{"id":"https://openalex.org/W4383101415","doi":"https://doi.org/10.1109/icra48891.2023.10161105","title":"Using Learning Curve Predictions to Learn from Incorrect Feedback","display_name":"Using Learning Curve Predictions to Learn from Incorrect Feedback","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383101415","doi":"https://doi.org/10.1109/icra48891.2023.10161105"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"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":["University of Texas at Austin,Department of Computer Science","Department of Computer Science, University of Texas at Austin","Department of Computer Science and Engineering, University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Department of Computer Science","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"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":["The University of Texas at Austin,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The University of Texas at Austin","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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9414","last_page":"9420"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9659000039100647,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9478999972343445,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7612314224243164},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.729762077331543},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.582777202129364},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.578616738319397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5762238502502441},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5383893251419067},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5318690538406372},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5306174755096436},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5113672614097595},{"id":"https://openalex.org/keywords/learning-curve","display_name":"Learning curve","score":0.4722256660461426},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4708024263381958},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46733248233795166},{"id":"https://openalex.org/keywords/perfect-information","display_name":"Perfect information","score":0.44908517599105835},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15290573239326477},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11318805813789368},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11051362752914429}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7612314224243164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.729762077331543},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.582777202129364},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.578616738319397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5762238502502441},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5383893251419067},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5318690538406372},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5306174755096436},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5113672614097595},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.4722256660461426},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4708024263381958},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46733248233795166},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.44908517599105835},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15290573239326477},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11318805813789368},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11051362752914429},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/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},{"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/icra48891.2023.10161105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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":0.7799999713897705,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1036031458","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/G5419887967","display_name":null,"funder_award_id":"1564080,1724157","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1991618009","https://openalex.org/W2044865707","https://openalex.org/W2098441518","https://openalex.org/W2101234009","https://openalex.org/W2158782408","https://openalex.org/W2290053245","https://openalex.org/W2294422333","https://openalex.org/W2402734324","https://openalex.org/W2415726935","https://openalex.org/W2736629007","https://openalex.org/W2754794180","https://openalex.org/W2788862220","https://openalex.org/W2900406861","https://openalex.org/W2909713847","https://openalex.org/W2944766483","https://openalex.org/W2962937519","https://openalex.org/W2963099939","https://openalex.org/W2963411833","https://openalex.org/W2963489214","https://openalex.org/W2963571918","https://openalex.org/W2973093144","https://openalex.org/W3090894178","https://openalex.org/W3199500857","https://openalex.org/W4321392130","https://openalex.org/W6674812091","https://openalex.org/W6675354045","https://openalex.org/W6683397050","https://openalex.org/W6696265566","https://openalex.org/W6696972564","https://openalex.org/W6716193690","https://openalex.org/W6739585900","https://openalex.org/W6744338129","https://openalex.org/W6744563498","https://openalex.org/W6749950433","https://openalex.org/W6761908843","https://openalex.org/W6768100995","https://openalex.org/W6784078559"],"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":[1,14,19,42],"incorporate":[2],"data":[3,13],"from":[4,33,45,53,63,103,139],"human":[5,34,54,115,136,146,161],"teachers":[6,35,64,105,162],"when":[7],"learning":[8,32,77,99,125],"new":[9],"tasks.":[10],"However,":[11,56],"this":[12],"often":[15],"be":[16],"noisy,":[17],"which":[18,41],"cause":[20],"robots":[21],"to":[22,101,112,141],"learn":[23,102],"slowly":[24],"or":[25,65,157],"not":[26],"at":[27],"all.":[28],"One":[29],"method":[30],"for":[31,82,93],"is":[36,89,110,117],"Human-in-the-loop":[37],"Reinforcement":[38,94],"Learning":[39,83,95],"(HRL),":[40],"combine":[43],"information":[44,62],"both":[46],"an":[47],"environmental":[48],"reward":[49],"and":[50,149],"external":[51],"feedback":[52,91,116,137],"teachers.":[55],"many":[57],"HRL":[58],"methods":[59],"assume":[60],"near-perfect":[61],"must":[66],"know":[67],"the":[68,76,123,133],"skill":[69],"level":[70],"of":[71,122,135],"each":[72],"teacher":[73],"before":[74],"starting":[75],"process.":[78],"Our":[79,127],"algorithm,":[80],"Classification":[81],"Erroneous":[84],"Assessments":[85],"using":[86],"Rewards":[87],"(CLEAR),":[88],"a":[90,145],"filter":[92],"(RL)":[96],"algorithms,":[97],"enabling":[98],"agents":[100],"imperfect":[104],"without":[106,160],"prior":[107],"modeling.":[108],"CLEAR":[109,131],"able":[111],"determine":[113],"whether":[114],"correct":[118,143],"based":[119],"on":[120],"observations":[121],"RL":[124,159],"curve.":[126],"results":[128],"suggest":[129],"that":[130],"improves":[132],"quality":[134],"-":[138,148],"57.5%":[140],"65%":[142],"in":[144,163],"study":[147],"performs":[150],"more":[151],"reliably":[152],"than":[153],"baselines":[154],"by":[155],"matching":[156],"outperforming":[158],"all":[164],"tested":[165],"cases.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}