\u2013jacobi\u2013bellman-equation","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","score":0.7522349953651428},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5513368844985962},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5220889449119568},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5074314475059509},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4721272885799408},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4564743638038635},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4514937102794647},{"id":"https://openalex.org/keywords/uniqueness","display_name":"Uniqueness","score":0.4404970109462738},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.43103939294815063},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.426118940114975},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.36925023794174194},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.33961671590805054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15891024470329285},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1343851089477539},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.12688949704170227}],"concepts":[{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.7953740358352661},{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.7522349953651428},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5513368844985962},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5220889449119568},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5074314475059509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4721272885799408},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4564743638038635},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4514937102794647},{"id":"https://openalex.org/C2777021972","wikidata":"https://www.wikidata.org/wiki/Q22976830","display_name":"Uniqueness","level":2,"score":0.4404970109462738},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.43103939294815063},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.426118940114975},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.36925023794174194},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.33961671590805054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15891024470329285},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1343851089477539},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.12688949704170227},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W586490843","https://openalex.org/W1808956822","https://openalex.org/W1983997656","https://openalex.org/W2010057869","https://openalex.org/W2019338681","https://openalex.org/W2026814250","https://openalex.org/W2038686546","https://openalex.org/W2081458347","https://openalex.org/W2117717397","https://openalex.org/W2125088529","https://openalex.org/W2145956080","https://openalex.org/W2165726932","https://openalex.org/W2423077613","https://openalex.org/W2770250658","https://openalex.org/W2785315072","https://openalex.org/W2803629276","https://openalex.org/W2903583264","https://openalex.org/W2908261578","https://openalex.org/W2951396266","https://openalex.org/W2963039558","https://openalex.org/W2970875146","https://openalex.org/W3009344227","https://openalex.org/W3011347165","https://openalex.org/W3102704006","https://openalex.org/W6747941106","https://openalex.org/W6758732251"],"related_works":["https://openalex.org/W2358967034","https://openalex.org/W2155717523","https://openalex.org/W2024495128","https://openalex.org/W4319881067","https://openalex.org/W2112014346","https://openalex.org/W4251016492","https://openalex.org/W2174882787","https://openalex.org/W2028614848","https://openalex.org/W2126977748","https://openalex.org/W4226145367"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposed":[2],"the":[3,9,35,46,55,61,67,79,85,89,100,107,118,127,144,154,161,165,170,173,179,191],"Actor-critic-mass":[4],"(ACM)":[5],"algorithm":[6],"to":[7,34,59,105,152],"solve":[8],"discrete-time":[10],"mean":[11,72],"field":[12,73],"type":[13,74],"tracking":[14],"control":[15,24,57,75],"problem":[16,25,58],"without":[17],"discretization":[18],"errors.":[19],"The":[20],"traditional":[21,71],"large-scale":[22],"multi-agent":[23,56],"suffers":[26],"from":[27],"computational":[28],"explosion":[29],"and":[30,63,122,147,160,167,172],"communication":[31,64],"difficulty":[32],"due":[33],"team's":[36],"nearly":[37],"infinite":[38],"agent":[39,68],"number.":[40,69],"To":[41],"deal":[42],"with":[43,66],"those":[44],"challenges,":[45],"Mean":[47],"Field":[48],"Games":[49],"(MFG)":[50],"have":[51,189],"been":[52],"introduced":[53],"in":[54,126],"disconnect":[60],"computation":[62],"complexity":[65],"However,":[70],"problems":[76],"mainly":[77],"studied":[78],"continuous-":[80],"times":[81],"systems":[82],"limited":[83],"by":[84,95],"concerns":[86],"of":[87,129,169,186],"losing":[88],"solutions'":[90],"existence":[91],"or":[92],"uniqueness":[93],"caused":[94],"discretization.":[96],"In":[97],"this":[98],"paper,":[99],"Feynman-Kac":[101],"formula":[102],"is":[103],"utilized":[104],"reformulate":[106],"continuous":[108],"MFG":[109,155],"equation":[110,121,125,134,156],"system":[111,175],"into":[112],"a":[113,130,184],"backward":[114,123,131],"discretized":[115,158],"system.":[116],"Specifically,":[117],"Hamiltonian-Jacobi-Bellman":[119],"(HJB)":[120],"Kolmogorov":[124],"form":[128],"stochastic":[132],"differential":[133],"(BSDE)":[135],"are":[136,150,176],"introduced.":[137],"Meanwhile,":[138],"three":[139],"neural":[140],"networks":[141],"(NN),":[142],"i.e.,":[143],"actor,":[145],"critic,":[146],"mass":[148],"NN,":[149],"developed":[151],"approximate":[153],"system's":[157],"solution":[159],"optimal":[162],"control.":[163],"Moreover,":[164],"stability":[166,181],"convergence":[168],"NNs":[171],"closed-loop":[174],"provided":[177],"via":[178],"Lyapunov":[180],"analysis.":[182],"Finally,":[183],"series":[185],"numerical":[187],"simulations":[188],"shown":[190],"new":[192],"discrete":[193],"algorithm's":[194],"performance.":[195]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}