{"id":"https://openalex.org/W3084024636","doi":"https://doi.org/10.48550/arxiv.2009.04875","title":"Importance Weighted Policy Learning and Adaptation","display_name":"Importance Weighted Policy Learning and Adaptation","publication_year":2020,"publication_date":"2020-09-10","ids":{"openalex":"https://openalex.org/W3084024636","doi":"https://doi.org/10.48550/arxiv.2009.04875","mag":"3084024636"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2009.04875","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.04875","pdf_url":"https://arxiv.org/pdf/2009.04875","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/2009.04875","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067400056","display_name":"Alexandre Galashov","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":"Galashov, Alexandre","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033464007","display_name":"Jakub Sygnowski","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":"Sygnowski, Jakub","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Desjardins, Guillaume","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":"Desjardins, Guillaume","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102771619","display_name":"Jan Humplik","orcid":"https://orcid.org/0000-0002-7573-7635","observed_orcids":["https://orcid.org/0000-0002-7573-7635"]},"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":"Humplik, Jan","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014567358","display_name":"Leonard Hasenclever","orcid":"https://orcid.org/0000-0003-1844-696X","observed_orcids":["https://orcid.org/0000-0003-1844-696X"]},"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":"Hasenclever, Leonard","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079341248","display_name":"Rae Jeong","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":"Jeong, Rae","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064373793","display_name":"Yee Whye Teh","orcid":"https://orcid.org/0000-0001-5365-6933","observed_orcids":["https://orcid.org/0000-0001-5365-6933"]},"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":"Teh, Yee Whye","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062951341","display_name":"Nicolas Heess","orcid":"https://orcid.org/0000-0001-7876-9256","observed_orcids":["https://orcid.org/0000-0001-7876-9256"]},"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":"Heess, Nicolas","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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":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":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"}},{"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/off-policy-learning","display_name":"off-policy learning","score":0.7179999947547913},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.5429999828338623},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.5099999904632568},{"id":"https://openalex.org/keywords/exploration-bias","display_name":"exploration bias","score":0.5590000152587891},{"id":"https://openalex.org/keywords/value-function-representation","display_name":"value function representation","score":0.7360000014305115},{"id":"https://openalex.org/keywords/meta-reinforcement-learning","display_name":"meta-reinforcement learning","score":0.5709999799728394}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8699308633804321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7780199646949768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6423023343086243},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5900222659111023},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5862665772438049},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.572239875793457},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5477064847946167},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5119910836219788},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5086017847061157},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4962683320045471},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.4715195894241333},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44979193806648254},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4122734069824219},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2009.04875","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.04875","pdf_url":"https://arxiv.org/pdf/2009.04875","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:3084024636","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2009.04875","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.2009.04875","doi":"https://doi.org/10.48550/arxiv.2009.04875","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2009.04875","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:2009.04875","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.04875","pdf_url":"https://arxiv.org/pdf/2009.04875","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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3084024636.pdf","grobid_xml":"https://content.openalex.org/works/W3084024636.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1757796397","https://openalex.org/W1906772730","https://openalex.org/W2133458291","https://openalex.org/W2162888803","https://openalex.org/W2328078142","https://openalex.org/W2402108766","https://openalex.org/W2411690432","https://openalex.org/W2534060593","https://openalex.org/W2550182557","https://openalex.org/W2594103415","https://openalex.org/W2604763608","https://openalex.org/W2781726626","https://openalex.org/W2785342287","https://openalex.org/W2787501667","https://openalex.org/W2787938642","https://openalex.org/W2788781499","https://openalex.org/W2794363191","https://openalex.org/W2795900505","https://openalex.org/W2902286283","https://openalex.org/W2905822515","https://openalex.org/W2909000816","https://openalex.org/W2913340405","https://openalex.org/W2921528247","https://openalex.org/W2923504512","https://openalex.org/W2942608247","https://openalex.org/W2944299231","https://openalex.org/W2945020056","https://openalex.org/W2954970763","https://openalex.org/W2962717849","https://openalex.org/W2963176272","https://openalex.org/W2963199420","https://openalex.org/W2963985863","https://openalex.org/W2964078140","https://openalex.org/W2974885182","https://openalex.org/W2980555752","https://openalex.org/W2998488389","https://openalex.org/W3002855444","https://openalex.org/W4302288054"],"related_works":["https://openalex.org/W4394657676","https://openalex.org/W2923504512","https://openalex.org/W3124020087","https://openalex.org/W3037114224","https://openalex.org/W3127942204","https://openalex.org/W3208912291","https://openalex.org/W3144439340","https://openalex.org/W2737617713","https://openalex.org/W4414684717","https://openalex.org/W7109093094"],"abstract_inverted_index":{"The":[0,70],"ability":[1],"to":[2,6,141,149],"exploit":[3],"prior":[4],"experience":[5],"solve":[7],"novel":[8],"problems":[9],"rapidly":[10],"is":[11,55,72],"a":[12,51,87,102,109,122,128],"hallmark":[13],"of":[14,19,40,64,97,116,124],"biological":[15],"learning":[16,30,43,85,144],"systems":[17],"and":[18,60,81,99,146],"great":[20],"practical":[21],"importance":[22],"for":[23,104,111],"artificial":[24],"ones.":[25],"In":[26,46],"the":[27,38,42,77,95,112],"meta":[28,142],"reinforcement":[29,143],"literature":[31,80],"much":[32],"recent":[33,65],"work":[34],"has":[35],"focused":[36],"on":[37,62,137],"problem":[39],"optimizing":[41],"process":[44],"itself.":[45],"this":[47],"paper":[48],"we":[49],"study":[50],"complementary":[52],"approach":[53,132],"which":[54,117],"conceptually":[56],"simple,":[57],"general,":[58],"modular":[59],"built":[61],"top":[63],"improvements":[66],"in":[67,127],"off-policy":[68,84],"learning.":[69],"framework":[71],"inspired":[73],"by":[74],"ideas":[75],"from":[76,121],"probabilistic":[78],"inference":[79],"combines":[82],"robust":[83],"with":[86],"behavior":[88,92],"prior,":[89],"or":[90],"default":[91],"that":[93],"constrains":[94],"space":[96],"solutions":[98],"serves":[100],"as":[101,106,108],"bias":[103],"exploration;":[105],"well":[107],"representation":[110],"value":[113],"function,":[114],"both":[115],"are":[118],"easily":[119],"learned":[120],"number":[123],"training":[125],"tasks":[126,139],"multi-task":[129],"scenario.":[130],"Our":[131],"achieves":[133],"competitive":[134],"adaptation":[135],"performance":[136],"hold-out":[138],"compared":[140],"baselines":[145],"can":[147],"scale":[148],"complex":[150],"sparse-reward":[151],"scenarios.":[152]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2020-09-14T00:00:00"}