{"id":"https://openalex.org/W3135497281","doi":"https://doi.org/10.1145/3434074.3446361","title":"Interactive Reinforcement Learning from Imperfect Teachers","display_name":"Interactive Reinforcement Learning from Imperfect Teachers","publication_year":2021,"publication_date":"2021-03-08","ids":{"openalex":"https://openalex.org/W3135497281","doi":"https://doi.org/10.1145/3434074.3446361","mag":"3135497281"},"language":"en","primary_location":{"id":"doi:10.1145/3434074.3446361","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3434074.3446361","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3434074.3446361","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3434074.3446361","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052192059","display_name":"Taylor A. Kessler Faulkner","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor A. Kessler Faulkner","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066797327","display_name":"Andrea L. Thomaz","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Thomaz","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"577","last_page":"579"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9807000160217285,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9696999788284302,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.8245651721954346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7404370903968811},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7309974431991577},{"id":"https://openalex.org/keywords/perfect-information","display_name":"Perfect information","score":0.6644023060798645},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6300055980682373},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.547124981880188},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5468357801437378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4808505177497864},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3521432876586914},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07148048281669617}],"concepts":[{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.8245651721954346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404370903968811},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7309974431991577},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.6644023060798645},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6300055980682373},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.547124981880188},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5468357801437378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4808505177497864},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3521432876586914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07148048281669617},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"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/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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3434074.3446361","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3434074.3446361","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3434074.3446361","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3434074.3446361","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3434074.3446361","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3434074.3446361","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G5255482611","display_name":null,"funder_award_id":"1564080, 1724157, DGE-1610403","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5963171147","display_name":null,"funder_award_id":"N000141612785","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6872063243","display_name":null,"funder_award_id":"DGE-1610403","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G767989324","display_name":null,"funder_award_id":"N000141612835, N000141612785","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7740938808","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"1610403","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G829377574","display_name":"S&AS: INT: Socially-Aware Autonomy for Long-Term Deployment of Always-On Heterogeneous Robot Teams","funder_award_id":"1724157","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3135497281.pdf","grobid_xml":"https://content.openalex.org/works/W3135497281.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1583953806","https://openalex.org/W1589064538","https://openalex.org/W1973749650","https://openalex.org/W2010695153","https://openalex.org/W2044142939","https://openalex.org/W2044865707","https://openalex.org/W2096258902","https://openalex.org/W2098441518","https://openalex.org/W2110064869","https://openalex.org/W2131797004","https://openalex.org/W2493924325","https://openalex.org/W2539402368","https://openalex.org/W2909713847","https://openalex.org/W2944766483","https://openalex.org/W2963489214","https://openalex.org/W3032916997","https://openalex.org/W3032981689"],"related_works":["https://openalex.org/W2360321812","https://openalex.org/W2395295193","https://openalex.org/W3122057932","https://openalex.org/W2113798763","https://openalex.org/W3088364074","https://openalex.org/W2004230228","https://openalex.org/W2610227658","https://openalex.org/W2145796981","https://openalex.org/W2900431508","https://openalex.org/W2050340470"],"abstract_inverted_index":{"Robots":[0],"can":[1,14],"use":[2],"information":[3],"from":[4,31,48,71],"people":[5,13,40],"to":[6,65],"improve":[7],"learning":[8,30,47],"speed":[9],"or":[10],"quality.":[11],"However,":[12],"have":[15],"short":[16],"attention":[17],"spans":[18],"and":[19,43],"misunderstand":[20],"tasks.":[21],"Our":[22],"work":[23],"addresses":[24],"these":[25],"issues":[26],"with":[27],"algorithms":[28],"for":[29,46],"inattentive":[32],"teachers":[33,50],"that":[34,51],"take":[35,66],"advantage":[36,67],"of":[37,68],"feedback":[38,70],"when":[39],"are":[41],"present,":[42],"an":[44],"algorithm":[45],"inaccurate":[49],"estimates":[52],"which":[53],"state-action":[54],"pairs":[55],"receive":[56],"incorrect":[57],"feedback.":[58],"These":[59],"advances":[60],"will":[61],"enhance":[62],"robots'":[63],"ability":[64],"imperfect":[69],"human":[72],"teachers.":[73]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}