{"id":"https://openalex.org/W2942910319","doi":null,"title":"Learning good policies from suboptimal demonstrations","display_name":"Learning good policies from suboptimal demonstrations","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2942910319","mag":"2942910319"},"language":"en","primary_location":{"id":"mag:2942910319","doi":null,"is_oa":false,"landing_page_url":"https://www.microsoft.com/en-us/research/publication/learning-good-policies-from-suboptimal-demonstrations/","pdf_url":null,"source":{"id":"https://openalex.org/S4306418391","display_name":"European Workshop on Reinforcement Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"European Workshop on Reinforcement Learning","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100341650","display_name":"Yuxiang Li","orcid":"https://orcid.org/0000-0002-1575-3692","observed_orcids":["https://orcid.org/0000-0002-1575-3692","https://orcid.org/0009-0004-5386-8070"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxiang Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1575-3692","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045648666","display_name":"Ian A. Kash","orcid":"https://orcid.org/0000-0002-7826-8555","observed_orcids":["https://orcid.org/0000-0002-7826-8555"]},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian A. Kash","raw_affiliation_strings":["University of Illinois at Chicago, Chicago, United States"],"raw_orcid":"https://orcid.org/0000-0002-7826-8555","affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago, Chicago, United States","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027441885","display_name":"Katja Hofmann","orcid":"https://orcid.org/0000-0003-3697-407X","observed_orcids":["https://orcid.org/0000-0003-3697-407X"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katja Hofmann","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3539,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.58952355,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"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":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/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/imitation-learning","display_name":"imitation learning","score":0.8840000033378601},{"id":"https://openalex.org/keywords/expert-policy","display_name":"expert policy","score":0.5360000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8088188171386719},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7268720865249634},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.6495091319084167},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5490074157714844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5289590358734131},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5230337381362915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5171675086021423},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2942910319","doi":null,"is_oa":false,"landing_page_url":"https://www.microsoft.com/en-us/research/publication/learning-good-policies-from-suboptimal-demonstrations/","pdf_url":null,"source":{"id":"https://openalex.org/S4306418391","display_name":"European Workshop on Reinforcement Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"European Workshop on Reinforcement Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1850531616","https://openalex.org/W1931877416","https://openalex.org/W1986014385","https://openalex.org/W1998427280","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2287850282","https://openalex.org/W2603266952","https://openalex.org/W2620777928","https://openalex.org/W2756826236"],"related_works":["https://openalex.org/W4409347153","https://openalex.org/W3144127138","https://openalex.org/W4405955696","https://openalex.org/W4414989063","https://openalex.org/W4306317306","https://openalex.org/W4226373607","https://openalex.org/W4416016187","https://openalex.org/W4400728388","https://openalex.org/W4415800601","https://openalex.org/W7160315562"],"abstract_inverted_index":{"Imitating":[0],"an":[1,43],"expert":[2,52],"policy":[3],"is":[4,54],"one":[5],"way":[6],"to":[7,57,106],"boost":[8],"reinforcement":[9],"learning":[10,69],"algorithms":[11],"which,":[12],"in":[13,59],"most":[14,40],"cases,":[15],"rely":[16],"on":[17,68,88],"random":[18],"exploration":[19],"and":[20,91,116],"a":[21,48,82,111],"huge":[22],"amount":[23],"of":[24,30,46,81],"data.":[25,75,100],"While":[26],"some":[27],"major":[28],"drawbacks":[29],"imitation":[31],"learning,":[32],"such":[33],"as":[34],"compound":[35],"errors,":[36],"have":[37],"been":[38],"addressed,":[39],"results":[41],"make":[42],"implicit":[44],"hypothesis":[45],"having":[47],"good":[49,70],"(or":[50],"desired)":[51],"which":[53],"usually":[55],"hard":[56],"get":[58],"practice.":[60],"To":[61],"overcome":[62,107],"this":[63,65,108],"obstacle,":[64],"paper":[66],"focuses":[67],"policies":[71],"from":[72],"suboptimal":[73,98],"demonstration":[74,89,99],"We":[76,101],"systematically":[77],"investigate":[78],"the":[79,104],"performance":[80,112],"recent":[83],"approach":[84],"under":[85],"varying":[86],"assumptions":[87],"quality":[90],"show":[92],"that":[93],"it":[94],"performs":[95],"poorly":[96],"with":[97],"then":[102],"demonstrate":[103],"potential":[105],"issue":[109],"through":[110],"comparison":[113],"between":[114],"learner":[115],"demonstrator.":[117]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-05-09T00:00:00"}