{"id":"https://openalex.org/W4210405871","doi":"https://doi.org/10.1631/fitee.2000446","title":"Minimax Q-learning design for H\u221e control of linear discrete-time systems","display_name":"Minimax Q-learning design for H\u221e control of linear discrete-time systems","publication_year":2022,"publication_date":"2022-02-04","ids":{"openalex":"https://openalex.org/W4210405871","doi":"https://doi.org/10.1631/fitee.2000446"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.2000446","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2000446","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-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/A5101733708","display_name":"Xinxing Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinxing Li","raw_affiliation_strings":["Information Science Academy, China Electronics Technology Group Corporation, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6264-2955","affiliations":[{"raw_affiliation_string":"Information Science Academy, China Electronics Technology Group Corporation, Beijing, China","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008064723","display_name":"Lele Xi","orcid":"https://orcid.org/0000-0002-8024-3349"},"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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lele Xi","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China","School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8024-3349","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017187516","display_name":"Wenzhong Zha","orcid":"https://orcid.org/0000-0003-2718-5052"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenzhong Zha","raw_affiliation_strings":["Information Science Academy, China Electronics Technology Group Corporation, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2718-5052","affiliations":[{"raw_affiliation_string":"Information Science Academy, China Electronics Technology Group Corporation, Beijing, China","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055648384","display_name":"Zhihong Peng","orcid":"https://orcid.org/0000-0001-9430-8652"},"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":"Zhihong Peng","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017187516"],"corresponding_institution_ids":["https://openalex.org/I2800372957"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":1.1954,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79861595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"23","issue":"3","first_page":"438","last_page":"451"},"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":0.9943000078201294,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9733999967575073,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.8687723278999329},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.761616051197052},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7615057229995728},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6554611325263977},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5688574314117432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.568300724029541},{"id":"https://openalex.org/keywords/algebraic-riccati-equation","display_name":"Algebraic Riccati equation","score":0.452388733625412},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.45011648535728455},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44258779287338257},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4174799621105194},{"id":"https://openalex.org/keywords/riccati-equation","display_name":"Riccati equation","score":0.40330544114112854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33570826053619385},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2793557643890381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11863026022911072}],"concepts":[{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.8687723278999329},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.761616051197052},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7615057229995728},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6554611325263977},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5688574314117432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.568300724029541},{"id":"https://openalex.org/C13847129","wikidata":"https://www.wikidata.org/wiki/Q4723989","display_name":"Algebraic Riccati equation","level":4,"score":0.452388733625412},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.45011648535728455},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44258779287338257},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4174799621105194},{"id":"https://openalex.org/C45473103","wikidata":"https://www.wikidata.org/wiki/Q851503","display_name":"Riccati equation","level":3,"score":0.40330544114112854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33570826053619385},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2793557643890381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11863026022911072},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.2000446","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2000446","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W601351931","https://openalex.org/W1614417283","https://openalex.org/W1973039793","https://openalex.org/W2005437559","https://openalex.org/W2012451615","https://openalex.org/W2042106612","https://openalex.org/W2078977470","https://openalex.org/W2081242334","https://openalex.org/W2112507254","https://openalex.org/W2136064843","https://openalex.org/W2141076336","https://openalex.org/W2329769476","https://openalex.org/W2405379562","https://openalex.org/W2498694880","https://openalex.org/W2579592432","https://openalex.org/W2580629550","https://openalex.org/W2735449579","https://openalex.org/W2772589676","https://openalex.org/W2802164917","https://openalex.org/W2807176303","https://openalex.org/W2884970059","https://openalex.org/W2887322987","https://openalex.org/W2930306639","https://openalex.org/W2942227124","https://openalex.org/W2966477753","https://openalex.org/W2983705688","https://openalex.org/W3009014967","https://openalex.org/W4214717370","https://openalex.org/W6677916085"],"related_works":["https://openalex.org/W2107449083","https://openalex.org/W2056488881","https://openalex.org/W3158610175","https://openalex.org/W2781068818","https://openalex.org/W3152984843","https://openalex.org/W3128310684","https://openalex.org/W2993537844","https://openalex.org/W4287997452","https://openalex.org/W1612466322","https://openalex.org/W2057886085"],"abstract_inverted_index":{"The":[0,91],"H":[1,25,46,212,235],"\u221e":[2,26,47,213,236],"control":[3,105,155],"method":[4,68,86,146,208],"is":[5,20,69,81,137],"an":[6,45,75,158,211,217],"effective":[7],"approach":[8],"for":[9,35,49,87,107,216],"attenuating":[10],"the":[11,24,30,42,55,72,89,103,108,111,116,121,142,149,175,198,203,228,233],"effect":[12],"of":[13,44,74,167],"disturbances":[14],"on":[15,71],"practical":[16],"systems,":[17],"but":[18],"it":[19],"difficult":[21],"to":[22,29,83,148,209],"obtain":[23],"controller":[27,48,109,215,238],"due":[28],"nonlinear":[31],"Hamilton\u2014Jacobi\u2014Isaacs":[32],"equation,":[33],"even":[34],"linear":[36,50],"systems.":[37,52],"This":[38],"study":[39],"deals":[40],"with":[41],"design":[43,210],"discrete-time":[51],"To":[53],"solve":[54],"related":[56],"game":[57],"algebraic":[58],"Riccati":[59],"equation":[60],"(GARE),":[61],"a":[62,131],"novel":[63,132],"model-free":[64],"minimax":[65,93,143,205],"Q":[66,94,128,144,206],"-learning":[67,95,129,145,207],"developed,":[70],"basis":[73],"offline":[76],"policy":[77,134],"iteration":[78],"algorithm,":[79],"which":[80,97],"shown":[82],"be":[84,179],"Newton\u2019s":[85],"solving":[88],"GARE.":[90],"proposed":[92,204],"method,":[96],"employs":[98],"off-policy":[99],"reinforcement":[100],"learning,":[101],"learns":[102],"optimal":[104],"policies":[106,156,186],"and":[110,157,227],"disturbance":[112,241],"online,":[113],"using":[114],"only":[115],"state":[117],"samples":[118],"generated":[119],"by":[120,182],"implemented":[122],"behavior":[123,185],"policies.":[124],"Different":[125],"from":[126,224],"existing":[127],"methods,":[130],"gradient-based":[133],"improvement":[135],"scheme":[136],"proposed.":[138],"We":[139],"prove":[140],"that":[141,164,222,232],"converges":[147],"saddle":[150],"solution":[151],"under":[152],"initially":[153],"admissible":[154],"appropriate":[159,184],"positive":[160],"learning":[161],"rate,":[162],"provided":[163],"certain":[165,188],"persistence":[166],"excitation":[168,189,194],"(PE)":[169],"conditions":[170,177],"are":[171],"satisfied.":[172],"In":[173,197],"addition,":[174],"PE":[176],"can":[178],"easily":[180],"met":[181],"choosing":[183],"containing":[187],"noises,":[190],"without":[191],"causing":[192],"any":[193],"noise":[195],"bias.":[196],"simulation":[199,229],"study,":[200],"we":[201],"apply":[202],"load-frequency":[214,237],"electrical":[218],"power":[219],"system":[220],"generator":[221],"suffers":[223],"load":[225],"disturbance,":[226],"results":[230],"indicate":[231],"obtained":[234],"has":[239],"good":[240],"rejection":[242],"performance.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}