{"id":"https://openalex.org/W3102359080","doi":"https://doi.org/10.48550/arxiv.2102.13185","title":"Off-Policy Imitation Learning from Observations","display_name":"Off-Policy Imitation Learning from Observations","publication_year":2021,"publication_date":"2021-02-25","ids":{"openalex":"https://openalex.org/W3102359080","doi":"https://doi.org/10.48550/arxiv.2102.13185","mag":"3102359080"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2102.13185","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.13185","pdf_url":"https://arxiv.org/pdf/2102.13185","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.13185","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079428801","display_name":"Zhuangdi Zhu","orcid":"https://orcid.org/0000-0002-7418-731X","observed_orcids":["https://orcid.org/0000-0002-7418-731X"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhu, Zhuangdi","raw_affiliation_strings":["Michigan State University","Michigan State University, East Lansing, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"Michigan State University, East Lansing, United States","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443077","display_name":"Kaixiang Lin","orcid":"https://orcid.org/0009-0006-6738-651X","observed_orcids":["https://orcid.org/0009-0006-6738-651X","https://orcid.org/0000-0002-8626-8934"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin, Kaixiang","raw_affiliation_strings":["Michigan State University","Michigan State University, East Lansing, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"Michigan State University, East Lansing, United States","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101990494","display_name":"Bo Dai","orcid":"https://orcid.org/0000-0003-0866-447X","observed_orcids":["https://orcid.org/0000-0003-0866-447X"]},"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":"Dai, Bo","raw_affiliation_strings":["Google Research","Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047215778","display_name":"Jiayu Zhou","orcid":"https://orcid.org/0000-0003-4336-6777","observed_orcids":["https://orcid.org/0000-0003-4336-6777"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Jiayu","raw_affiliation_strings":["Michigan State University","Michigan State University, East Lansing, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"Michigan State University, East Lansing, United States","institution_ids":["https://openalex.org/I87216513"]}]}],"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":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"12402","last_page":"12413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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":0.0,"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/observational-learning","display_name":"observational learning","score":0.9649999737739563},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.9300000071525574},{"id":"https://openalex.org/keywords/off-policy-learning","display_name":"off-policy learning","score":0.8029999732971191},{"id":"https://openalex.org/keywords/distribution-matching","display_name":"distribution matching","score":0.8159999847412109},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.8920000195503235},{"id":"https://openalex.org/keywords/mode-coverage","display_name":"mode coverage","score":0.8830000162124634},{"id":"https://openalex.org/keywords/locomotor-control","display_name":"locomotion control","score":0.6340000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7478827238082886},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6690141558647156},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6040080189704895},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5843731164932251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5530866384506226},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5078313946723938},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4945544898509979},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.48989027738571167},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4893288016319275},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.41330671310424805},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4118081033229828},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1342070996761322},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09855198860168457},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2102.13185","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.13185","pdf_url":"https://arxiv.org/pdf/2102.13185","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.2102.13185","doi":"https://doi.org/10.48550/arxiv.2102.13185","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.13185","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3102359080","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.13185","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":"pmh:oai:arXiv.org:2102.13185","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.13185","pdf_url":"https://arxiv.org/pdf/2102.13185","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4406779234","https://openalex.org/W7133192510","https://openalex.org/W2946160813","https://openalex.org/W2994977742","https://openalex.org/W2970003882","https://openalex.org/W4387355780","https://openalex.org/W7119199112","https://openalex.org/W4381250507","https://openalex.org/W4416159171","https://openalex.org/W7126146253"],"abstract_inverted_index":{"Learning":[0],"from":[1,10,129],"Observations":[2],"(LfO)":[3],"is":[4,29,48,145],"a":[5,97,106],"practical":[6],"reinforcement":[7],"learning":[8,26,113],"scenario":[9],"which":[11,61,125],"many":[12],"applications":[13],"can":[14],"benefit":[15],"through":[16],"the":[17,34,50,87,112,117,130],"reuse":[18],"of":[19,33,36,52,89,132,151],"incomplete":[20],"resources.":[21],"Compared":[22],"to":[23],"conventional":[24,42],"imitation":[25],"(IL),":[27],"LfO":[28,99],"more":[30],"challenging":[31,138],"because":[32],"lack":[35,80],"expert":[37,90],"action":[38,123],"guidance.":[39],"In":[40,92],"both":[41,152],"IL":[43],"and":[44,154],"LfO,":[45],"distribution":[46,56,127],"matching":[47,57,128],"at":[49],"heart":[51],"their":[53],"foundation.":[54],"Traditional":[55],"approaches":[58],"are":[59],"sample-costly":[60],"depend":[62,85],"on":[63,86,137],"on-policy":[64],"transitions":[65],"for":[66],"policy":[67,118],"learning.":[68],"Towards":[69],"sample-efficiency,":[70],"some":[71],"off-policy":[72,103],"solutions":[73],"have":[74],"been":[75],"proposed,":[76],"which,":[77],"however,":[78],"either":[79],"comprehensive":[81],"theoretical":[82],"justifications":[83],"or":[84],"guidance":[88],"actions.":[91],"this":[93],"work,":[94],"we":[95,115],"propose":[96],"sample-efficient":[98],"approach":[100,144],"that":[101,142],"enables":[102],"optimization":[104],"in":[105,149],"principled":[107],"manner.":[108],"To":[109],"further":[110],"accelerate":[111],"procedure,":[114],"regulate":[116],"update":[119],"with":[120,147],"an":[121],"inverse":[122],"model,":[124],"assists":[126],"perspective":[131],"mode-covering.":[133],"Extensive":[134],"empirical":[135],"results":[136],"locomotion":[139],"tasks":[140],"indicate":[141],"our":[143],"comparable":[146],"state-of-the-art":[148],"terms":[150],"sample-efficiency":[153],"asymptotic":[155],"performance.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-11-23T00:00:00"}