{"id":"https://openalex.org/W3003376977","doi":"https://doi.org/10.1109/access.2020.2970760","title":"H \u221e Control for Discrete-Time Multi-Player Systems via Off-Policy Q-Learning","display_name":"H \u221e Control for Discrete-Time Multi-Player Systems via Off-Policy Q-Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3003376977","doi":"https://doi.org/10.1109/access.2020.2970760","mag":"3003376977"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2970760","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2970760","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08977468.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08977468.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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, Liaoning, China","State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0001-9985-6308","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Liaoning Shihua University, Liaoning, 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/A5057045555","display_name":"Zhenfei Xiao","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenfei Xiao","raw_affiliation_strings":["School of Information and Control Engineering, Liaoning Shihua University, Liaoning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Liaoning Shihua University, Liaoning, China","institution_ids":["https://openalex.org/I166846921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2075,"currency":"USD","value_usd":2075},"apc_paid":{"value":2075,"currency":"USD","value_usd":2075},"fwci":0.5172,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70461725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"8","issue":null,"first_page":"28831","last_page":"28846"},"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9761999845504761,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T12277","display_name":"Frequency Control in Power Systems","score":0.9623000025749207,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.7506533861160278},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7233571410179138},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6537376642227173},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.572689414024353},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5297091007232666},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.5099364519119263},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5096991062164307},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4536159038543701},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.44591382145881653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.346452534198761},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2500517666339874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22629016637802124},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.20695102214813232}],"concepts":[{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.7506533861160278},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7233571410179138},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6537376642227173},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.572689414024353},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5297091007232666},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.5099364519119263},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5096991062164307},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4536159038543701},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.44591382145881653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.346452534198761},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2500517666339874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22629016637802124},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.20695102214813232},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.2970760","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2970760","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08977468.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cc4f37c562be45628cbdaeca5dfef146","is_oa":true,"landing_page_url":"https://doaj.org/article/cc4f37c562be45628cbdaeca5dfef146","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 28831-28846 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2970760","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2970760","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08977468.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2303554934","display_name":null,"funder_award_id":"2018XJJ-005","funder_id":"https://openalex.org/F4320329351","funder_display_name":"Liaoning Shihua University"},{"id":"https://openalex.org/G74425646","display_name":null,"funder_award_id":"61673280","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/F4320329351","display_name":"Liaoning Shihua University","ror":"https://ror.org/00k6c4h29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3003376977.pdf","grobid_xml":"https://content.openalex.org/works/W3003376977.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1488674906","https://openalex.org/W1580348315","https://openalex.org/W1614417283","https://openalex.org/W1912694276","https://openalex.org/W1968908471","https://openalex.org/W1970148674","https://openalex.org/W1983523797","https://openalex.org/W1984525458","https://openalex.org/W2000779032","https://openalex.org/W2005437559","https://openalex.org/W2007784570","https://openalex.org/W2012451615","https://openalex.org/W2013895638","https://openalex.org/W2019338681","https://openalex.org/W2068949505","https://openalex.org/W2087063454","https://openalex.org/W2093831009","https://openalex.org/W2108383324","https://openalex.org/W2109640889","https://openalex.org/W2112103082","https://openalex.org/W2120038868","https://openalex.org/W2139416664","https://openalex.org/W2144557480","https://openalex.org/W2148439597","https://openalex.org/W2155979098","https://openalex.org/W2158755755","https://openalex.org/W2173749656","https://openalex.org/W2288654255","https://openalex.org/W2299109138","https://openalex.org/W2329769476","https://openalex.org/W2498694880","https://openalex.org/W2551113280","https://openalex.org/W2560131027","https://openalex.org/W2564717627","https://openalex.org/W2579592432","https://openalex.org/W2580629550","https://openalex.org/W2590583874","https://openalex.org/W2606378794","https://openalex.org/W2786933610","https://openalex.org/W2800584559","https://openalex.org/W2807176303","https://openalex.org/W2885522335","https://openalex.org/W2887344203","https://openalex.org/W2963674921","https://openalex.org/W2972128755","https://openalex.org/W2990022244","https://openalex.org/W3043164720","https://openalex.org/W3193283090","https://openalex.org/W6715102896","https://openalex.org/W6781357533","https://openalex.org/W6799835771"],"related_works":["https://openalex.org/W4312141693","https://openalex.org/W2602009922","https://openalex.org/W2166339378","https://openalex.org/W1969185016","https://openalex.org/W1536009559","https://openalex.org/W2103821767","https://openalex.org/W3104183741","https://openalex.org/W2037619003","https://openalex.org/W2111030377","https://openalex.org/W1574958246"],"abstract_inverted_index":{"This":[0],"paper":[1,28],"presents":[2],"a":[3],"novel":[4],"off-policy":[5,44,54,123,171],"game":[6,95,137,172],"Q-learning":[7,33,124,173],"algorithm":[8,39,125,174],"to":[9,69,81,163,182],"solve":[10],"H\u221econtrol":[11],"problem":[12,112],"for":[13],"discrete-time":[14],"linear":[15],"multi-player":[16],"systems":[17],"with":[18],"completely":[19],"unknown":[20],"system":[21],"dynamics.":[22],"The":[23],"primary":[24],"contribution":[25],"of":[26,65,94,106,143,158,161,190],"this":[27],"lies":[29],"in":[30,36,42,97,129],"that":[31,79,140],"the":[32,37,53,61,77,83,91,104,107,130,155,164,169,184,188,191],"strategy":[34],"employed":[35],"proposed":[38,170,192],"is":[40,113,126,175],"implemented":[41],"an":[43,117,122],"policy":[45],"iteration":[46],"approach":[47],"other":[48],"than":[49],"on-policy":[50,62],"learning,":[51],"since":[52],"learning":[55],"has":[56],"some":[57],"well-known":[58],"advantages":[59,189],"over":[60],"learning.":[63],"All":[64],"players":[66,145],"struggle":[67],"together":[68],"minimize":[70],"their":[71],"common":[72],"performance":[73,85],"index":[74],"meanwhile":[75],"defeating":[76],"disturbance":[78,99],"tries":[80],"maximize":[82],"specific":[84],"index,":[86],"and":[87,136,186],"finally":[88],"they":[89],"reach":[90],"Nash":[92,108,165],"equilibrium":[93,166],"resulting":[96],"satisfying":[98],"attenuation":[100],"condition.":[101],"For":[102],"finding":[103],"solution":[105,162],"equilibrium,":[109],"H":[110],"control":[111,119,141],"first":[114],"transformed":[115],"into":[116],"optimal":[118],"problem.":[120],"Then":[121],"put":[127],"forward":[128],"typical":[131],"adaptive":[132],"dynamic":[133],"programming":[134],"(ADP)":[135],"architecture,":[138],"such":[139],"policies":[142],"all":[144],"can":[146],"be":[147],"learned":[148],"using":[149,168],"only":[150],"measured":[151],"data.":[152],"More":[153],"importantly,":[154],"rigorous":[156],"proof":[157],"no":[159],"bias":[160],"by":[167],"presented.":[176],"Comparative":[177],"simulation":[178],"results":[179],"are":[180],"provided":[181],"verify":[183],"effectiveness":[185],"demonstrate":[187],"method.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}