{"id":"https://openalex.org/W7123355985","doi":"https://doi.org/10.1109/cdc57313.2025.11312396","title":"Efficient Inverse Reinforcement Learning for Unknown Discrete-Time Systems","display_name":"Efficient Inverse Reinforcement Learning for Unknown Discrete-Time Systems","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123355985","doi":"https://doi.org/10.1109/cdc57313.2025.11312396"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5147460503","display_name":"Longyang Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longyang Huang","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Automation and Intelligent Sensing,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Automation and Intelligent Sensing,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121040954","display_name":"Ruonan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruonan Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Automation and Intelligent Sensing,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Automation and Intelligent Sensing,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064564307","display_name":"Zehua Jia","orcid":"https://orcid.org/0000-0001-9936-5883"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Jia","raw_affiliation_strings":["Hainan University,School of Information and Communication Engineering,Haikou,China,570228"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hainan University,School of Information and Communication Engineering,Haikou,China,570228","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414775","display_name":"Weidong Zhang","orcid":"https://orcid.org/0000-0002-4700-1276"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Automation and Intelligent Sensing,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Automation and Intelligent Sensing,China,200240","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61034775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4188","last_page":"4193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9843000173568726,"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":0.9843000173568726,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.0020000000949949026,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0017000000225380063,"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/stability","display_name":"Stability (learning theory)","score":0.6241000294685364},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6107000112533569},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5324000120162964},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4350999891757965},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.43130001425743103},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4142000079154968},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4065999984741211},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.40630000829696655}],"concepts":[{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6241000294685364},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6107000112533569},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5324000120162964},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5268999934196472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49059998989105225},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4805000126361847},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4350999891757965},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4296000003814697},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.3456000089645386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3325999975204468},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C184497298","wikidata":"https://www.wikidata.org/wiki/Q7229773","display_name":"Population-based incremental learning","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C122129529","wikidata":"https://www.wikidata.org/wiki/Q2634828","display_name":"Inverse system","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2011386240","https://openalex.org/W2062525454","https://openalex.org/W2467518411","https://openalex.org/W2484646121","https://openalex.org/W2903410452","https://openalex.org/W3037298378","https://openalex.org/W3038972086","https://openalex.org/W3129238832","https://openalex.org/W3138984732","https://openalex.org/W3197594072","https://openalex.org/W3200276130","https://openalex.org/W3209118784","https://openalex.org/W4210665702","https://openalex.org/W4225647710","https://openalex.org/W4315472194","https://openalex.org/W4321021825","https://openalex.org/W4362722144","https://openalex.org/W4383652256","https://openalex.org/W4390120077","https://openalex.org/W4407827592","https://openalex.org/W4408145523","https://openalex.org/W4408441459"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"develops":[2],"a":[3,34],"data-driven":[4,93],"inverse":[5,36,94],"Q-learning":[6,37],"algorithm":[7,38,48,69,101,125],"for":[8],"unknown":[9],"discrete-time":[10],"linear":[11],"time-invariant":[12],"systems.":[13],"A":[14],"novel":[15],"data":[16],"representation":[17],"method":[18],"is":[19,39,70,74,88,126],"designed":[20],"to":[21,41],"construct":[22],"the":[23,26,30,43,68,78,81,99,124],"iteration":[24],"of":[25,32,67,80,107,123],"cost":[27,44],"kernel,":[28],"on":[29],"basis":[31],"which":[33],"sample-efficient":[35],"proposed":[40,47,100],"learn":[42],"function.":[45],"The":[46,65,110,121],"only":[49],"utilizes":[50],"expert":[51],"demonstration":[52],"trajectories":[53],"and":[54,61,119],"does":[55],"not":[56],"require":[57],"system":[58,83],"dynamics":[59],"information":[60],"stabilizing":[62],"control":[63],"gains.":[64],"convergence":[66],"proven.":[71],"Moreover,":[72],"it":[73],"also":[75],"demonstrated":[76],"that":[77],"stability":[79],"closed-loop":[82],"under":[84],"each":[85],"iterative":[86],"gain":[87],"guaranteed.":[89],"Compared":[90],"with":[91],"existing":[92],"reinforcement":[95],"learning":[96],"(RL)":[97],"methods,":[98],"has":[102],"significant":[103],"advantages":[104],"in":[105,113],"terms":[106],"sample":[108,114],"efficiency.":[109],"substantial":[111],"reduction":[112],"complexity":[115],"significantly":[116],"improves":[117],"efficiency":[118],"scalability.":[120],"effectiveness":[122],"verified":[127],"through":[128],"simulations.":[129]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-01-14T00:00:00"}