{"id":"https://openalex.org/W4221153122","doi":"https://doi.org/10.1109/icra46639.2022.9811891","title":"Learning from Imperfect Demonstrations via Adversarial Confidence Transfer","display_name":"Learning from Imperfect Demonstrations via Adversarial Confidence Transfer","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4221153122","doi":"https://doi.org/10.1109/icra46639.2022.9811891"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9811891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811891","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5010800424","display_name":"Zhangjie Cao","orcid":"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":true,"raw_author_name":"Zhangjie Cao","raw_affiliation_strings":["Computer Science, Stanford University,CA,USA","Computer Science, Stanford University, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science, Stanford University,CA,USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Computer Science, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380107","display_name":"Zihan Wang","orcid":"https://orcid.org/0000-0003-0493-2668"},"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":"Zihan Wang","raw_affiliation_strings":["Computer Science, Stanford University,CA,USA","Computer Science, Stanford University, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science, Stanford University,CA,USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Computer Science, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080725225","display_name":"Dorsa Sadigh","orcid":"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":"Dorsa Sadigh","raw_affiliation_strings":["Computer Science, Stanford University,CA,USA","Computer Science, Stanford University, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science, Stanford University,CA,USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Computer Science, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010800424"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.5203,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61013845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"441","last_page":"447"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9997000098228455,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9997000098228455,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9991999864578247,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.771964430809021},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6427279710769653},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.6421568393707275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6289401650428772},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.613231360912323},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.600340723991394},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.545123279094696},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.535655677318573},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4903864860534668},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14194020628929138},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10609516501426697},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0986860990524292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.771964430809021},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6427279710769653},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.6421568393707275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6289401650428772},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.613231360912323},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.600340723991394},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.545123279094696},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.535655677318573},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4903864860534668},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14194020628929138},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10609516501426697},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0986860990524292},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9811891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811891","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G328467149","display_name":null,"funder_award_id":"1849952,1941722","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/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1510672157","https://openalex.org/W1771410628","https://openalex.org/W1848094219","https://openalex.org/W1931877416","https://openalex.org/W1999874108","https://openalex.org/W2098774185","https://openalex.org/W2133040789","https://openalex.org/W2142641780","https://openalex.org/W2171425630","https://openalex.org/W2174803659","https://openalex.org/W2605102758","https://openalex.org/W2767050701","https://openalex.org/W2949600457","https://openalex.org/W2949916679","https://openalex.org/W2962937519","https://openalex.org/W2962957005","https://openalex.org/W2963277051","https://openalex.org/W2964120017","https://openalex.org/W2965175271","https://openalex.org/W2968217299","https://openalex.org/W2978037192","https://openalex.org/W2987651531","https://openalex.org/W2995709298","https://openalex.org/W3030981716","https://openalex.org/W3090359064","https://openalex.org/W3093784762","https://openalex.org/W3101442004","https://openalex.org/W3121989526","https://openalex.org/W3144127138","https://openalex.org/W3209866168","https://openalex.org/W3210459894","https://openalex.org/W4286961552","https://openalex.org/W4288083537","https://openalex.org/W4288284400","https://openalex.org/W6638018090","https://openalex.org/W6638853687","https://openalex.org/W6640174482","https://openalex.org/W6674884181","https://openalex.org/W6679818365","https://openalex.org/W6680724558","https://openalex.org/W6685664872","https://openalex.org/W6718092244","https://openalex.org/W6731094094","https://openalex.org/W6736179038","https://openalex.org/W6736469832","https://openalex.org/W6759312711","https://openalex.org/W6761908843","https://openalex.org/W6763952582","https://openalex.org/W6766451708","https://openalex.org/W6769174716","https://openalex.org/W6771673025","https://openalex.org/W6785034342","https://openalex.org/W6786816963","https://openalex.org/W6801328502","https://openalex.org/W6802868314","https://openalex.org/W6803562061"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4288019534","https://openalex.org/W4310988119"],"abstract_inverted_index":{"Existing":[0],"learning":[1,39,44,120],"from":[2,40,58,122],"demonstration":[3],"algorithms":[4],"usually":[5],"assume":[6],"access":[7],"to":[8,65,75,101,118],"expert":[9],"demonstrations.":[10],"However,":[11],"this":[12],"assumption":[13],"is":[14],"limiting":[15],"in":[16,79,132],"many":[17],"real-world":[18],"applications":[19],"since":[20],"the":[21,36,71,103,116,127,150,156],"collected":[22],"demonstrations":[23,42,52,117,124],"may":[24],"be":[25],"suboptimal":[26],"or":[27],"even":[28],"consist":[29],"of":[30,38,97,105,158],"failure":[31],"cases.":[32],"We":[33,87,154],"therefore":[34],"study":[35],"problem":[37],"imperfect":[41],"by":[43],"a":[45,59,67,77,89,137,147],"confidence":[46,56,68,106,114],"predictor.":[47],"Specifically,":[48],"we":[49,73,82],"rely":[50],"on":[51,161],"along":[53],"with":[54,149],"their":[55],"values":[57],"different":[60],"correspondent":[61],"environment":[62,72],"(source":[63],"environment)":[64],"learn":[66,76,88],"predictor":[69],"for":[70],"aim":[74],"policy":[78,148],"(target":[80],"environment-where":[81],"only":[83],"have":[84],"unlabeled":[85],"demonstrations).":[86],"common":[90],"latent":[91],"space":[92],"through":[93],"adversarial":[94],"distribution":[95],"matching":[96],"multi-length":[98],"partial":[99],"trajectories":[100],"enable":[102,119],"transfer":[104],"across":[107],"source":[108],"and":[109,125,136],"target":[110],"environments.":[111],"The":[112],"learned":[113],"reweights":[115],"more":[121],"informative":[123],"discarding":[126],"irrelevant":[128],"ones.":[129],"Our":[130],"experiments":[131,160],"three":[133],"simulated":[134],"environments":[135],"real":[138],"robot":[139],"reaching":[140],"task":[141],"demonstrate":[142],"that":[143],"our":[144,159,162],"approach":[145],"learns":[146],"highest":[151],"expected":[152],"return.":[153],"show":[155],"videos":[157],"website.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}