{"id":"https://openalex.org/W2889990052","doi":"https://doi.org/10.1109/icra.2018.8460854","title":"Active Reward Learning from Critiques","display_name":"Active Reward Learning from Critiques","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2889990052","doi":"https://doi.org/10.1109/icra.2018.8460854","mag":"2889990052"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2018.8460854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8460854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5070110088","display_name":"Yuchen Cui","orcid":"https://orcid.org/0000-0001-7417-1222"},"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":"Yuchen Cui","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin, Austin, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043572737","display_name":"Scott Niekum","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":"Scott Niekum","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin, Austin, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, Austin, TX","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":6.0824,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.97013695,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6907","last_page":"6914"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.7664922475814819},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7426058650016785},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.631942868232727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6127417683601379},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.48705771565437317},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4849836826324463},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44801753759384155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7664922475814819},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7426058650016785},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.631942868232727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6127417683601379},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.48705771565437317},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4849836826324463},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44801753759384155},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2018.8460854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8460854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W195533127","https://openalex.org/W1491541693","https://openalex.org/W1539975474","https://openalex.org/W1591675293","https://openalex.org/W1663973292","https://openalex.org/W1965555277","https://openalex.org/W1983801113","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2098774185","https://openalex.org/W2117481033","https://openalex.org/W2150879893","https://openalex.org/W2154633587","https://openalex.org/W2156163138","https://openalex.org/W2158582431","https://openalex.org/W2163037893","https://openalex.org/W2169498096","https://openalex.org/W2228499913","https://openalex.org/W2259002239","https://openalex.org/W2283935042","https://openalex.org/W2402734324","https://openalex.org/W2478027467","https://openalex.org/W2735318784","https://openalex.org/W2954040150","https://openalex.org/W4321392130","https://openalex.org/W6607976765","https://openalex.org/W6635261211","https://openalex.org/W6674884181","https://openalex.org/W6683119562","https://openalex.org/W6683921772","https://openalex.org/W6689138081","https://openalex.org/W6713168676"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4323768008","https://openalex.org/W1941703695","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W2768698792","https://openalex.org/W3132773133"],"abstract_inverted_index":{"Learning":[0],"from":[1],"demonstration":[2],"algorithms,":[3],"such":[4],"as":[5,79],"Inverse":[6],"Reinforcement":[7],"Learning,":[8],"aim":[9],"to":[10,27,45,70,84,135,148,165,168],"provide":[11],"a":[12,22,32,65,89,99,172],"natural":[13],"mechanism":[14],"for":[15,49,113,124],"programming":[16],"robots,":[17],"but":[18],"can":[19,62],"often":[20],"require":[21,64],"prohibitive":[23],"number":[24,67],"of":[25,31,68,117],"demonstrations":[26,38,125],"capture":[28],"important":[29],"subtleties":[30],"task.":[33],"Rather":[34],"than":[35,122],"requesting":[36],"additional":[37],"blindly,":[39],"active":[40,102],"learning":[41,106],"methods":[42],"leverage":[43],"uncertainty":[44,73],"query":[46],"the":[47,111,137,145,150],"user":[48,112],"action":[50,127],"labels":[51,69],"at":[52],"states":[53],"with":[54],"high":[55],"expected":[56],"information":[57],"gain.":[58],"However,":[59],"this":[60],"approach":[61],"still":[63],"large":[66],"adequately":[71],"reduce":[72],"and":[74,142,171],"may":[75],"also":[76],"be":[77],"unintuitive,":[78],"users":[80],"are":[81],"not":[82],"accustomed":[83],"determining":[85],"optimal":[86],"actions":[87],"in":[88,160],"single":[90],"out-of-context":[91],"state.":[92],"To":[93],"address":[94],"these":[95],"shortcomings,":[96],"we":[97],"propose":[98],"novel":[100],"trajectory-based":[101],"Bayesian":[103],"inverse":[104],"reinforcement":[105],"algorithm":[107,159],"that":[108],"(1)":[109],"queries":[110],"<i":[114,131],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[115,132],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">critiques</i>":[116],"automatically":[118],"generated":[119],"trajectories,":[120],"rather":[121],"asking":[123],"or":[126],"labels,":[128],"(2)":[129],"utilizes":[130],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">trajectory":[133],"segmentation</i>":[134],"expedite":[136],"critique":[138],"/":[139],"labeling":[140],"process,":[141],"(3)":[143],"predicts":[144],"user's":[146],"critiques":[147],"generate":[149],"most":[151],"highly":[152],"informative":[153],"trajectory":[154],"queries.":[155],"We":[156],"evaluated":[157],"our":[158],"simulated":[161],"domains,":[162],"finding":[163],"it":[164],"compare":[166],"favorably":[167],"prior":[169],"work":[170],"randomized":[173],"baseline.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}