{"id":"https://openalex.org/W3089340499","doi":"https://doi.org/10.48550/arxiv.2010.01748","title":"Policy Learning Using Weak Supervision","display_name":"Policy Learning Using Weak Supervision","publication_year":2020,"publication_date":"2020-10-05","ids":{"openalex":"https://openalex.org/W3089340499","doi":"https://doi.org/10.48550/arxiv.2010.01748","mag":"3089340499"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2010.01748","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.01748","pdf_url":"https://arxiv.org/pdf/2010.01748","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/2010.01748","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wang, Jingkang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Wang, Jingkang","raw_affiliation_strings":["University of Toronto , Vector Institute 2 , Northwestern University 3 , UC Santa Cruz 4","University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto , Vector Institute 2 , Northwestern University 3 , UC Santa Cruz 4","institution_ids":["https://openalex.org/I111979921","https://openalex.org/I185103710","https://openalex.org/I185261750","https://openalex.org/I4210127509"]},{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102756966","display_name":"Hongyi Guo","orcid":"https://orcid.org/0000-0001-9338-731X","observed_orcids":["https://orcid.org/0000-0001-9338-731X"]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guo, Hongyi","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025441627","display_name":"Zhaowei Zhu","orcid":"https://orcid.org/0000-0003-3894-5862","observed_orcids":["https://orcid.org/0000-0003-3894-5862"]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhu, Zhaowei","raw_affiliation_strings":["UNIVERSITY OF CALIFORNIA (SANTA CRUZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNIVERSITY OF CALIFORNIA (SANTA CRUZ)","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"last","author":{"id":null,"display_name":"Liu, Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Yang","raw_affiliation_strings":["UNIVERSITY OF CALIFORNIA (SANTA CRUZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNIVERSITY OF CALIFORNIA (SANTA CRUZ)","institution_ids":["https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"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/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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/policy-learning","display_name":"policy learning","score":0.8199999928474426},{"id":"https://openalex.org/keywords/weakly-supervised-learning","display_name":"weakly supervised learning","score":1.0},{"id":"https://openalex.org/keywords/peer-agents","display_name":"peer agents","score":0.4519999921321869},{"id":"https://openalex.org/keywords/behavioral-cloning","display_name":"behavior cloning","score":0.890999972820282},{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.7739999890327454},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.4699999988079071},{"id":"https://openalex.org/keywords/theoretical-guarantees","display_name":"theoretical guarantees","score":0.5320000052452087}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8153076171875},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7972092032432556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7032828330993652},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.5941571593284607},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5571799874305725},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4836098253726959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42350879311561584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34662771224975586},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10690498352050781},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2010.01748","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.01748","pdf_url":"https://arxiv.org/pdf/2010.01748","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.2010.01748","doi":"https://doi.org/10.48550/arxiv.2010.01748","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.01748","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.01748","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.01748","pdf_url":"https://arxiv.org/pdf/2010.01748","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":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1645553586","display_name":"Collaborative Research: RI: Small: Wisdom of Crowds with Machines in the Loop","funder_award_id":"2007951","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5751932703","display_name":null,"funder_award_id":"N00014-20-1-2240","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8006577219","display_name":null,"funder_award_id":"N00014-20","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320319880","display_name":"Government of Canada","ror":"https://ror.org/010q4q527"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W107583932","https://openalex.org/W303151045","https://openalex.org/W1512919909","https://openalex.org/W1514928307","https://openalex.org/W1583330603","https://openalex.org/W1757796397","https://openalex.org/W1777239053","https://openalex.org/W1866072925","https://openalex.org/W1866935739","https://openalex.org/W1977124739","https://openalex.org/W2051228319","https://openalex.org/W2113290770","https://openalex.org/W2120898858","https://openalex.org/W2122701159","https://openalex.org/W2142641780","https://openalex.org/W2145339207","https://openalex.org/W2147750403","https://openalex.org/W2155027007","https://openalex.org/W2155968351","https://openalex.org/W2159600763","https://openalex.org/W2165131254","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2265722441","https://openalex.org/W2295734738","https://openalex.org/W2296673577","https://openalex.org/W2342840547","https://openalex.org/W2356882517","https://openalex.org/W2397581010","https://openalex.org/W2536321907","https://openalex.org/W2617069179","https://openalex.org/W2734594771","https://openalex.org/W2736601468","https://openalex.org/W2751973545","https://openalex.org/W2774527530","https://openalex.org/W2785379783","https://openalex.org/W2802726207","https://openalex.org/W2938421504","https://openalex.org/W2950226226","https://openalex.org/W2962957031","https://openalex.org/W2963028646","https://openalex.org/W2963376229","https://openalex.org/W2963477884","https://openalex.org/W2963572325","https://openalex.org/W2964120017","https://openalex.org/W2978612180","https://openalex.org/W2981030070","https://openalex.org/W2988175183","https://openalex.org/W2998116579","https://openalex.org/W3021906347","https://openalex.org/W3035753488","https://openalex.org/W3122805849","https://openalex.org/W3125547903","https://openalex.org/W3127098609","https://openalex.org/W3128198050","https://openalex.org/W3129100675","https://openalex.org/W3129603874","https://openalex.org/W3130878888","https://openalex.org/W3170213241","https://openalex.org/W3170414933"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W3009056573","https://openalex.org/W4297676672","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W2989932438","https://openalex.org/W4387297750","https://openalex.org/W2186333919"],"abstract_inverted_index":{"Most":[0],"existing":[1],"policy":[2,58,83,93,103,130],"learning":[3,7,20,59,81,150],"solutions":[4],"require":[5],"the":[6,51,67,80,90,107,143,146,149],"agents":[8],"to":[9,39,56,106,112,137],"receive":[10],"high-quality":[11,23],"supervision":[12],"signals":[13],"such":[14],"as":[15,70],"well-designed":[16],"rewards":[17],"in":[18,26,41],"reinforcement":[19],"(RL)":[21],"or":[22,36,145],"expert":[24],"demonstrations":[25],"behavioral":[27],"cloning":[28],"(BC).":[29],"These":[30],"quality":[31],"supervisions":[32,55],"are":[33],"usually":[34],"infeasible":[35],"prohibitively":[37],"expensive":[38],"obtain":[40],"practice.":[42],"We":[43],"aim":[44],"for":[45,104],"a":[46,75,86,102],"unified":[47],"framework":[48],"that":[49,133],"leverages":[50],"available":[52],"cheap":[53],"weak":[54,108,126],"perform":[57],"efficiently.":[60],"To":[61],"handle":[62],"this":[63],"problem,":[64],"we":[65],"treat":[66],"\"weak":[68],"supervision\"":[69],"imperfect":[71],"information":[72],"coming":[73],"from":[74],"peer":[76,91],"agent,":[77],"and":[78,128],"evaluate":[79],"agent's":[82,92],"based":[84],"on":[85,117],"\"correlated":[87],"agreement\"":[88],"with":[89,121,125],"(instead":[94],"of":[95,148],"simple":[96],"agreements).":[97],"Our":[98],"approach":[99],"explicitly":[100],"punishes":[101],"overfitting":[105],"supervision.":[109],"In":[110],"addition":[111],"theoretical":[113],"guarantees,":[114],"extensive":[115],"evaluations":[116],"tasks":[118],"including":[119],"RL":[120],"noisy":[122],"rewards,":[123],"BC":[124],"demonstrations,":[127],"standard":[129],"co-training":[131],"show":[132],"our":[134],"method":[135],"leads":[136],"substantial":[138],"performance":[139],"improvements,":[140],"especially":[141],"when":[142],"complexity":[144],"noise":[147],"environments":[151],"is":[152],"high.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}