{"id":"https://openalex.org/W4376456629","doi":"https://doi.org/10.1109/tac.2023.3274629","title":"Trust-Region Inverse Reinforcement Learning","display_name":"Trust-Region Inverse Reinforcement Learning","publication_year":2023,"publication_date":"2023-05-11","ids":{"openalex":"https://openalex.org/W4376456629","doi":"https://doi.org/10.1109/tac.2023.3274629"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2023.3274629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2023.3274629","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"},"type":"article","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/A5101436339","display_name":"Kun Cao","orcid":"https://orcid.org/0000-0003-4688-1096"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Kun Cao","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365448","display_name":"Lihua Xie","orcid":"https://orcid.org/0000-0002-7137-4136"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lihua Xie","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101436339"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":1.4274,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83964432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"69","issue":"2","first_page":"1037","last_page":"1044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9896000027656555,"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":0.9896000027656555,"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":0.9577999711036682,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9161999821662903,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.6138966083526611},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5072950720787048},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.4946264922618866},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4833247661590576},{"id":"https://openalex.org/keywords/hessian-matrix","display_name":"Hessian matrix","score":0.4801423251628876},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.47919973731040955},{"id":"https://openalex.org/keywords/pontryagins-minimum-principle","display_name":"Pontryagin's minimum principle","score":0.4441378712654114},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4364125728607178},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.43596696853637695},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4083279073238373},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.393172025680542},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3777448534965515},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.37697404623031616},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.34137386083602905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.284383624792099},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.264461487531662},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.1055772602558136}],"concepts":[{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.6138966083526611},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5072950720787048},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.4946264922618866},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4833247661590576},{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.4801423251628876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47919973731040955},{"id":"https://openalex.org/C141803461","wikidata":"https://www.wikidata.org/wiki/Q3491629","display_name":"Pontryagin's minimum principle","level":3,"score":0.4441378712654114},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4364125728607178},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.43596696853637695},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4083279073238373},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.393172025680542},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3777448534965515},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.37697404623031616},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.34137386083602905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.284383624792099},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.264461487531662},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.1055772602558136},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tac.2023.3274629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2023.3274629","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/170705","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/170705","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1977655452","https://openalex.org/W1999874108","https://openalex.org/W2027161089","https://openalex.org/W2051944318","https://openalex.org/W2107308405","https://openalex.org/W2142847239","https://openalex.org/W2169498096","https://openalex.org/W2257979135","https://openalex.org/W2462906003","https://openalex.org/W2592261783","https://openalex.org/W2737702598","https://openalex.org/W2765164677","https://openalex.org/W2765713587","https://openalex.org/W2772589676","https://openalex.org/W2842089854","https://openalex.org/W3031798691","https://openalex.org/W3081754649","https://openalex.org/W3088197938","https://openalex.org/W4213206621","https://openalex.org/W4255086963","https://openalex.org/W4300448178","https://openalex.org/W6638018090","https://openalex.org/W6674884181","https://openalex.org/W6714580625","https://openalex.org/W6718836005","https://openalex.org/W6743802245","https://openalex.org/W6753207554","https://openalex.org/W6772521232"],"related_works":["https://openalex.org/W2962746246","https://openalex.org/W1967384683","https://openalex.org/W1520410026","https://openalex.org/W4285534277","https://openalex.org/W3031081244","https://openalex.org/W4292923857","https://openalex.org/W3209004265","https://openalex.org/W1643670820","https://openalex.org/W15954510","https://openalex.org/W2022910674"],"abstract_inverted_index":{"This":[0],"article":[1],"proposes":[2],"a":[3,15],"new":[4],"unified":[5],"inverse":[6],"reinforcement":[7],"learning":[8,77],"framework":[9,80],"based":[10],"on":[11],"trust-region":[12,88],"methods":[13],"and":[14,39,61,94,106,126,137],"recently":[16],"proposed":[17,147],"Pontryagin":[18],"differential":[19],"programming":[20],"method":[21],"in":[22,34],"Jin":[23],"et":[24],"al.\u2019s":[25],"work":[26],"(2020),":[27],"which":[28],"aims":[29],"to":[30,75,114,117,141],"learn":[31],"the":[32,36,40,70,84,118,143],"parameters":[33],"both":[35],"system":[37],"model":[38],"cost":[41],"function":[42],"for":[43,121],"three":[44],"types":[45],"of":[46,87,145],"problems,":[47],"namely,":[48],"<inline-formula":[49],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[50],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[51],"notation=\"LaTeX\">$N$</tex-math></inline-formula>":[52],"-player":[53],"nonzero-sum":[54],"multistage":[55,59],"games,":[56,60],"two-player":[57],"zero-sum":[58],"one-player":[62],"optimal":[63],"control,":[64],"from":[65,69],"demonstrated":[66],"trajectories.":[67],"Different":[68],"existing":[71],"frameworks":[72],"using":[73],"gradient":[74,93],"update":[76],"parameters,":[78],"our":[79,146],"updates":[81],"them":[82],"with":[83],"candidate":[85],"solution":[86],"subproblem,":[89],"where":[90],"its":[91],"required":[92],"Hessian":[95],"are":[96,112,139],"obtained":[97],"by":[98,130],"differentiating":[99],"Pontryagin's":[100],"maximum":[101],"principle":[102],"(PMP)":[103],"equations":[104,111,120],"once":[105],"twice,":[107],"respectively.":[108],"The":[109],"differentiated":[110],"shown":[113],"be":[115,128],"equivalent":[116],"PMP":[119],"affine-quadratic":[122],"games/optimal":[123],"control":[124],"problems":[125],"can":[127],"solved":[129],"some":[131],"explicit":[132],"recursions.":[133],"Extensive":[134],"simulation":[135],"examples":[136],"comparisons":[138],"presented":[140],"demonstrate":[142],"effectiveness":[144],"algorithm.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}