{"id":"https://openalex.org/W3090894178","doi":"https://doi.org/10.1109/icra40945.2020.9197219","title":"Interactive Reinforcement Learning with Inaccurate Feedback","display_name":"Interactive Reinforcement Learning with Inaccurate Feedback","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3090894178","doi":"https://doi.org/10.1109/icra40945.2020.9197219","mag":"3090894178"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/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":["Department of Computer Science, The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077011363","display_name":"Elaine Schaertl Short","orcid":"https://orcid.org/0000-0002-4789-9979"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elaine Schaertl Short","raw_affiliation_strings":["Department of Computer Science, Tufts University, Medford, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]}]},{"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 L. Thomaz","raw_affiliation_strings":["Department of Electrical and Computer Engineering, The University of Texas of Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The University of Texas of Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7498","last_page":"7504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11182","display_name":"Auction Theory and Applications","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9581000208854675,"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":0.9063360691070557},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8186049461364746},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.7589446306228638},{"id":"https://openalex.org/keywords/perfect-information","display_name":"Perfect information","score":0.7073220014572144},{"id":"https://openalex.org/keywords/advice","display_name":"Advice (programming)","score":0.7024878263473511},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5374501347541809},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5253169536590576},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4896154999732971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42842698097229004},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4131041467189789},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37947383522987366},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32795411348342896}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9063360691070557},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186049461364746},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.7589446306228638},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.7073220014572144},{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.7024878263473511},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5374501347541809},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5253169536590576},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4896154999732971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42842698097229004},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4131041467189789},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37947383522987366},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32795411348342896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra40945.2020.9197219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1515851193","https://openalex.org/W1777239053","https://openalex.org/W1991618009","https://openalex.org/W1996626416","https://openalex.org/W2044865707","https://openalex.org/W2098441518","https://openalex.org/W2110064869","https://openalex.org/W2116157560","https://openalex.org/W2156869222","https://openalex.org/W2205847592","https://openalex.org/W2275119517","https://openalex.org/W2290053245","https://openalex.org/W2402734324","https://openalex.org/W2415726935","https://openalex.org/W2565971318","https://openalex.org/W2741122588","https://openalex.org/W2754794180","https://openalex.org/W2785379783","https://openalex.org/W2962937519","https://openalex.org/W2963363446","https://openalex.org/W2963943581","https://openalex.org/W6638088447","https://openalex.org/W6674812091","https://openalex.org/W6677262939","https://openalex.org/W6696265566","https://openalex.org/W6716193690","https://openalex.org/W6730861637","https://openalex.org/W6744338129","https://openalex.org/W6748314335","https://openalex.org/W6761908843"],"related_works":["https://openalex.org/W2360321812","https://openalex.org/W2395295193","https://openalex.org/W3122057932","https://openalex.org/W2152537654","https://openalex.org/W2113798763","https://openalex.org/W3088364074","https://openalex.org/W2004230228","https://openalex.org/W2610227658","https://openalex.org/W2145796981","https://openalex.org/W2900431508"],"abstract_inverted_index":{"Interactive":[0,86],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"enables":[4],"agents":[5,47],"to":[6,48,65,107],"learn":[7,49],"from":[8,13,22,38,98],"two":[9],"sources:":[10],"rewards":[11],"taken":[12],"observations":[14],"of":[15,36,140,152],"the":[16,42,46,137,149],"environment,":[17],"and":[18,92,118,125],"feedback":[19,62,109,142],"or":[20,31,63,147],"advice":[21,64],"a":[23,39,82,122,141],"secondary":[24],"critic":[25,40],"source,":[26,143],"such":[27],"as":[28],"human":[29],"teachers":[30,91],"sensor":[32],"feedback.":[33],"The":[34],"addition":[35],"information":[37,135],"during":[41],"learning":[43],"process":[44],"allows":[45],"more":[50],"quickly":[51],"than":[52],"non-interactive":[53],"RL.":[54,69],"There":[55],"are":[56],"many":[57],"methods":[58,88],"that":[59,127],"allow":[60],"policy":[61],"be":[66],"combined":[67],"with":[68,89],"However,":[70],"critics":[71],"can":[72,104],"often":[73],"give":[74],"imperfect":[75,90,108],"information.":[76],"In":[77],"this":[78],"work,":[79],"we":[80],"introduce":[81],"framework":[83],"for":[84],"characterizing":[85],"RL":[87],"propose":[93],"an":[94],"algorithm,":[95],"Revision":[96],"Estimation":[97],"Partially":[99],"Incorrect":[100],"Resources":[101],"(REPaIR),":[102],"which":[103],"estimate":[105],"corrections":[106],"over":[110],"time.":[111],"We":[112],"run":[113],"experiments":[114],"both":[115],"in":[116],"simulations":[117],"demonstrate":[119],"performance":[120,151],"on":[121,136],"physical":[123],"robot,":[124],"find":[126],"when":[128],"baseline":[129],"algorithms":[130],"do":[131],"not":[132],"have":[133],"prior":[134],"exact":[138],"quality":[139],"using":[144],"REPaIR":[145],"matches":[146],"improves":[148],"expected":[150],"these":[153],"algorithms.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}