{"id":"https://openalex.org/W3102329144","doi":"https://doi.org/10.1109/access.2020.3038674","title":"Output Feedback H\u221e Control for Linear Discrete-Time Multi-Player Systems With Multi-Source Disturbances Using Off-Policy Q-Learning","display_name":"Output Feedback H\u221e Control for Linear Discrete-Time Multi-Player Systems With Multi-Source Disturbances Using Off-Policy Q-Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3102329144","doi":"https://doi.org/10.1109/access.2020.3038674","mag":"3102329144"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3038674","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3038674","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09261350.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":null,"license_id":null,"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/ielx7/6287639/6514899/09261350.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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"]}]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinna Li","raw_affiliation_strings":["School of Information and Control Engineering, Liaoning Shihua University, Liaoning, 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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741313","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-3216-6246"},"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":"Ping Li","raw_affiliation_strings":["School of Information and Control Engineering, Liaoning Shihua University, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0002-3216-6246","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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I166846921"],"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":8,"citation_normalized_percentile":{"value":0.7308627,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"8","issue":null,"first_page":"208938","last_page":"208951"},"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/T12277","display_name":"Frequency Control in Power Systems","score":0.9598000049591064,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9277999997138977,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.6767287850379944},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.655846118927002},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6274725198745728},{"id":"https://openalex.org/keywords/mathematical-proof","display_name":"Mathematical proof","score":0.565083384513855},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.5355889797210693},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.5182116627693176},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4743983745574951},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46838003396987915},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45251962542533875},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41613101959228516},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.41351255774497986},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3479102551937103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.317177951335907},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.271536648273468},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25046277046203613},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.2078058123588562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6767287850379944},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.655846118927002},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6274725198745728},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.565083384513855},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.5355889797210693},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.5182116627693176},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4743983745574951},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46838003396987915},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45251962542533875},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41613101959228516},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.41351255774497986},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3479102551937103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.317177951335907},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.271536648273468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25046277046203613},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.2078058123588562},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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":2,"locations":[{"id":"doi:10.1109/access.2020.3038674","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3038674","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09261350.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3e357ede12024911adea612ed20ecdab","is_oa":true,"landing_page_url":"https://doaj.org/article/3e357ede12024911adea612ed20ecdab","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 208938-208951 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3038674","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3038674","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09261350.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.550000011920929,"display_name":"Partnerships for the 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"},{"id":"https://openalex.org/G7510781838","display_name":null,"funder_award_id":"(61673199)","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8129005080","display_name":null,"funder_award_id":"62073158","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/W3102329144.pdf","grobid_xml":"https://content.openalex.org/works/W3102329144.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1614417283","https://openalex.org/W1972243698","https://openalex.org/W1977671496","https://openalex.org/W2005437559","https://openalex.org/W2013219041","https://openalex.org/W2013895638","https://openalex.org/W2035003264","https://openalex.org/W2041866840","https://openalex.org/W2071004621","https://openalex.org/W2121764658","https://openalex.org/W2125102784","https://openalex.org/W2139416664","https://openalex.org/W2333120204","https://openalex.org/W2340995602","https://openalex.org/W2484646121","https://openalex.org/W2580629550","https://openalex.org/W2590583874","https://openalex.org/W2593469813","https://openalex.org/W2761756876","https://openalex.org/W2766143943","https://openalex.org/W2800584559","https://openalex.org/W2807176303","https://openalex.org/W2885522335","https://openalex.org/W2885604019","https://openalex.org/W2887344203","https://openalex.org/W2912832158","https://openalex.org/W2942227124","https://openalex.org/W2983464671","https://openalex.org/W2990022244","https://openalex.org/W2997938989","https://openalex.org/W3003376977","https://openalex.org/W3005335721","https://openalex.org/W3016762526","https://openalex.org/W3043748799"],"related_works":["https://openalex.org/W4285537323","https://openalex.org/W2379312070","https://openalex.org/W2136173754","https://openalex.org/W2332086753","https://openalex.org/W2953025626","https://openalex.org/W2499081552","https://openalex.org/W2110050003","https://openalex.org/W3104183741","https://openalex.org/W2366053282","https://openalex.org/W2602009922"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,46,90],"data-driven":[4],"optimal":[5],"control":[6,72],"method":[7],"based":[8,71],"on":[9],"adaptive":[10],"dynamic":[11],"programming":[12],"and":[13,74,100,131],"game":[14,48,56,93],"theory":[15],"is":[16,104],"presented":[17],"for":[18,28,115],"solving":[19],"the":[20,25,42,51,59,68,80,108,120,141,144],"output":[21,69],"feedback":[22,70],"solutions":[23,53,134],"of":[24,82,122,128,133,143],"H\u221econtrol":[26,43,109],"problem":[27,44,49,110],"linear":[29,116],"discrete-time":[30],"systems":[31,118],"with":[32,97],"multiple":[33],"players":[34,103],"subject":[35],"to":[36,55],"multi-source":[37],"disturbances.":[38],"We":[39],"first":[40],"transform":[41],"into":[45],"multi-player":[47,117],"following":[50],"theoretical":[52],"according":[54],"theory.":[57],"Since":[58],"system":[60,123],"state":[61],"may":[62],"not":[63],"be":[64,112],"measurable,":[65],"we":[66],"derive":[67],"policies":[73],"disturbances":[75],"through":[76],"mathematical":[77],"operations.":[78],"Considering":[79],"advantages":[81],"off-policy":[83,92],"reinforcement":[84],"learning":[85],"(RL)":[86],"over":[87],"on-policy":[88],"RL,":[89],"novel":[91],"Q-learning":[94],"algorithm":[95,129],"dealing":[96],"mixed":[98],"competition":[99],"cooperation":[101],"among":[102],"developed,":[105],"such":[106],"that":[107],"can":[111],"finally":[113],"solved":[114],"without":[119],"knowledge":[121],"dynamics.":[124],"Moreover,":[125],"rigorous":[126],"proofs":[127],"convergence":[130],"unbiasedness":[132],"are":[135],"presented.":[136],"Finally,":[137],"simulation":[138],"results":[139],"demonstrated":[140],"effectiveness":[142],"proposed":[145],"method.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}
