{"id":"https://openalex.org/W4416366469","doi":"https://doi.org/10.1109/tcyb.2025.3631917","title":"Human Behavior Identification for Linear Systems in Adversarial Environments by Adaptive Inverse Reinforcement Learning","display_name":"Human Behavior Identification for Linear Systems in Adversarial Environments by Adaptive Inverse Reinforcement Learning","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W4416366469","doi":"https://doi.org/10.1109/tcyb.2025.3631917","pmid":"https://pubmed.ncbi.nlm.nih.gov/41259178"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2025.3631917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2025.3631917","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/A5100742709","display_name":"Mi Wang","orcid":"https://orcid.org/0000-0003-2331-702X"},"institutions":[{"id":"https://openalex.org/I198645480","display_name":"North China University of Water Resources and Electric Power","ror":"https://ror.org/03acrzv41","country_code":"CN","type":"education","lineage":["https://openalex.org/I198645480"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mi Wang","raw_affiliation_strings":["School of Electrical Engineering, North China University of Water Resources and Electric Power, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, North China University of Water Resources and Electric Power, Zhengzhou, China","institution_ids":["https://openalex.org/I198645480"]}]},{"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":["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/A5111359697","display_name":"Jingbo Fu","orcid":"https://orcid.org/0009-0004-0963-3258"},"institutions":[{"id":"https://openalex.org/I68581759","display_name":"China Academy of Launch Vehicle Technology","ror":"https://ror.org/012z62f48","country_code":"CN","type":"facility","lineage":["https://openalex.org/I68581759"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbo Fu","raw_affiliation_strings":["China Academy of Aerospace Science and Industry Launch Vehicle Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"China Academy of Aerospace Science and Industry Launch Vehicle Technology, Beijing, China","institution_ids":["https://openalex.org/I68581759"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100334592","display_name":"Liang Chen","orcid":"https://orcid.org/0000-0002-1991-7586"},"institutions":[{"id":"https://openalex.org/I202334528","display_name":"Beijing Electronic Science and Technology Institute","ror":"https://ror.org/01xdzh226","country_code":"CN","type":"education","lineage":["https://openalex.org/I202334528"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Liang","raw_affiliation_strings":["Beijing Institute of Control and Electronics Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Control and Electronics Technology, Beijing, China","institution_ids":["https://openalex.org/I202334528"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100742709"],"corresponding_institution_ids":["https://openalex.org/I198645480"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35702581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"56","issue":"3","first_page":"1649","last_page":"1660"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.33730000257492065,"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":0.33730000257492065,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.16419999301433563,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.09279999881982803,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/adversarial-system","display_name":"Adversarial system","score":0.6847000122070312},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6705999970436096},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5874000191688538},{"id":"https://openalex.org/keywords/system-identification","display_name":"System identification","score":0.5091999769210815},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4629000127315521},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4278999865055084},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4090999960899353},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4088999927043915},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4018999934196472}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6847000122070312},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6705999970436096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.614300012588501},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5874000191688538},{"id":"https://openalex.org/C119247159","wikidata":"https://www.wikidata.org/wiki/Q1366192","display_name":"System identification","level":3,"score":0.5091999769210815},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453900009393692},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4090999960899353},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4018999934196472},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38350000977516174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37299999594688416},{"id":"https://openalex.org/C147513830","wikidata":"https://www.wikidata.org/wiki/Q5938602","display_name":"Human systems engineering","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C79610928","wikidata":"https://www.wikidata.org/wiki/Q1656743","display_name":"Parameter identification problem","level":3,"score":0.3237999975681305},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.2833000123500824},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C9936470","wikidata":"https://www.wikidata.org/wiki/Q6510405","display_name":"Least-squares function approximation","level":3,"score":0.25290000438690186}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001519","descriptor_name":"Behavior","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D001519","descriptor_name":"Behavior","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003491","descriptor_name":"Cybernetics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D003491","descriptor_name":"Cybernetics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2025.3631917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2025.3631917","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:41259178","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41259178","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1970916399","https://openalex.org/W1977880420","https://openalex.org/W1991833878","https://openalex.org/W1997576152","https://openalex.org/W1997932767","https://openalex.org/W1998331973","https://openalex.org/W1999874108","https://openalex.org/W2001808786","https://openalex.org/W2014336612","https://openalex.org/W2027161089","https://openalex.org/W2031571562","https://openalex.org/W2037997802","https://openalex.org/W2056975430","https://openalex.org/W2067910439","https://openalex.org/W2070832112","https://openalex.org/W2077177611","https://openalex.org/W2081559824","https://openalex.org/W2088993090","https://openalex.org/W2107308405","https://openalex.org/W2155418574","https://openalex.org/W2157577161","https://openalex.org/W2166302491","https://openalex.org/W2166916103","https://openalex.org/W2169498096","https://openalex.org/W2174803659","https://openalex.org/W2262743940","https://openalex.org/W2273466378","https://openalex.org/W2474718355","https://openalex.org/W2604382266","https://openalex.org/W2789185723","https://openalex.org/W2907920236","https://openalex.org/W2971761264","https://openalex.org/W2975359243","https://openalex.org/W3015527773","https://openalex.org/W3038972086","https://openalex.org/W3101780148","https://openalex.org/W3120930765","https://openalex.org/W3195322794","https://openalex.org/W4225647710","https://openalex.org/W4310329823","https://openalex.org/W4396877821","https://openalex.org/W4400877505","https://openalex.org/W4402301581","https://openalex.org/W4402624667","https://openalex.org/W4407827592","https://openalex.org/W4408441459","https://openalex.org/W4408566536","https://openalex.org/W4409073839"],"related_works":[],"abstract_inverted_index":{"This":[0],"article":[1,89],"is":[2,47,72,102,143],"concerned":[3],"with":[4],"the":[5,20,33,41,44,62,68,82,106,110,116,120,137,146,151,155,170,177,185,188],"human":[6,21,63,69,111,124,139,191],"behavior":[7,70,140,192],"identification":[8,71,141,193],"problem":[9],"for":[10,153],"linear":[11],"human-in-the-loop":[12],"(HiTL)":[13],"systems":[14],"in":[15,87,123,164],"adversarial":[16,34,65],"environments.":[17],"By":[18],"modeling":[19],"as":[22,36,49,93],"an":[23,37,75,96],"optimal":[24],"controller":[25],"that":[26,55,60,160],"minimizes":[27],"his/her":[28],"individual":[29],"cost":[30,42,125],"function":[31,126],"and":[32,64,112,150,174],"environment":[35],"opponent":[38],"to":[39,74,104,144],"maximize":[40],"function,":[43],"HiTL":[45],"system":[46],"formulated":[48],"a":[50,131,182],"linear-quadratic":[51],"zero-sum":[52],"differential":[53],"game":[54],"consists":[56],"of":[57,109,136,158,172,181,187],"two":[58],"players":[59],"are":[61,127,161],"environment.":[66],"Then,":[67],"transformed":[73],"inverse":[76],"reinforcement":[77],"learning":[78,99,167],"(IRL)":[79],"problem.":[80],"Accordingly,":[81],"main":[83,134],"works":[84],"carried":[85],"out":[86],"this":[88],"can":[90],"be":[91],"summarized":[92],"follows:":[94],"1)":[95],"integral":[97],"concurrent":[98],"(ICL)":[100],"law":[101],"proposed":[103,189],"estimate":[105],"feedback":[107,118],"matrix":[108],"2)":[113],"based":[114],"on":[115,176],"estimated":[117],"matrix,":[119],"weighting":[121],"matrices":[122],"retrieved":[128],"by":[129],"minimizing":[130],"residual.":[132],"The":[133],"focus":[135],"developed":[138],"method":[142],"remove":[145],"persisting":[147],"excitation":[148],"constraint":[149],"demand":[152],"measuring":[154],"control":[156],"input":[157],"humans":[159],"universally":[162],"required":[163],"existing":[165],"online":[166],"approaches.":[168],"Finally,":[169],"results":[171],"simulation":[173],"experiment":[175],"lane":[178],"keeping":[179],"scenario":[180],"vehicle":[183],"verify":[184],"validity":[186],"adaptive-IRL-based":[190],"strategy.":[194]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-19T00:00:00"}
