{"id":"https://openalex.org/W3213050345","doi":"https://doi.org/10.48550/arxiv.2110.14754","title":"Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality","display_name":"Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality","publication_year":2021,"publication_date":"2021-10-27","ids":{"openalex":"https://openalex.org/W3213050345","doi":"https://doi.org/10.48550/arxiv.2110.14754","mag":"3213050345"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2110.14754","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.14754","pdf_url":"https://arxiv.org/pdf/2110.14754","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.14754","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103236448","display_name":"Songyuan Zhang","orcid":"https://orcid.org/0009-0005-6465-4833","observed_orcids":["https://orcid.org/0009-0005-6465-4833"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhang, Songyuan","raw_affiliation_strings":["National Engineering Lab for Neuromodulation , SAE , Tsinghua University , China","Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Lab for Neuromodulation , SAE , Tsinghua University , China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010800424","display_name":"Zhangjie Cao","orcid":"https://orcid.org/0000-0001-5098-2194","observed_orcids":["https://orcid.org/0000-0001-5098-2194"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cao, Zhangjie","raw_affiliation_strings":["Department of Computer Science , Stanford University , USA","Stanford University, Stanford, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Stanford University , USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080725225","display_name":"Dorsa Sadigh","orcid":"https://orcid.org/0000-0002-7802-9183","observed_orcids":["https://orcid.org/0000-0002-7802-9183"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sadigh, Dorsa","raw_affiliation_strings":["Department of Computer Science , Stanford University , USA","Stanford University, Stanford, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Stanford University , USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069290448","display_name":"Yanan Sui","orcid":"https://orcid.org/0000-0002-9480-627X","observed_orcids":["https://orcid.org/0000-0002-9480-627X"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sui, Yanan","raw_affiliation_strings":["National Engineering Lab for Neuromodulation , SAE , Tsinghua University , China","Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Lab for Neuromodulation , SAE , Tsinghua University , China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0010999999940395355,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":9.999999747378752e-05,"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/imitation-learning","display_name":"imitation learning","score":0.9169999957084656},{"id":"https://openalex.org/keywords/confidence-estimation","display_name":"confidence estimation","score":0.6340000033378601},{"id":"https://openalex.org/keywords/convergence-guarantees","display_name":"convergence guarantees","score":0.6439999938011169},{"id":"https://openalex.org/keywords/robot-learning-from-demonstration","display_name":"robot learning from demonstration","score":0.5759999752044678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778667211532593},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7020981907844543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6077302098274231},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.598850667476654},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5163322687149048},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5045226812362671},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4848147928714752},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2110.14754","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.14754","pdf_url":"https://arxiv.org/pdf/2110.14754","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2110.14754","doi":"https://doi.org/10.48550/arxiv.2110.14754","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2110.14754","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3213050345","doi":null,"is_oa":false,"landing_page_url":"http://arxiv-export-lb.library.cornell.edu/abs/2110.14754","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.14754","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.14754","pdf_url":"https://arxiv.org/pdf/2110.14754","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1902905260","display_name":"CRII: RI: Active Learning of Preferences for Human-Aware Autonomy","funder_award_id":"1849952","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6022427645","display_name":"CAREER: Safe and Influencing Interactions for Human-Robot Systems","funder_award_id":"1941722","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3213050345.pdf","grobid_xml":"https://content.openalex.org/works/W3213050345.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W122021961","https://openalex.org/W1591675293","https://openalex.org/W1931877416","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2051228319","https://openalex.org/W2098774185","https://openalex.org/W2099471712","https://openalex.org/W2158782408","https://openalex.org/W2166302491","https://openalex.org/W2174803659","https://openalex.org/W2395738761","https://openalex.org/W2434014514","https://openalex.org/W2481910659","https://openalex.org/W2566467060","https://openalex.org/W2567252694","https://openalex.org/W2573393487","https://openalex.org/W2736601468","https://openalex.org/W2766610320","https://openalex.org/W2914824760","https://openalex.org/W2939047085","https://openalex.org/W2962845991","https://openalex.org/W2970971581","https://openalex.org/W2992693735","https://openalex.org/W3031027020","https://openalex.org/W3035366536","https://openalex.org/W3037533353","https://openalex.org/W3091550845","https://openalex.org/W3093674515","https://openalex.org/W3093784762","https://openalex.org/W3098253476","https://openalex.org/W3144127138"],"related_works":["https://openalex.org/W2914824760","https://openalex.org/W4385301499","https://openalex.org/W3144127138","https://openalex.org/W4399939232","https://openalex.org/W4221153122","https://openalex.org/W4223636929","https://openalex.org/W6926779860","https://openalex.org/W4416016187","https://openalex.org/W4308609982","https://openalex.org/W3129580072"],"abstract_inverted_index":{"Most":[0],"existing":[1],"imitation":[2,29,157],"learning":[3,30,158],"approaches":[4],"assume":[5],"the":[6,92,119,127,134],"demonstrations":[7,37,53,85,161],"are":[8,13],"drawn":[9],"from":[10,36,52,60,84,109,160],"experts":[11],"who":[12],"optimal,":[14],"but":[15,57],"relaxing":[16],"this":[17,75],"assumption":[18],"enables":[19],"us":[20],"to":[21,48,82,117,125,172],"use":[22,43],"a":[23,33,79,96,106,180],"wider":[24],"range":[25],"of":[26,72,121,136],"data.":[27],"Standard":[28],"may":[31],"learn":[32,83,126,179],"suboptimal":[34],"policy":[35,108],"with":[38,54,86,162],"varying":[39,55,87,163],"optimality.":[40,164],"Prior":[41],"works":[42],"confidence":[44,66,93],"scores":[45,67],"or":[46,68],"rankings":[47],"capture":[49],"beneficial":[50],"information":[51],"optimality,":[56],"they":[58],"suffer":[59],"many":[61],"limitations,":[62],"e.g.,":[63],"manually":[64],"annotated":[65],"high":[69],"average":[70],"optimality":[71,88],"demonstrations.":[73],"In":[74],"paper,":[76],"we":[77],"propose":[78],"general":[80],"framework":[81],"that":[89,152,168],"jointly":[90],"learns":[91,105],"score":[94],"and":[95,124,138,145,183],"well-performing":[97,107],"policy.":[98],"Our":[99,149],"approach,":[100],"Confidence-Aware":[101],"Imitation":[102],"Learning":[103],"(CAIL)":[104],"confidence-reweighted":[110],"demonstrations,":[111,175],"while":[112],"using":[113],"an":[114],"outer":[115],"loss":[116],"track":[118],"performance":[120,141],"our":[122],"model":[123],"confidence.":[128],"We":[129,165],"provide":[130],"theoretical":[131],"guarantees":[132],"on":[133],"convergence":[135],"CAIL":[137,153,176],"evaluate":[139],"its":[140],"in":[142],"both":[143],"simulated":[144],"real":[146],"robot":[147],"experiments.":[148],"results":[150],"show":[151,167],"significantly":[154],"outperforms":[155,184],"other":[156],"methods":[159],"further":[166],"even":[169],"without":[170],"access":[171],"any":[173],"optimal":[174],"can":[177],"still":[178],"successful":[181],"policy,":[182],"prior":[185],"work.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-11-22T00:00:00"}