{"id":"https://openalex.org/W4381415941","doi":"https://doi.org/10.1109/tpami.2023.3287908","title":"Prescribed Safety Performance Imitation Learning From a Single Expert Dataset","display_name":"Prescribed Safety Performance Imitation Learning From a Single Expert Dataset","publication_year":2023,"publication_date":"2023-06-20","ids":{"openalex":"https://openalex.org/W4381415941","doi":"https://doi.org/10.1109/tpami.2023.3287908","pmid":"https://pubmed.ncbi.nlm.nih.gov/37339035"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3287908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3287908","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5101965819","display_name":"Zhihao Cheng","orcid":"https://orcid.org/0000-0002-8360-5149"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhihao Cheng","raw_affiliation_strings":["Sydney AI Centre and the School of Computer Science, in the Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8360-5149","affiliations":[{"raw_affiliation_string":"Sydney AI Centre and the School of Computer Science, in the Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042802004","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-5659-3464"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["JD Explore Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5659-3464","affiliations":[{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110995376","display_name":"Miaoxi Zhu","orcid":"https://orcid.org/0009-0000-9534-1999"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miaoxi Zhu","raw_affiliation_strings":["School of Computer Science, the National Engineering Research Center for Multimedia Software, the Institute of Artificial Intelligence, and the Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0000-9534-1999","affiliations":[{"raw_affiliation_string":"School of Computer Science, the National Engineering Research Center for Multimedia Software, the Institute of Artificial Intelligence, and the Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084631859","display_name":"Jiaxian Guo","orcid":"https://orcid.org/0000-0002-0212-8329"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiaxian Guo","raw_affiliation_strings":["Sydney AI Centre and the School of Computer Science, in the Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0212-8329","affiliations":[{"raw_affiliation_string":"Sydney AI Centre and the School of Computer Science, in the Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400486","display_name":"Meng Fang","orcid":"https://orcid.org/0000-0001-6745-286X"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Meng Fang","raw_affiliation_strings":["University of Liverpool, Liverpool, U.K","University of Liverpool, the United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-6745-286X","affiliations":[{"raw_affiliation_string":"University of Liverpool, Liverpool, U.K","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"University of Liverpool, the United Kingdom","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324286","display_name":"Liu Liu","orcid":"https://orcid.org/0000-0002-8128-2788"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Liu Liu","raw_affiliation_strings":["Sydney AI Centre and the School of Computer Science, in the Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8128-2788","affiliations":[{"raw_affiliation_string":"Sydney AI Centre and the School of Computer Science, in the Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060042752","display_name":"Bo Du","orcid":"https://orcid.org/0000-0002-0059-8458"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Du","raw_affiliation_strings":["School of Computer Science, the National Engineering Research Center for Multimedia Software, the Institute of Artificial Intelligence, and the Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-0059-8458","affiliations":[{"raw_affiliation_string":"School of Computer Science, the National Engineering Research Center for Multimedia Software, the Institute of Artificial Intelligence, and the Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["Sydney AI Centre and the School of Computer Science, in the Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"Sydney AI Centre and the School of Computer Science, in the Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4759,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67804269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"45","issue":"10","first_page":"12236","last_page":"12249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9955999851226807,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9955999851226807,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9890999794006348,"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":0.9639000296592712,"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/lagrange-multiplier","display_name":"Lagrange multiplier","score":0.7328243851661682},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.627334713935852},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6181847453117371},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5165058970451355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49765971302986145},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49288392066955566},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44692039489746094},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.380209356546402},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16276511549949646}],"concepts":[{"id":"https://openalex.org/C73684929","wikidata":"https://www.wikidata.org/wiki/Q598870","display_name":"Lagrange multiplier","level":2,"score":0.7328243851661682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.627334713935852},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6181847453117371},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5165058970451355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49765971302986145},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49288392066955566},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44692039489746094},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.380209356546402},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16276511549949646},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3287908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3287908","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37339035","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37339035","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1845972764","https://openalex.org/W1965555277","https://openalex.org/W1969085927","https://openalex.org/W2005912592","https://openalex.org/W2033468335","https://openalex.org/W2086475365","https://openalex.org/W2146950091","https://openalex.org/W2174803659","https://openalex.org/W2396217537","https://openalex.org/W2462906003","https://openalex.org/W2558232109","https://openalex.org/W2604382266","https://openalex.org/W2767506186","https://openalex.org/W2781565978","https://openalex.org/W2884247313","https://openalex.org/W2886572631","https://openalex.org/W2895649888","https://openalex.org/W2913300629","https://openalex.org/W2963616027","https://openalex.org/W2964120017","https://openalex.org/W2967195040","https://openalex.org/W2978084855","https://openalex.org/W2979863294","https://openalex.org/W2991391803","https://openalex.org/W2998050631","https://openalex.org/W3002628166","https://openalex.org/W3003342008","https://openalex.org/W3004800063","https://openalex.org/W3034819467","https://openalex.org/W3035427621","https://openalex.org/W3088310808","https://openalex.org/W3092938557","https://openalex.org/W3120778962","https://openalex.org/W3120855041","https://openalex.org/W3136504339","https://openalex.org/W3138984732","https://openalex.org/W3171210634","https://openalex.org/W3176452384","https://openalex.org/W3178520484","https://openalex.org/W3189576409","https://openalex.org/W4206497039","https://openalex.org/W4221144242","https://openalex.org/W4226316432","https://openalex.org/W4250589301","https://openalex.org/W4283793632","https://openalex.org/W4287064065","https://openalex.org/W4287725923","https://openalex.org/W4292347911","https://openalex.org/W4293545785","https://openalex.org/W4294811378","https://openalex.org/W4300479382","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6640174482","https://openalex.org/W6650265722","https://openalex.org/W6682142825","https://openalex.org/W6683204974","https://openalex.org/W6712453370","https://openalex.org/W6718092244","https://openalex.org/W6718836005","https://openalex.org/W6730402787","https://openalex.org/W6737893269","https://openalex.org/W6751535212","https://openalex.org/W6753770476","https://openalex.org/W6758924645","https://openalex.org/W6759312711","https://openalex.org/W6771280675","https://openalex.org/W6779370943","https://openalex.org/W6779458208","https://openalex.org/W6780089238","https://openalex.org/W6780167026","https://openalex.org/W6780486084","https://openalex.org/W6780587392","https://openalex.org/W6782102727","https://openalex.org/W6784709865","https://openalex.org/W6785187516","https://openalex.org/W6786148139","https://openalex.org/W6788926732","https://openalex.org/W6799402547","https://openalex.org/W6803800456","https://openalex.org/W6809864479","https://openalex.org/W6811221485","https://openalex.org/W6843754643","https://openalex.org/W6846052559","https://openalex.org/W6846122673"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2387995142","https://openalex.org/W4380714744","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2057775761","https://openalex.org/W1608433645","https://openalex.org/W2964074194"],"abstract_inverted_index":{"Existing":[0],"safe":[1,11,45,165],"imitation":[2,96],"learning":[3,10,132,163],"(safe":[4],"IL)":[5],"methods":[6],"mainly":[7],"focus":[8],"on":[9,151],"policies":[12,46],"that":[13],"are":[14],"similar":[15],"to":[16,93,109,117,135],"expert":[17,50,127],"ones,":[18],"but":[19],"may":[20],"fail":[21],"in":[22,175],"applications":[23],"requiring":[24],"different":[25],"safety":[26,55,64,88,98,141,155,169],"constraints.":[27,56,170],"In":[28],"this":[29],"paper,":[30],"we":[31,60,103],"propose":[32],"the":[33,87,95,119,122,126,137,152,180],"Lagrangian":[34],"Generative":[35],"Adversarial":[36],"Imitation":[37],"Learning":[38],"(LGAIL)":[39],"algorithm,":[40],"which":[41],"can":[42],"adaptively":[43,162],"learn":[44],"from":[47],"a":[48,77,105,113,145,164],"single":[49],"dataset":[51],"under":[52],"diverse":[53],"prescribed":[54,168],"To":[57],"achieve":[58],"this,":[59],"augment":[61],"GAIL":[62],"with":[63],"constraints":[65],"and":[66,89,97,125,154],"then":[67],"relax":[68],"it":[69],"as":[70],"an":[71],"unconstrained":[72],"optimization":[73,107],"problem":[74],"by":[75,144],"utilizing":[76],"Lagrange":[78,81,146],"multiplier.":[79,147],"The":[80],"multiplier":[82],"enables":[83],"explicit":[84],"consideration":[85],"of":[86,156,161,182],"is":[90,115,133],"dynamically":[91],"adjusted":[92],"balance":[94],"performance":[99],"during":[100],"training.":[101],"Then,":[102],"apply":[104],"two-stage":[106],"framework":[108],"solve":[110],"LGAIL:":[111],"(1)":[112],"discriminator":[114],"optimized":[116],"measure":[118],"similarity":[120,138],"between":[121],"agent-generated":[123],"data":[124],"ones;":[128],"(2)":[129],"forward":[130],"reinforcement":[131],"employed":[134],"improve":[136],"while":[139],"considering":[140],"concerns":[142],"enabled":[143],"Furthermore,":[148],"theoretical":[149],"analyses":[150],"convergence":[153],"LGAIL":[157],"demonstrate":[158],"its":[159],"capability":[160],"policy":[166],"given":[167],"At":[171],"last,":[172],"extensive":[173],"experiments":[174],"OpenAI":[176],"Safety":[177],"Gym":[178],"conclude":[179],"effectiveness":[181],"our":[183],"approach.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}