{"id":"https://openalex.org/W2012451615","doi":"https://doi.org/10.1109/tcyb.2014.2319577","title":"Off-Policy Reinforcement Learning for $ H_\\infty $ Control Design","display_name":"Off-Policy Reinforcement Learning for $ H_\\infty $ Control Design","publication_year":2014,"publication_date":"2014-05-09","ids":{"openalex":"https://openalex.org/W2012451615","doi":"https://doi.org/10.1109/tcyb.2014.2319577","mag":"2012451615","pmid":"https://pubmed.ncbi.nlm.nih.gov/25532162"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2014.2319577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2014.2319577","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":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1311.6107","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012004938","display_name":"Biao Luo","orcid":"https://orcid.org/0000-0002-3353-2586"},"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/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Luo","raw_affiliation_strings":["Science and Technology on Aircraft Control Laboratory, Beihang University (Beijing University of Aeronautics and Astronautics), Beijing, China","State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Aircraft Control Laboratory, Beihang University (Beijing University of Aeronautics and Astronautics), Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000266144","display_name":"Huai\u2010Ning Wu","orcid":"https://orcid.org/0000-0002-4366-5147"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huai-Ning Wu","raw_affiliation_strings":["Science and Technology on Aircraft Control Laboratory, Beihang University (Beijing University of Aeronautics and Astronautics), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Aircraft Control Laboratory, Beihang University (Beijing University of Aeronautics and Astronautics), Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074290686","display_name":"Tingwen Huang","orcid":"https://orcid.org/0000-0001-9610-846X"},"institutions":[{"id":"https://openalex.org/I58152225","display_name":"Texas A&M University at Qatar","ror":"https://ror.org/03vb4dm14","country_code":"QA","type":"education","lineage":["https://openalex.org/I58152225","https://openalex.org/I91045830"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Tingwen Huang","raw_affiliation_strings":["Texas A& M University at Qatar, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A& M University at Qatar, Doha, Qatar","institution_ids":["https://openalex.org/I58152225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":31.7561,"has_fulltext":true,"cited_by_count":361,"citation_normalized_percentile":{"value":0.9985266,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"45","issue":"1","first_page":"65","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9873999953269958,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9805999994277954,"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/notation","display_name":"Notation","score":0.6106885671615601},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5208078622817993},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.38027340173721313},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.3323415517807007},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.32560914754867554}],"concepts":[{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.6106885671615601},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5208078622817993},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.38027340173721313},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.3323415517807007},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.32560914754867554}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcyb.2014.2319577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2014.2319577","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:25532162","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25532162","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":"Journal Article"},{"id":"pmh:oai:arXiv.org:1311.6107","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1311.6107","pdf_url":"https://arxiv.org/pdf/1311.6107","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1311.6107","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1311.6107","pdf_url":"https://arxiv.org/pdf/1311.6107","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2145544449","display_name":null,"funder_award_id":"61121003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G284778911","display_name":null,"funder_award_id":"61121003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3545376117","display_name":null,"funder_award_id":"NPRP 4-1162-1-181","funder_id":"https://openalex.org/F4320332753","funder_display_name":"Qatar National Research Fund"},{"id":"https://openalex.org/G4095704533","display_name":null,"funder_award_id":"4-1162-1-181","funder_id":"https://openalex.org/F4320332753","funder_display_name":"Qatar National Research Fund"},{"id":"https://openalex.org/G4145481528","display_name":null,"funder_award_id":"2012CB720003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6066862572","display_name":null,"funder_award_id":"2012CB720003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7186521472","display_name":null,"funder_award_id":"9140C480301130C48001","funder_id":"https://openalex.org/F4320321125","funder_display_name":"Beihang University"},{"id":"https://openalex.org/G8290000575","display_name":null,"funder_award_id":"4-1162-1-181","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8434169383","display_name":null,"funder_award_id":"NPRP 4-1162-1-181","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309815","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321038","display_name":"Fonds National de la Recherche Luxembourg","ror":"https://ror.org/039z13y21"},{"id":"https://openalex.org/F4320321125","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56"},{"id":"https://openalex.org/F4320332753","display_name":"Qatar National Research Fund","ror":"https://ror.org/01svaqq28"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2012451615.pdf","grobid_xml":"https://content.openalex.org/works/W2012451615.grobid-xml"},"referenced_works_count":82,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W627388892","https://openalex.org/W1481779519","https://openalex.org/W1487127700","https://openalex.org/W1492186721","https://openalex.org/W1504212531","https://openalex.org/W1505506151","https://openalex.org/W1513689897","https://openalex.org/W1559107966","https://openalex.org/W1567906773","https://openalex.org/W1579118835","https://openalex.org/W1580348315","https://openalex.org/W1600046456","https://openalex.org/W1601081659","https://openalex.org/W1606119439","https://openalex.org/W1835291487","https://openalex.org/W1868559974","https://openalex.org/W1983089547","https://openalex.org/W1983523797","https://openalex.org/W1986864433","https://openalex.org/W1986957722","https://openalex.org/W1990401127","https://openalex.org/W1997603681","https://openalex.org/W1999678919","https://openalex.org/W2002260889","https://openalex.org/W2016088733","https://openalex.org/W2019338681","https://openalex.org/W2019478222","https://openalex.org/W2024303516","https://openalex.org/W2024376777","https://openalex.org/W2024780670","https://openalex.org/W2037025184","https://openalex.org/W2037539475","https://openalex.org/W2045283962","https://openalex.org/W2045689494","https://openalex.org/W2046386580","https://openalex.org/W2047090868","https://openalex.org/W2047470736","https://openalex.org/W2048687352","https://openalex.org/W2052305027","https://openalex.org/W2052399669","https://openalex.org/W2055891887","https://openalex.org/W2060605484","https://openalex.org/W2065313971","https://openalex.org/W2066828334","https://openalex.org/W2068328804","https://openalex.org/W2081242334","https://openalex.org/W2081514674","https://openalex.org/W2083283377","https://openalex.org/W2085194340","https://openalex.org/W2088246243","https://openalex.org/W2098035803","https://openalex.org/W2098432798","https://openalex.org/W2100276679","https://openalex.org/W2107726111","https://openalex.org/W2108286682","https://openalex.org/W2109640889","https://openalex.org/W2110357265","https://openalex.org/W2111980775","https://openalex.org/W2112507254","https://openalex.org/W2116479681","https://openalex.org/W2116488102","https://openalex.org/W2120038868","https://openalex.org/W2121863487","https://openalex.org/W2132468772","https://openalex.org/W2134024695","https://openalex.org/W2137092694","https://openalex.org/W2150841368","https://openalex.org/W2160561608","https://openalex.org/W2316629923","https://openalex.org/W2331220696","https://openalex.org/W2487144912","https://openalex.org/W2612353123","https://openalex.org/W2971156298","https://openalex.org/W3195133498","https://openalex.org/W4214717370","https://openalex.org/W4245176833","https://openalex.org/W4285719527","https://openalex.org/W6600556750","https://openalex.org/W6630225054","https://openalex.org/W6635798015","https://openalex.org/W6656684102"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2504004674","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2962838298"],"abstract_inverted_index":{"The":[0],"H\u221e":[1,21],"control":[2,22],"design":[3],"problem":[4,23],"is":[5,16,35,42,66,84,105,127,144,153,169],"considered":[6],"for":[7,56,132],"nonlinear":[8,20,37],"systems":[9],"with":[10,118],"unknown":[11],"internal":[12],"system":[13,64,95,100,113],"model.":[14],"It":[15],"known":[17],"that":[18,41],"the":[19,29,62,88,108,112,123,157,163],"can":[24,115],"be":[25,46,54,116],"transformed":[26],"into":[27],"solving":[28,58],"so-called":[30],"Hamilton-Jacobi-Isaacs":[31],"(HJI)":[32],"equation,":[33,60],"which":[34,126],"a":[36,138,147,172,181],"partial":[38],"differential":[39],"equation":[40,92],"generally":[43],"impossible":[44],"to":[45,70,86,180],"solved":[47],"analytically.":[48],"Even":[49],"worse,":[50],"model-based":[51],"approaches":[52],"cannot":[53],"used":[55],"approximately":[57],"HJI":[59,91],"when":[61],"accurate":[63],"model":[65],"unavailable":[67],"or":[68],"costly":[69],"obtain":[71],"in":[72],"practice.":[73],"To":[74],"overcome":[75],"these":[76],"difficulties,":[77],"an":[78],"off-policy":[79,109,166],"reinforcement":[80],"leaning":[81],"(RL)":[82],"method":[83,158,168],"introduced":[85],"learn":[87],"solution":[89],"of":[90,98,159],"from":[93],"real":[94],"data":[96,114],"instead":[97],"mathematical":[99],"model,":[101],"and":[102,130,146,177],"its":[103],"convergence":[104],"proved.":[106],"In":[107],"RL":[110,167],"method,":[111],"generated":[117],"arbitrary":[119],"policies":[120],"rather":[121],"than":[122],"evaluating":[124],"policy,":[125],"extremely":[128],"important":[129],"promising":[131],"practical":[133],"systems.":[134],"For":[135],"implementation":[136],"purpose,":[137],"neural":[139],"network":[140],"(NN)-based":[141],"actor-critic":[142],"structure":[143],"employed":[145],"least-square":[148],"NN":[149],"weight":[150],"update":[151],"algorithm":[152],"derived":[154],"based":[155],"on":[156,171],"weighted":[160],"residuals.":[161],"Finally,":[162],"developed":[164],"NN-based":[165],"tested":[170],"linear":[173],"F16":[174],"aircraft":[175],"plant,":[176],"further":[178],"applied":[179],"rotational/translational":[182],"actuator":[183],"system.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":36},{"year":2023,"cited_by_count":31},{"year":2022,"cited_by_count":28},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":35},{"year":2018,"cited_by_count":44},{"year":2017,"cited_by_count":43},{"year":2016,"cited_by_count":24},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":6}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2016-06-24T00:00:00"}