{"id":"https://openalex.org/W4408145523","doi":"https://doi.org/10.1109/tcyb.2025.3540967","title":"Discounted Inverse Reinforcement Learning for Linear Quadratic Control","display_name":"Discounted Inverse Reinforcement Learning for Linear Quadratic Control","publication_year":2025,"publication_date":"2025-03-04","ids":{"openalex":"https://openalex.org/W4408145523","doi":"https://doi.org/10.1109/tcyb.2025.3540967","pmid":"https://pubmed.ncbi.nlm.nih.gov/40036510"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2025.3540967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2025.3540967","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/A5107879422","display_name":"Han Wu","orcid":"https://orcid.org/0009-0003-0884-9041"},"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":true,"raw_author_name":"Han Wu","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033355107","display_name":"Qinglei Hu","orcid":"https://orcid.org/0000-0002-5563-310X"},"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":"Qinglei Hu","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102833972","display_name":"Jianying Zheng","orcid":"https://orcid.org/0000-0003-4976-5998"},"institutions":[{"id":"https://openalex.org/I105126617","display_name":"Zhejiang International Studies University","ror":"https://ror.org/01vwvvq12","country_code":"CN","type":"education","lineage":["https://openalex.org/I105126617"]},{"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":"Jianying Zheng","raw_affiliation_strings":["International Innovation Institute, Beihang University, Hangzhou, China","School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"International Innovation Institute, Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I105126617","https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003595553","display_name":"Fei Dong","orcid":"https://orcid.org/0000-0002-2768-6829"},"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":"Fei Dong","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090872855","display_name":"Zhenchao Ouyang","orcid":"https://orcid.org/0000-0003-1304-5366"},"institutions":[{"id":"https://openalex.org/I105126617","display_name":"Zhejiang International Studies University","ror":"https://ror.org/01vwvvq12","country_code":"CN","type":"education","lineage":["https://openalex.org/I105126617"]},{"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":"Zhenchao Ouyang","raw_affiliation_strings":["International Innovation Institute, Beihang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"International Innovation Institute, Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I105126617","https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056294093","display_name":"Dongyu Li","orcid":"https://orcid.org/0000-0001-8338-0536"},"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":"Dongyu Li","raw_affiliation_strings":["School of Cyber Science and Technology, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5107879422"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":7.5417,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96983818,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"55","issue":"4","first_page":"1995","last_page":"2007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9854000210762024,"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":0.9854000210762024,"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","display_name":"Reinforcement","score":0.5552946329116821},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5331854820251465},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4540567696094513},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.42044737935066223},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.41317951679229736},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3850749731063843},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3743872046470642},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3202708959579468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2294539213180542},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19783130288124084},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07552191615104675}],"concepts":[{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5552946329116821},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5331854820251465},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4540567696094513},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.42044737935066223},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41317951679229736},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3850749731063843},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3743872046470642},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3202708959579468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2294539213180542},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19783130288124084},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07552191615104675},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2025.3540967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2025.3540967","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:40036510","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40036510","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/G1110827076","display_name":null,"funder_award_id":"U24B20157","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1137650985","display_name":null,"funder_award_id":"62227812","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1532039694","display_name":null,"funder_award_id":"62473023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4972051119","display_name":null,"funder_award_id":"62303036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7538248125","display_name":null,"funder_award_id":"2023YFB4704500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8130655386","display_name":null,"funder_award_id":"62273017","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1964009772","https://openalex.org/W1972243698","https://openalex.org/W1999172680","https://openalex.org/W1999874108","https://openalex.org/W2029234750","https://openalex.org/W2070469928","https://openalex.org/W2121196039","https://openalex.org/W2148439597","https://openalex.org/W2153160463","https://openalex.org/W2467518411","https://openalex.org/W2484646121","https://openalex.org/W2523345745","https://openalex.org/W2772589676","https://openalex.org/W2907944110","https://openalex.org/W3000451313","https://openalex.org/W3015527773","https://openalex.org/W3114263192","https://openalex.org/W3126316434","https://openalex.org/W3129238832","https://openalex.org/W3130500701","https://openalex.org/W3156476459","https://openalex.org/W3170519291","https://openalex.org/W3195322794","https://openalex.org/W3200276130","https://openalex.org/W3216784117","https://openalex.org/W4206303331","https://openalex.org/W4210704481","https://openalex.org/W4210909794","https://openalex.org/W4220668453","https://openalex.org/W4225647710","https://openalex.org/W4290991295","https://openalex.org/W4296121324","https://openalex.org/W4301886962","https://openalex.org/W4306910464","https://openalex.org/W4310258352","https://openalex.org/W4320008850","https://openalex.org/W4321021825","https://openalex.org/W4327662239","https://openalex.org/W4376256723","https://openalex.org/W4383652256","https://openalex.org/W4388579564","https://openalex.org/W4390120077","https://openalex.org/W4395689166"],"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":{"Linear":[0],"quadratic":[1,35,77],"control":[2,78,89],"with":[3,27,43],"unknown":[4,44],"value":[5,45,84,143],"functions":[6],"and":[7,12,37,86,97,114,142,148],"dynamics":[8,141],"is":[9,94,101],"extremely":[10],"challenging,":[11],"most":[13],"of":[14,25,62,138,151,163],"the":[15,21,28,59,83,87,125,130,139,161,164],"existing":[16],"studies":[17],"have":[18],"focused":[19],"on":[20,124],"regulation":[22,36],"problem,":[23],"incapable":[24],"dealing":[26],"tracking":[29,38],"problem.":[30],"To":[31,81],"solve":[32],"both":[33],"linear":[34,76],"problems":[39],"for":[40,74],"continuous-time":[41],"systems":[42],"functions,":[46],"this":[47],"article":[48],"develops":[49],"a":[50,71,98],"discounted":[51],"inverse":[52],"reinforcement":[53,63],"learning":[54,64],"(DIRL)":[55],"method":[56],"that":[57],"inherits":[58],"model-independent":[60],"property":[61],"(RL).":[65],"More":[66],"specifically,":[67],"we":[68],"first":[69],"formulate":[70],"standard":[72],"paradigm":[73],"solving":[75],"using":[79],"DIRL.":[80],"recover":[82],"function":[85],"target":[88],"gain,":[90],"an":[91],"error":[92],"metric":[93],"elaborately":[95],"constructed,":[96],"quasi-Newton":[99],"algorithm":[100],"adopted":[102],"to":[103],"minimize":[104],"it.":[105],"Furthermore,":[106],"three":[107],"DIRL":[108],"algorithms,":[109,117],"including":[110],"model-based,":[111],"model-free":[112,115],"off-policy,":[113],"on-policy":[116],"are":[118,154],"proposed.":[119],"The":[120,145],"latter":[121],"two":[122],"rely":[123],"expert's":[126],"demonstration":[127],"data":[128],"or":[129],"online":[131],"observed":[132],"data,":[133],"requiring":[134],"no":[135],"prior":[136],"knowledge":[137],"system":[140],"function.":[144],"stability,":[146],"convergence,":[147],"existence":[149],"conditions":[150],"multiple":[152],"solutions":[153],"thoroughly":[155],"analyzed.":[156],"Finally,":[157],"numerical":[158],"simulations":[159],"demonstrate":[160],"effectiveness":[162],"theoretical":[165],"results.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}