{"id":"https://openalex.org/W3019638220","doi":"https://doi.org/10.1109/tnnls.2020.2985738","title":"Hierarchical Optimal Synchronization for Linear Systems via Reinforcement Learning: A Stackelberg\u2013Nash Game Perspective","display_name":"Hierarchical Optimal Synchronization for Linear Systems via Reinforcement Learning: A Stackelberg\u2013Nash Game Perspective","publication_year":2020,"publication_date":"2020-04-27","ids":{"openalex":"https://openalex.org/W3019638220","doi":"https://doi.org/10.1109/tnnls.2020.2985738","mag":"3019638220","pmid":"https://pubmed.ncbi.nlm.nih.gov/32340962"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.2985738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.2985738","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100404496","display_name":"Man Li","orcid":"https://orcid.org/0000-0002-9776-1628"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Man Li","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053071794","display_name":"Jiahu Qin","orcid":"https://orcid.org/0000-0001-7580-0836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahu Qin","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101997909","display_name":"Qichao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qichao Ma","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108050907","display_name":"Wei Xing Zheng","orcid":"https://orcid.org/0000-0002-0572-5938"},"institutions":[{"id":"https://openalex.org/I63525965","display_name":"Western Sydney University","ror":"https://ror.org/03t52dk35","country_code":"AU","type":"education","lineage":["https://openalex.org/I63525965"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei Xing Zheng","raw_affiliation_strings":["School of Computer, Data and Mathematical Sciences, Western Sydney University, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Data and Mathematical Sciences, Western Sydney University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I63525965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025987638","display_name":"Yu Kang","orcid":"https://orcid.org/0000-0002-8706-3252"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Kang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China","Institute of Advanced Technology, University of Science and Technology of China, Hefei, China","Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems, Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Fire Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Institute of Advanced Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory of Fire Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5656,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.93072371,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":"4","first_page":"1600","last_page":"1611"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11347","display_name":"Neural Networks Stability and Synchronization","score":0.9995999932289124,"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/T11347","display_name":"Neural Networks Stability and Synchronization","score":0.9995999932289124,"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":0.9994999766349792,"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":0.9980999827384949,"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/hamilton\u2013jacobi\u2013bellman-equation","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","score":0.7948024272918701},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7137494683265686},{"id":"https://openalex.org/keywords/stackelberg-competition","display_name":"Stackelberg competition","score":0.6846604943275452},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6771140098571777},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6413404941558838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5844877362251282},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5131083726882935},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4501200318336487},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.3533955216407776},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3532674014568329},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3428329825401306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21284782886505127},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.18536999821662903}],"concepts":[{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.7948024272918701},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7137494683265686},{"id":"https://openalex.org/C199510392","wikidata":"https://www.wikidata.org/wiki/Q1184602","display_name":"Stackelberg competition","level":2,"score":0.6846604943275452},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6771140098571777},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6413404941558838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5844877362251282},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5131083726882935},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4501200318336487},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.3533955216407776},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3532674014568329},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3428329825401306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21284782886505127},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.18536999821662903},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2020.2985738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.2985738","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:32340962","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32340962","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G4086287620","display_name":null,"funder_award_id":"61873252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6110658884","display_name":null,"funder_award_id":"61725304","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7536121652","display_name":null,"funder_award_id":"P00025091","funder_id":"https://openalex.org/F4320330843","funder_display_name":"NSW Cyber Security Network"},{"id":"https://openalex.org/G8871303421","display_name":null,"funder_award_id":"61673361","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8898690338","display_name":null,"funder_award_id":"61922076","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/F4320330843","display_name":"NSW Cyber Security Network","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W847771221","https://openalex.org/W1513689897","https://openalex.org/W1578630563","https://openalex.org/W1968076711","https://openalex.org/W1997974219","https://openalex.org/W2017999653","https://openalex.org/W2081514674","https://openalex.org/W2085778185","https://openalex.org/W2092839484","https://openalex.org/W2098432798","https://openalex.org/W2108286682","https://openalex.org/W2108383324","https://openalex.org/W2121863487","https://openalex.org/W2160420729","https://openalex.org/W2189990206","https://openalex.org/W2206832235","https://openalex.org/W2277723519","https://openalex.org/W2293710996","https://openalex.org/W2508512712","https://openalex.org/W2556875844","https://openalex.org/W2579592432","https://openalex.org/W2594875618","https://openalex.org/W2597306162","https://openalex.org/W2606378794","https://openalex.org/W2615830653","https://openalex.org/W2793914020","https://openalex.org/W2797305442","https://openalex.org/W2803623613","https://openalex.org/W2805542056","https://openalex.org/W2888258418","https://openalex.org/W2888559564","https://openalex.org/W2909993591","https://openalex.org/W2962991497","https://openalex.org/W3106116738","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2032834442","https://openalex.org/W3153900688","https://openalex.org/W2115544975","https://openalex.org/W2902017027","https://openalex.org/W1654696814","https://openalex.org/W4291598237","https://openalex.org/W2766998270","https://openalex.org/W4292330635","https://openalex.org/W3168988147","https://openalex.org/W2733656312"],"abstract_inverted_index":{"Considering":[0],"the":[1,5,64,73,76,95,100,103,108,153,162,167,182,186,194,206,209],"fact":[2],"that":[3,122],"in":[4,43,80,124],"real":[6],"world,":[7],"a":[8,21,47,131,138],"certain":[9],"agent":[10,34,53],"may":[11],"have":[12],"some":[13],"sort":[14],"of":[15,31,102,196,208],"advantage":[16],"to":[17,59,90,99,119,158,180,192,204],"act":[18],"before":[19],"others,":[20,60],"novel":[22],"hierarchical":[23],"optimal":[24,74,168],"synchronization":[25],"problem":[26],"for":[27,106],"linear":[28],"systems,":[29],"composed":[30],"one":[32],"major":[33,52],"and":[35,41,61,93,116,161,185],"multiple":[36],"minor":[37,65],"agents,":[38,107],"is":[39,156,190,202],"formulated":[40],"studied":[42],"this":[44,172],"article":[45],"from":[46],"Stackelberg-Nash":[48,96],"game":[49],"perspective.":[50],"The":[51],"herein":[54],"makes":[55],"its":[56],"decision":[57],"prior":[58],"then,":[62],"all":[63],"agents":[66],"determine":[67],"their":[68],"actions":[69],"simultaneously.":[70],"To":[71,170],"seek":[72],"controllers,":[75],"Hamilton-Jacobi-Bellman":[77],"(HJB)":[78],"equations":[79,111],"coupled":[81,115],"forms":[82],"are":[83,87,112,165,178],"established,":[84],"whose":[85],"solutions":[86],"further":[88],"proven":[89],"be":[91,159],"stable":[92],"constitute":[94],"equilibrium.":[97],"Due":[98],"introduction":[101],"asymmetric":[104],"roles":[105],"established":[109],"HJB":[110],"more":[113,117],"strongly":[114],"difficult":[118],"solve":[120],"than":[121],"given":[123],"most":[125],"existing":[126],"works.":[127],"Therefore,":[128],"we":[129],"propose":[130],"new":[132],"reinforcement":[133],"learning":[134],"(RL)":[135],"algorithm,":[136,143,174],"i.e.,":[137],"two-level":[139],"value":[140,183],"iteration":[141],"(VI)":[142],"which":[144],"does":[145],"not":[146],"rely":[147],"on":[148],"complete":[149],"system":[150],"matrices.":[151],"Furthermore,":[152],"proposed":[154,210],"algorithm":[155],"shown":[157],"convergent,":[160],"converged":[163],"values":[164],"exactly":[166],"ones.":[169],"implement":[171],"VI":[173],"neural":[175],"networks":[176],"(NNs)":[177],"employed":[179],"approximate":[181],"functions,":[184],"gradient":[187],"descent":[188],"method":[189],"used":[191],"update":[193],"weights":[195],"NNs.":[197],"Finally,":[198],"an":[199],"illustrative":[200],"example":[201],"provided":[203],"verify":[205],"effectiveness":[207],"algorithm.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}