{"id":"https://openalex.org/W3110445832","doi":"https://doi.org/10.1109/icca51439.2020.9264527","title":"Graphical Minimax Game and On-Policy Reinforcement Learning for Consensus of Leaderless Multi-Agent Systems","display_name":"Graphical Minimax Game and On-Policy Reinforcement Learning for Consensus of Leaderless Multi-Agent Systems","publication_year":2020,"publication_date":"2020-10-09","ids":{"openalex":"https://openalex.org/W3110445832","doi":"https://doi.org/10.1109/icca51439.2020.9264527","mag":"3110445832"},"language":"en","primary_location":{"id":"doi:10.1109/icca51439.2020.9264527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5070605818","display_name":"Wei Dong","orcid":"https://orcid.org/0000-0001-7692-0872"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Dong","raw_affiliation_strings":["Key Laboratory of Dynamics and Control of Flight Vehicle within Ministry of Education, School of Aerospace Engineering, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Dynamics and Control of Flight Vehicle within Ministry of Education, School of Aerospace Engineering, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451091","display_name":"Chunyan Wang","orcid":"https://orcid.org/0000-0003-3218-2083"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyan Wang","raw_affiliation_strings":["Key Laboratory of Dynamics and Control of Flight Vehicle within Ministry of Education, School of Aerospace Engineering, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Dynamics and Control of Flight Vehicle within Ministry of Education, School of Aerospace Engineering, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070599005","display_name":"Jinna Li","orcid":"https://orcid.org/0000-0001-9985-6308"},"institutions":[{"id":"https://openalex.org/I166846921","display_name":"Liaoning Shihua University","ror":"https://ror.org/00k6c4h29","country_code":"CN","type":"education","lineage":["https://openalex.org/I166846921"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinna Li","raw_affiliation_strings":["School of Information and Control Engineering, Liaoning Shihua University, Fushun, China","State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Liaoning Shihua University, Fushun, China","institution_ids":["https://openalex.org/I166846921"]},{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100458008","display_name":"Jianan Wang","orcid":"https://orcid.org/0000-0003-4161-1687"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianan Wang","raw_affiliation_strings":["Key Laboratory of Dynamics and Control of Flight Vehicle within Ministry of Education, School of Aerospace Engineering, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Dynamics and Control of Flight Vehicle within Ministry of Education, School of Aerospace Engineering, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"606","last_page":"611"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9998000264167786,"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/T11347","display_name":"Neural Networks Stability and Synchronization","score":0.9940000176429749,"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/minimax","display_name":"Minimax","score":0.822447657585144},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8135737776756287},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.700838565826416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6403608918190002},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5838161110877991},{"id":"https://openalex.org/keywords/algebraic-riccati-equation","display_name":"Algebraic Riccati equation","score":0.5405958294868469},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5353249907493591},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5053480267524719},{"id":"https://openalex.org/keywords/consensus","display_name":"Consensus","score":0.485895574092865},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.46623632311820984},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.4601626396179199},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.45742926001548767},{"id":"https://openalex.org/keywords/riccati-equation","display_name":"Riccati equation","score":0.341938853263855},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2500261962413788},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19887614250183105}],"concepts":[{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.822447657585144},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8135737776756287},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.700838565826416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6403608918190002},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5838161110877991},{"id":"https://openalex.org/C13847129","wikidata":"https://www.wikidata.org/wiki/Q4723989","display_name":"Algebraic Riccati equation","level":4,"score":0.5405958294868469},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5353249907493591},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5053480267524719},{"id":"https://openalex.org/C107107730","wikidata":"https://www.wikidata.org/wiki/Q2994424","display_name":"Consensus","level":3,"score":0.485895574092865},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.46623632311820984},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.4601626396179199},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.45742926001548767},{"id":"https://openalex.org/C45473103","wikidata":"https://www.wikidata.org/wiki/Q851503","display_name":"Riccati equation","level":3,"score":0.341938853263855},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2500261962413788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19887614250183105},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icca51439.2020.9264527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1509185796","https://openalex.org/W1579118835","https://openalex.org/W1630241696","https://openalex.org/W1885224416","https://openalex.org/W1923286139","https://openalex.org/W1983523909","https://openalex.org/W2000806524","https://openalex.org/W2013959326","https://openalex.org/W2035608030","https://openalex.org/W2055891887","https://openalex.org/W2092215165","https://openalex.org/W2108383324","https://openalex.org/W2122375213","https://openalex.org/W2135519533","https://openalex.org/W2148439597","https://openalex.org/W2166103243","https://openalex.org/W2333120204","https://openalex.org/W2560131027","https://openalex.org/W2560491401","https://openalex.org/W2606378794","https://openalex.org/W2786933610","https://openalex.org/W2809051949","https://openalex.org/W3043748799","https://openalex.org/W3047879910"],"related_works":["https://openalex.org/W2005019312","https://openalex.org/W2105459831","https://openalex.org/W1546579375","https://openalex.org/W1563296412","https://openalex.org/W2127238600","https://openalex.org/W2096105566","https://openalex.org/W2114791549","https://openalex.org/W16457797","https://openalex.org/W2792258377","https://openalex.org/W1530596433"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"study":[4],"the":[5,19,32,54,60,71,74,80,84,87,90],"adaptive":[6],"optimal":[7,55],"consensus":[8,20],"control":[9,21,56],"of":[10,73,83,89],"leaderless":[11],"multi-agent":[12],"systems":[13],"(MASs)":[14],"with":[15],"heterogeneous":[16],"dynamics.":[17,62],"First,":[18],"problem":[22,30],"is":[23,41,49,67,93],"converted":[24],"into":[25],"a":[26,96],"graphical":[27],"minimax":[28],"game":[29],"and":[31],"corresponding":[33],"algebraic":[34],"Riccati":[35],"equation":[36],"(ARE)":[37],"for":[38],"each":[39],"agent":[40],"obtained.":[42],"Then,":[43],"an":[44],"on-policy":[45],"reinforcement":[46],"learning":[47,77],"algorithm":[48,78,92],"proposed":[50,75,91],"to":[51,69,79],"online":[52,76],"learn":[53],"policy":[57],"without":[58],"requiring":[59],"system":[61],"A":[63],"certain":[64],"rank":[65],"condition":[66],"established":[68],"guarantee":[70],"convergence":[72],"unique":[81],"solution":[82],"ARE.":[85],"Finally,":[86],"effectiveness":[88],"demonstrated":[94],"through":[95],"numerical":[97],"simulation.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}