{"id":"https://openalex.org/W2995508322","doi":null,"title":"Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards","display_name":"Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards","publication_year":2020,"publication_date":"2020-04-30","ids":{"openalex":"https://openalex.org/W2995508322","mag":"2995508322"},"language":"en","primary_location":{"id":"mag:2995508322","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.03352.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":null,"is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.03352.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063400595","display_name":"Allan Zhou","orcid":"https://orcid.org/0000-0001-9448-8075","observed_orcids":["https://orcid.org/0000-0001-9448-8075"]},"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":"Allan Zhou","raw_affiliation_strings":["Stanford University, Stanford, United States"],"raw_orcid":"https://orcid.org/0000-0001-9448-8075","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083516691","display_name":"Eric Jang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Jang","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039293409","display_name":"Daniel Kappler","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Kappler","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007112220","display_name":"Alex Herzog","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Herzog","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065802887","display_name":"Mohi Khansari","orcid":"https://orcid.org/0009-0007-5870-726X","observed_orcids":["https://orcid.org/0009-0007-5870-726X"]},"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":"Mohi Khansari","raw_affiliation_strings":["Stanford University, Stanford, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089600388","display_name":"Paul Wohlhart","orcid":"https://orcid.org/0000-0002-3669-2809","observed_orcids":["https://orcid.org/0000-0002-3669-2809"]},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Paul Wohlhart","raw_affiliation_strings":["Graz University of Technology, Graz, Austria"],"raw_orcid":"https://orcid.org/0000-0002-3669-2809","affiliations":[{"raw_affiliation_string":"Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110628285","display_name":"Yunfei Bai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunfei Bai","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080415080","display_name":"Mrinal Kalakrishnan","orcid":"https://orcid.org/0000-0003-4292-9857","observed_orcids":["https://orcid.org/0000-0003-4292-9857"]},"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":"Mrinal Kalakrishnan","raw_affiliation_strings":["Stanford University, Stanford, United States"],"raw_orcid":"https://orcid.org/0000-0003-4292-9857","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743","observed_orcids":["https://orcid.org/0000-0001-6764-2743"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":"https://orcid.org/0000-0001-6764-2743","affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005431772","display_name":"Chelsea Finn","orcid":"https://orcid.org/0000-0001-6298-0874","observed_orcids":["https://orcid.org/0000-0001-6298-0874"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chelsea Finn","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":"https://orcid.org/0000-0001-6298-0874","affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]}],"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":false,"cited_by_count":12,"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":0.9990000128746033,"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":0.9990000128746033,"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":0.0008999999845400453,"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":0.0,"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/meta-reinforcement-learning","display_name":"meta-reinforcement learning","score":0.8190000057220459},{"id":"https://openalex.org/keywords/demonstration-based-learning","display_name":"demonstration-based learning","score":0.6549999713897705},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.7720000147819519},{"id":"https://openalex.org/keywords/visual-servoing","display_name":"visual servoing","score":0.7599999904632568},{"id":"https://openalex.org/keywords/task-ambiguity","display_name":"task ambiguity","score":0.4359999895095825},{"id":"https://openalex.org/keywords/meta-learning","display_name":"meta-learning","score":0.5609999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8125789165496826},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7283807396888733},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7085199356079102},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7050543427467346},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6242073774337769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6132057905197144},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.6131709814071655},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5961564779281616},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4715060293674469},{"id":"https://openalex.org/C2986563244","wikidata":"https://www.wikidata.org/wiki/Q6822310","display_name":"Learning to learn","level":2,"score":0.4500005841255188},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4323454201221466},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42374908924102783},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.41956549882888794},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2995508322","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.03352.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":null,"is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2995508322","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.03352.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":null,"is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W99485931","https://openalex.org/W1579853615","https://openalex.org/W1598377843","https://openalex.org/W1977655452","https://openalex.org/W2016765487","https://openalex.org/W2127107099","https://openalex.org/W2137375617","https://openalex.org/W2137825550","https://openalex.org/W2167117957","https://openalex.org/W2257979135","https://openalex.org/W2290354866","https://openalex.org/W2397581010","https://openalex.org/W2415726935","https://openalex.org/W2550182557","https://openalex.org/W2604763608","https://openalex.org/W2726717203","https://openalex.org/W2755546070","https://openalex.org/W2756826236","https://openalex.org/W2757631751","https://openalex.org/W2785397462","https://openalex.org/W2787387965","https://openalex.org/W2787501667","https://openalex.org/W2790355818","https://openalex.org/W2895558617","https://openalex.org/W2899138465","https://openalex.org/W2903630557","https://openalex.org/W2923504512","https://openalex.org/W2942459156","https://openalex.org/W2963007936","https://openalex.org/W2963094133","https://openalex.org/W2963098081","https://openalex.org/W2963176272","https://openalex.org/W2963376229","https://openalex.org/W2964121744","https://openalex.org/W2964161785","https://openalex.org/W2964250417","https://openalex.org/W4297787359"],"related_works":["https://openalex.org/W2948199445","https://openalex.org/W6992890680","https://openalex.org/W2601322194","https://openalex.org/W2755546070","https://openalex.org/W3206106208","https://openalex.org/W3010145806","https://openalex.org/W7169800094","https://openalex.org/W3131421420","https://openalex.org/W4306317306","https://openalex.org/W7124227505"],"abstract_inverted_index":{"Imitation":[0],"learning":[1,11,24,47],"allows":[2],"agents":[3,31],"to":[4,32,73,88,102,109,122,128],"learn":[5,33,87,89],"complex":[6,13],"behaviors":[7],"from":[8,37,46,90],"demonstrations.":[9,22],"However,":[10],"a":[12,26,34,40,76,83,153],"vision-based":[14,157],"task":[15,36,54,72],"may":[16,61],"require":[17],"an":[18,66],"impractical":[19],"number":[20],"of":[21,53,132,140,155],"Meta-imitation":[23],"is":[25],"promising":[27],"approach":[28,105],"towards":[29],"enabling":[30],"new":[35],"one":[38],"or":[39,56],"few":[41],"demonstrations":[42,59,92],"by":[43],"leveraging":[44],"experience":[45,95],"similar":[48],"tasks.":[49,159],"In":[50,78,100,120],"the":[51,71,107,117,135,138],"presence":[52],"ambiguity":[55],"unobserved":[57],"dynamics,":[58],"alone":[60],"not":[62],"provide":[63],"enough":[64],"information;":[65],"agent":[67,108],"must":[68],"also":[69],"try":[70],"successfully":[74],"infer":[75],"policy.":[77],"this":[79,104],"work,":[80],"we":[81,125],"propose":[82],"method":[84,147],"that":[85,145],"can":[86,126],"both":[91],"and":[93,111],"trial-and-error":[94],"with":[96],"sparse":[97],"reward":[98],"feedback.":[99],"comparison":[101,121],"meta-imitation,":[103],"enables":[106],"effectively":[110],"efficiently":[112],"improve":[113],"itself":[114],"autonomously":[115],"beyond":[116],"demonstration":[118,136],"data.":[119],"meta-reinforcement":[123],"learning,":[124],"scale":[127],"substantially":[129],"broader":[130],"distributions":[131],"tasks,":[133],"as":[134],"reduces":[137],"burden":[139],"exploration.":[141],"Our":[142],"experiments":[143],"show":[144],"our":[146],"significantly":[148],"outperforms":[149],"prior":[150],"approaches":[151],"on":[152],"set":[154],"challenging,":[156],"control":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-12-26T00:00:00"}
