{"id":"https://openalex.org/W4408047604","doi":"https://doi.org/10.1109/tcyb.2025.3541815","title":"Reinforcement Learning for <i>H</i> \u221e Optimal Control of Unknown Continuous-Time Linear Systems","display_name":"Reinforcement Learning for <i>H</i> \u221e Optimal Control of Unknown Continuous-Time Linear Systems","publication_year":2025,"publication_date":"2025-02-28","ids":{"openalex":"https://openalex.org/W4408047604","doi":"https://doi.org/10.1109/tcyb.2025.3541815","pmid":"https://pubmed.ncbi.nlm.nih.gov/40031578"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2025.3541815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2025.3541815","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","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/A5100450549","display_name":"Hongyang Li","orcid":"https://orcid.org/0000-0001-5891-134X"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyang Li","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5891-134X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087825639","display_name":"Qinglai Wei","orcid":"https://orcid.org/0000-0001-7002-9800"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinglai Wei","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing"],"raw_orcid":"https://orcid.org/0000-0001-7002-9800","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019828891","display_name":"Xiangmin Tan","orcid":"https://orcid.org/0009-0007-6994-2783"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210120320","display_name":"Institute of Engineering Thermophysics","ror":"https://ror.org/031zj0q48","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210120320"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangmin Tan","raw_affiliation_strings":["Institute of Engineering Thermophysics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-6994-2783","affiliations":[{"raw_affiliation_string":"Institute of Engineering Thermophysics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210120320"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1793,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.87631795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"55","issue":"5","first_page":"2379","last_page":"2389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9656999707221985,"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":0.9656999707221985,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6933478116989136},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6928855180740356},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.49370965361595154},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.43308889865875244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.40792179107666016},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.40266162157058716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3199927508831024},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15798524022102356},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10456380248069763}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6933478116989136},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6928855180740356},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.49370965361595154},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.43308889865875244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40792179107666016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40266162157058716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3199927508831024},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15798524022102356},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10456380248069763}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2025.3541815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2025.3541815","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:40031578","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40031578","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 cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3097182727","display_name":null,"funder_award_id":"L241007","funder_id":"https://openalex.org/F4320334977","funder_display_name":"Beijing Municipal Natural Science Foundation"},{"id":"https://openalex.org/G3852134045","display_name":null,"funder_award_id":"62477045","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5017649286","display_name":null,"funder_award_id":"62425310","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5051330335","display_name":null,"funder_award_id":"4254106","funder_id":"https://openalex.org/F4320334977","funder_display_name":"Beijing Municipal Natural Science Foundation"},{"id":"https://openalex.org/G5938002141","display_name":null,"funder_award_id":"62073321","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6281094892","display_name":null,"funder_award_id":"FDCT-22-009-MISE","funder_id":"https://openalex.org/F4320321655","funder_display_name":"Science and Technology Development Fund"},{"id":"https://openalex.org/G6855475770","display_name":null,"funder_award_id":"0060/2021/A2","funder_id":"https://openalex.org/F4320321655","funder_display_name":"Science and Technology Development Fund"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321655","display_name":"Science and Technology Development Fund","ror":"https://ror.org/044vr6g03"},{"id":"https://openalex.org/F4320334977","display_name":"Beijing Municipal Natural Science Foundation","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1614417283","https://openalex.org/W2055891887","https://openalex.org/W2057236753","https://openalex.org/W2078977470","https://openalex.org/W2088246243","https://openalex.org/W2104843094","https://openalex.org/W2120038868","https://openalex.org/W2139416664","https://openalex.org/W2148439597","https://openalex.org/W2467518411","https://openalex.org/W2484646121","https://openalex.org/W2498694880","https://openalex.org/W2568019971","https://openalex.org/W2580629550","https://openalex.org/W2590419786","https://openalex.org/W2790958326","https://openalex.org/W2942027162","https://openalex.org/W3087896133","https://openalex.org/W4280577141","https://openalex.org/W4295126615","https://openalex.org/W4362602398","https://openalex.org/W4364856217","https://openalex.org/W4379409406","https://openalex.org/W4383112398","https://openalex.org/W4388076083","https://openalex.org/W4397019666","https://openalex.org/W4399033639","https://openalex.org/W4399487226","https://openalex.org/W4399666171","https://openalex.org/W4400877505","https://openalex.org/W4401687408","https://openalex.org/W4402123867","https://openalex.org/W4403095606","https://openalex.org/W4404132117","https://openalex.org/W4405934041","https://openalex.org/W4406067016"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Designing":[0],"the":[1,5,12,23,61,64,94,104,117,128,133,136,146,149],"optimal":[2,27,46,105],"control":[3,28,47,106],"for":[4,32],"practical":[6],"systems":[7,35],"is":[8,30,69,142],"challenging":[9],"due":[10],"to":[11,59,71,80,90,102,132],"unknown":[13,37],"system":[14,86],"dynamics":[15],"and":[16,75],"unavoidable":[17],"external":[18],"disturbances.":[19],"In":[20,88],"this":[21],"article,":[22],"$H_{\\infty":[24,43],"}":[25,44],"$":[26,45],"problem":[29],"investigated":[31],"continuous-time":[33],"linear":[34],"with":[36],"dynamics.":[38],"The":[39,114],"existing":[40],"reinforcement":[41,97,120],"learning-based":[42],"methods":[48],"require":[49],"persistence":[50],"of":[51,63,84,116,148],"excitation":[52,112,138],"(PE)":[53],"condition":[54,68],"or":[55],"data":[56,76],"storage":[57,77],"mechanism":[58,78],"guarantee":[60],"convergence":[62],"algorithms.":[65,151],"However,":[66],"PE":[67],"hard":[70],"be":[72],"monitored":[73],"online":[74],"requires":[79],"store":[81],"huge":[82],"amounts":[83],"past":[85],"data.":[87],"order":[89],"solve":[91],"these":[92],"problems,":[93],"initial":[95,111,118,137],"excitation-based":[96,119],"learning":[98,121],"algorithms":[99,122,130],"are":[100,123],"presented":[101,129,150],"learn":[103],"policy":[107],"under":[108,135],"an":[109],"online-verifiable":[110],"condition.":[113,139],"properties":[115],"analyzed,":[124],"which":[125,144],"show":[126],"that":[127],"converge":[131],"optimum":[134],"Numerical":[140],"analysis":[141],"provided":[143],"demonstrates":[145],"correctness":[147]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-03-01T00:00:00"}