{"id":"https://openalex.org/W4306317306","doi":"https://doi.org/10.1145/3511808.3557357","title":"Imitation Learning to Outperform Demonstrators by Directly Extrapolating Demonstrations","display_name":"Imitation Learning to Outperform Demonstrators by Directly Extrapolating Demonstrations","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317306","doi":"https://doi.org/10.1145/3511808.3557357"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557357","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557357","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557357","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557357","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112893154","display_name":"Yuanying Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanying Cai","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080460228","display_name":"Chuheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuheng Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101956272","display_name":"Wei Shen","orcid":"https://orcid.org/0000-0003-3479-1165"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Shen","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085997608","display_name":"Xiaonan He","orcid":"https://orcid.org/0009-0003-7263-7940"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaonan He","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076120553","display_name":"Xuyun Zhang","orcid":"https://orcid.org/0000-0001-7353-4159"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuyun Zhang","raw_affiliation_strings":["Macquarie University, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082905458","display_name":"Longbo Huang","orcid":"https://orcid.org/0000-0002-7341-447X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbo Huang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3374,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55568008,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"128","last_page":"137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9955000281333923,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9682000279426575,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7309224605560303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7304139733314514},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6222345232963562},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5593453049659729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5383497476577759},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.42488664388656616},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3496008515357971},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09126242995262146}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7309224605560303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304139733314514},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6222345232963562},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5593453049659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5383497476577759},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.42488664388656616},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3496008515357971},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09126242995262146},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":"doi:10.1145/3511808.3557357","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557357","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557357","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3511808.3557357","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3511808.3557357","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3511808.3557357","source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2614271227","display_name":null,"funder_award_id":"10001020109","funder_id":"https://openalex.org/F4320322392","funder_display_name":"Tsinghua University"}],"funders":[{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306317306.pdf","grobid_xml":"https://content.openalex.org/works/W4306317306.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W2098774185","https://openalex.org/W2158782408","https://openalex.org/W2187089797","https://openalex.org/W2402734324","https://openalex.org/W2788862220","https://openalex.org/W2911087563","https://openalex.org/W2914931737","https://openalex.org/W2947150733","https://openalex.org/W2963654596","https://openalex.org/W2964460729","https://openalex.org/W3015437096","https://openalex.org/W3080373606","https://openalex.org/W3101722615","https://openalex.org/W3115293622"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2468279273"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,28,32,54,60,64,78,156,167,188],"problem":[3],"of":[4,31,105,114],"imitation":[5,144,184],"learning":[6,38,106,145,185],"from":[7],"suboptimal":[8,176],"demonstrations":[9,58,122],"that":[10,117,123,173],"aims":[11],"to":[12,26,39,52,80,147],"learn":[13,22,40,148],"a":[14,23,41,94,107,128,149],"better":[15,180],"policy":[16,42,62,158],"than":[17,182],"demonstrators.":[18],"Previous":[19],"methods":[20,49],"usually":[21],"reward":[24,46,66,108],"function":[25,67],"encode":[27],"underlying":[29],"intention":[30],"demonstrators":[33,99,177],"and":[34,59,75,164,178,190],"use":[35,141],"standard":[36],"reinforcement":[37],"based":[43,131],"on":[44,72,132,187],"this":[45,90],"function.":[47],"Such":[48],"can":[50,76,140],"fail":[51],"control":[53],"distribution":[55,168],"shift":[56],"between":[57],"learned":[61,65,157],"since":[63],"may":[68,124],"not":[69],"generalize":[70],"well":[71],"out-of-distribution":[73],"samples":[74],"mislead":[77],"agent":[79],"highly":[81,161],"uncertain":[82,162],"states,":[83],"resulting":[84],"in":[85],"degenerated":[86],"performance.":[87],"To":[88],"address":[89],"limitation,":[91],"we":[92,139,171],"propose":[93],"novel":[95],"algorithm":[96,146],"called":[97],"Outperforming":[98],"by":[100,127,153],"Directly":[101],"Extrapolating":[102],"Demonstrations(ODED).":[103],"Instead":[104],"function,":[109],"ODED":[110,174],"trains":[111],"an":[112,142],"ensemble":[113],"extrapolation":[115],"networks":[116],"generate":[118],"extrapolated":[119,137,154],"demonstrations,":[120,138,155],"i.e.,":[121],"be":[125],"induced":[126],"good":[129,150],"agent,":[130],"provided":[133],"demonstrations.":[134],"With":[135],"these":[136],"off-the-shelf":[143],"policy.":[151],"Guided":[152],"avoids":[159],"visiting":[160],"states":[163],"therefore":[165],"controls":[166],"shift.":[169],"Empirically,":[170],"show":[172],"outperforms":[175],"achieves":[179],"performance":[181],"state-of-the-art":[183],"algorithms":[186],"MuJoCo":[189],"DeepMind":[191],"Control":[192],"Suite":[193],"tasks.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}