{"id":"https://openalex.org/W3093674515","doi":"https://doi.org/10.48550/arxiv.2010.10181","title":"Robust Imitation Learning from Noisy Demonstrations","display_name":"Robust Imitation Learning from Noisy Demonstrations","publication_year":2020,"publication_date":"2020-10-20","ids":{"openalex":"https://openalex.org/W3093674515","doi":"https://doi.org/10.48550/arxiv.2010.10181","mag":"3093674515"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2010.10181","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.10181","pdf_url":"https://arxiv.org/pdf/2010.10181","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/2010.10181","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055819776","display_name":"Voot Tangkaratt","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tangkaratt, Voot","raw_affiliation_strings":["RIKEN","The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN","institution_ids":["https://openalex.org/I4210110652"]},{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083583938","display_name":"Nontawat Charoenphakdee","orcid":"https://orcid.org/0000-0002-0214-4943","observed_orcids":["https://orcid.org/0000-0002-0214-4943"]},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Charoenphakdee, Nontawat","raw_affiliation_strings":["RIKEN","University of Tokyo & RIKEN","Univ.\\ of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN","institution_ids":["https://openalex.org/I4210110652"]},{"raw_affiliation_string":"University of Tokyo & RIKEN","institution_ids":["https://openalex.org/I4210110652","https://openalex.org/I74801974"]},{"raw_affiliation_string":"Univ.\\ of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072744508","display_name":"Masashi Sugiyama","orcid":"https://orcid.org/0000-0001-6658-6743","observed_orcids":["https://orcid.org/0000-0001-6658-6743"]},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sugiyama, Masashi","raw_affiliation_strings":["RIKEN","RIKEN & University of Tokyo","Univ.\\ of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN","institution_ids":["https://openalex.org/I4210110652"]},{"raw_affiliation_string":"RIKEN & University of Tokyo","institution_ids":["https://openalex.org/I4210110652","https://openalex.org/I74801974"]},{"raw_affiliation_string":"Univ.\\ of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"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":0.9994999766349792,"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":0.9994999766349792,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.00019999999494757503,"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":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/pseudo-labeling","display_name":"pseudo-labeling","score":0.996999979019165},{"id":"https://openalex.org/keywords/co-training","display_name":"co-training","score":0.9940000176429749},{"id":"https://openalex.org/keywords/continuous-control","display_name":"continuous control","score":0.5690000057220459}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.8363633155822754},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7146648168563843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5870086550712585},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.579873263835907},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49244794249534607},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4411763846874237},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07658487558364868},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2010.10181","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.10181","pdf_url":"https://arxiv.org/pdf/2010.10181","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":"mag:3093674515","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2010.10181.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2010.10181","doi":"https://doi.org/10.48550/arxiv.2010.10181","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.10181","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.10181","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.10181","pdf_url":"https://arxiv.org/pdf/2010.10181","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/G3538458246","display_name":"Theory and Application of Statistical Reinforcement Learning","funder_award_id":"17H00757","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3093674515.pdf","grobid_xml":"https://content.openalex.org/works/W3093674515.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W369786348","https://openalex.org/W1479807131","https://openalex.org/W1480376833","https://openalex.org/W2048679005","https://openalex.org/W2061562262","https://openalex.org/W2101807845","https://openalex.org/W2102847492","https://openalex.org/W2107189314","https://openalex.org/W2108501770","https://openalex.org/W2113290770","https://openalex.org/W2119567691","https://openalex.org/W2120497086","https://openalex.org/W2171054284","https://openalex.org/W2434014514","https://openalex.org/W2749928749","https://openalex.org/W2766447205","https://openalex.org/W2792263949","https://openalex.org/W2888934269","https://openalex.org/W2898634286","https://openalex.org/W2913520548","https://openalex.org/W2914824760","https://openalex.org/W2939047085","https://openalex.org/W2946160813","https://openalex.org/W2949416428","https://openalex.org/W2949916679","https://openalex.org/W2962879692","https://openalex.org/W2963313316","https://openalex.org/W2963328631","https://openalex.org/W2963735582","https://openalex.org/W2964121744","https://openalex.org/W2988072049","https://openalex.org/W3008082783","https://openalex.org/W3035366536","https://openalex.org/W3035429562","https://openalex.org/W6903373895","https://openalex.org/W6960125083"],"related_works":["https://openalex.org/W4206839009","https://openalex.org/W4221161101","https://openalex.org/W4395047259","https://openalex.org/W4394007438","https://openalex.org/W7052617256","https://openalex.org/W6926779860","https://openalex.org/W7124284875","https://openalex.org/W4387946911","https://openalex.org/W4414270615","https://openalex.org/W7162409669"],"abstract_inverted_index":{"Robust":[0],"learning":[1,25,49],"from":[2],"noisy":[3],"demonstrations":[4],"is":[5,87],"a":[6,31,35,46],"practical":[7],"but":[8],"highly":[9],"challenging":[10],"problem":[11],"in":[12],"imitation":[13,24,48],"learning.":[14],"In":[15],"this":[16,40],"paper,":[17],"we":[18,43],"first":[19],"theoretically":[20],"show":[21,83],"that":[22,51,84],"robust":[23,89],"can":[26],"be":[27],"achieved":[28],"by":[29,56],"optimizing":[30],"classification":[32,54],"risk":[33,55],"with":[34,60],"symmetric":[36],"loss.":[37],"Based":[38],"on":[39,80],"theoretical":[41],"finding,":[42],"then":[44],"propose":[45],"new":[47],"method":[50,66,86],"optimizes":[52],"the":[53],"effectively":[57],"combining":[58],"pseudo-labeling":[59],"co-training.":[61],"Unlike":[62],"existing":[63],"methods,":[64],"our":[65,85],"does":[67],"not":[68],"require":[69],"additional":[70],"labels":[71],"or":[72],"strict":[73],"assumptions":[74],"about":[75],"noise":[76],"distributions.":[77],"Experimental":[78],"results":[79],"continuous-control":[81],"benchmarks":[82],"more":[88],"compared":[90],"to":[91],"state-of-the-art":[92],"methods.":[93]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2020-10-29T00:00:00"}