{"id":"https://openalex.org/W3103898737","doi":"https://doi.org/10.1109/tro.2022.3192969","title":"Joint Estimation of Expertise and Reward Preferences From Human Demonstrations","display_name":"Joint Estimation of Expertise and Reward Preferences From Human Demonstrations","publication_year":2022,"publication_date":"2022-08-09","ids":{"openalex":"https://openalex.org/W3103898737","doi":"https://doi.org/10.1109/tro.2022.3192969","mag":"3103898737"},"language":"en","primary_location":{"id":"doi:10.1109/tro.2022.3192969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2022.3192969","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1546-1904","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"type":"article","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/A5015465808","display_name":"Pamela Carreno\u2010Medrano","orcid":"https://orcid.org/0000-0002-6026-0635"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Pamela Carreno-Medrano","raw_affiliation_strings":["Faculty of Engineering, Monash University, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6026-0635","affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Monash University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103134580","display_name":"Stephen L. Smith","orcid":"https://orcid.org/0000-0002-8636-407X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Stephen L. Smith","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Faculty of Engineering, University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8636-407X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Faculty of Engineering, University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072377971","display_name":"Dana Kuli\u0107","orcid":"https://orcid.org/0000-0002-4169-2141"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dana Kulic","raw_affiliation_strings":["Faculty of Engineering, Monash University, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4169-2141","affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Monash University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3936,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.64210065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"39","issue":"1","first_page":"681","last_page":"698"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9977999925613403,"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":0.9970999956130981,"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/inference","display_name":"Inference","score":0.7452055215835571},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7330330610275269},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7219645380973816},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6633278131484985},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.6305971741676331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6285274028778076},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.617158055305481},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5495674014091492},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5084332823753357},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4836467504501343},{"id":"https://openalex.org/keywords/human-behavior","display_name":"Human behavior","score":0.43274638056755066},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4225335121154785}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7452055215835571},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7330330610275269},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7219645380973816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6633278131484985},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.6305971741676331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6285274028778076},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.617158055305481},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5495674014091492},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5084332823753357},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4836467504501343},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.43274638056755066},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4225335121154785},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tro.2022.3192969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2022.3192969","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1546-1904","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1591675293","https://openalex.org/W1981276685","https://openalex.org/W1987626674","https://openalex.org/W2119493188","https://openalex.org/W2147544021","https://openalex.org/W2227909145","https://openalex.org/W2402734324","https://openalex.org/W2594103415","https://openalex.org/W2608332565","https://openalex.org/W2626804490","https://openalex.org/W2735318784","https://openalex.org/W2738190501","https://openalex.org/W2738895185","https://openalex.org/W2768059978","https://openalex.org/W2800727637","https://openalex.org/W2809461852","https://openalex.org/W2899771611","https://openalex.org/W2899850214","https://openalex.org/W2913737986","https://openalex.org/W2955071190","https://openalex.org/W2962937519","https://openalex.org/W2963106920","https://openalex.org/W2965140792","https://openalex.org/W2978644431","https://openalex.org/W2980094450","https://openalex.org/W2994446013","https://openalex.org/W3000711993","https://openalex.org/W3003858867","https://openalex.org/W3022169065","https://openalex.org/W3094558535","https://openalex.org/W3101314357","https://openalex.org/W3101754927","https://openalex.org/W3104160712","https://openalex.org/W3105729849","https://openalex.org/W3106171760","https://openalex.org/W3129827477","https://openalex.org/W3138984732","https://openalex.org/W3213466727","https://openalex.org/W4295312788","https://openalex.org/W4321392130","https://openalex.org/W6635261211","https://openalex.org/W6681478256","https://openalex.org/W6734517396","https://openalex.org/W6739585900","https://openalex.org/W6747473740","https://openalex.org/W6761908843","https://openalex.org/W6766978945","https://openalex.org/W6769196924","https://openalex.org/W6773844738","https://openalex.org/W6774122581","https://openalex.org/W6777078778","https://openalex.org/W6778229956","https://openalex.org/W6780562522","https://openalex.org/W6785883622","https://openalex.org/W6802868314","https://openalex.org/W6803526641"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W2787993192","https://openalex.org/W2158269427","https://openalex.org/W4381280689","https://openalex.org/W4379251913","https://openalex.org/W3205513966","https://openalex.org/W2052971528","https://openalex.org/W3120459843","https://openalex.org/W4366547574","https://openalex.org/W3200191727"],"abstract_inverted_index":{"When":[0],"a":[1,100,116,136,158],"robot":[2,26,35,51,93,174],"learns":[3,27],"from":[4,28,81],"human":[5,12,107,137,197],"examples,":[6],"most":[7],"approaches":[8,147,203],"assume":[9],"that":[10,33,192],"the":[11,25,34,41,62,89,92,106,128,132,151,170,173,177,185,189,195],"partner":[13,72],"provides":[14,67],"examples":[15],"of":[16,118,135,140,162,179],"optimal":[17],"behavior.":[18,198],"However,":[19],"there":[20],"are":[21,148],"applications":[22],"in":[23,205],"which":[24,65],"nonexpert":[29],"humans.":[30],"We":[31,199],"argue":[32],"should":[36],"learn":[37],"not":[38],"only":[39],"about":[40,46],"human's":[42,71,90,101],"objectives,":[43],"but":[44],"also":[45,95],"their":[47,141],"expertise":[48,129,167,190],"level.":[49],"The":[50],"could":[52],"then":[53],"leverage":[54],"this":[55,121],"joint":[56],"information":[57],"to":[58,69,98,109,115,125],"reduce":[59],"or":[60,73],"increase":[61],"frequency":[63],"at":[64],"it":[66],"assistance":[68],"its":[70],"be":[74,96],"more":[75],"cautious":[76],"when":[77,105],"learning":[78],"new":[79],"skills":[80],"novice":[82],"users.":[83],"Similarly,":[84],"by":[85],"taking":[86],"into":[87],"account":[88],"expertise,":[91],"would":[94],"able":[97],"infer":[99,127],"true":[102],"objectives":[103,113],"even":[104],"fails":[108],"properly":[110],"demonstrate":[111,200],"these":[112],"due":[114],"lack":[117],"expertise.":[119],"In":[120,150,169],"article,":[122],"we":[123],"propose":[124],"jointly":[126],"level":[130,191],"and":[131,166,183,188,207],"objective":[133,164,186],"function":[134,187],"given":[138],"observations":[139],"(possibly)":[142],"nonoptimal":[143],"demonstrations.":[144],"Two":[145],"inference":[146,154],"proposed.":[149],"first":[152],"approach,":[153,172],"is":[155],"done":[156],"over":[157,176],"finite":[159],"discrete":[160],"set":[161],"possible":[163,181],"functions":[165],"levels.":[168],"second":[171],"optimizes":[175],"space":[178],"all":[180],"hypotheses":[182],"finds":[184],"best":[193],"explain":[194],"observed":[196],"our":[201],"proposed":[202],"both":[204],"simulation":[206],"with":[208],"real":[209],"user":[210],"data.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}