{"id":"https://openalex.org/W4389667165","doi":"https://doi.org/10.1109/iros55552.2023.10341795","title":"VARIQuery: VAE Segment-Based Active Learning for Query Selection in Preference-Based Reinforcement Learning","display_name":"VARIQuery: VAE Segment-Based Active Learning for Query Selection in Preference-Based Reinforcement Learning","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389667165","doi":"https://doi.org/10.1109/iros55552.2023.10341795"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://kth.diva-portal.org/smash/get/diva2:1787953/FULLTEXT01","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084998580","display_name":"Daniel Marta","orcid":"https://orcid.org/0000-0002-3510-5481"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]},{"id":"https://openalex.org/I4210100930","display_name":"Futures Group (United States)","ror":"https://ror.org/0169taq91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210100930"]}],"countries":["SE","US"],"is_corresponding":true,"raw_author_name":"Daniel Marta","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Stockholm,Sweden,114 28","Digital Futures"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Stockholm,Sweden,114 28","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Digital Futures","institution_ids":["https://openalex.org/I4210100930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056430836","display_name":"Simon Holk","orcid":"https://orcid.org/0000-0001-5727-8140"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]},{"id":"https://openalex.org/I4210100930","display_name":"Futures Group (United States)","ror":"https://ror.org/0169taq91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210100930"]}],"countries":["SE","US"],"is_corresponding":false,"raw_author_name":"Simon Holk","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Stockholm,Sweden,114 28","Digital Futures"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Stockholm,Sweden,114 28","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Digital Futures","institution_ids":["https://openalex.org/I4210100930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005479279","display_name":"Christian Pek","orcid":"https://orcid.org/0000-0001-7461-920X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]},{"id":"https://openalex.org/I4210100930","display_name":"Futures Group (United States)","ror":"https://ror.org/0169taq91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210100930"]}],"countries":["SE","US"],"is_corresponding":false,"raw_author_name":"Christian Pek","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Stockholm,Sweden,114 28","Digital Futures"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Stockholm,Sweden,114 28","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Digital Futures","institution_ids":["https://openalex.org/I4210100930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042698317","display_name":"Jana T\u016fmov\u00e1","orcid":"https://orcid.org/0000-0003-4173-2593"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]},{"id":"https://openalex.org/I4210100930","display_name":"Futures Group (United States)","ror":"https://ror.org/0169taq91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210100930"]}],"countries":["SE","US"],"is_corresponding":false,"raw_author_name":"Jana Tumova","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Stockholm,Sweden,114 28","Digital Futures"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Stockholm,Sweden,114 28","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Digital Futures","institution_ids":["https://openalex.org/I4210100930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082559019","display_name":"Iolanda Leite","orcid":"https://orcid.org/0000-0002-2212-4325"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]},{"id":"https://openalex.org/I4210100930","display_name":"Futures Group (United States)","ror":"https://ror.org/0169taq91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210100930"]}],"countries":["SE","US"],"is_corresponding":false,"raw_author_name":"Iolanda Leite","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Stockholm,Sweden,114 28","Digital Futures"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology,Division of Robotics, Perception and Learning,Stockholm,Sweden,114 28","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Digital Futures","institution_ids":["https://openalex.org/I4210100930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5084998580"],"corresponding_institution_ids":["https://openalex.org/I4210100930","https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":2.0846,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89885803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7878","last_page":"7885"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998999834060669,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9969000220298767,"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/T12288","display_name":"Optimization and Search Problems","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8314851522445679},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8101765513420105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6745011806488037},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.6313785314559937},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6170228123664856},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6042208075523376},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5833250284194946},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5009102821350098},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.49001967906951904},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.436667799949646},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4113270044326782},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2643921375274658}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8314851522445679},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101765513420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6745011806488037},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.6313785314559937},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6170228123664856},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6042208075523376},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5833250284194946},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5009102821350098},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.49001967906951904},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.436667799949646},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4113270044326782},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2643921375274658},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros55552.2023.10341795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:kth-333948","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-333948","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1787953/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-333948","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-333948","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1787953/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3793158386","display_name":null,"funder_award_id":"SSF FFL18-0199","funder_id":"https://openalex.org/F4320320940","funder_display_name":"Stiftelsen f\u00f6r\u00a0Strategisk Forskning"}],"funders":[{"id":"https://openalex.org/F4320320940","display_name":"Stiftelsen f\u00f6r\u00a0Strategisk Forskning","ror":"https://ror.org/044wr7g58"},{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320322509","display_name":"Kungliga Tekniska H\u00f6gskolan","ror":"https://ror.org/026vcq606"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389667165.pdf","grobid_xml":"https://content.openalex.org/works/W4389667165.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W122021961","https://openalex.org/W1580375566","https://openalex.org/W1583953806","https://openalex.org/W1672197616","https://openalex.org/W1837766154","https://openalex.org/W1968200975","https://openalex.org/W1978633512","https://openalex.org/W2012210378","https://openalex.org/W2080021732","https://openalex.org/W2124244761","https://openalex.org/W2154023516","https://openalex.org/W2262342046","https://openalex.org/W2596585349","https://openalex.org/W2604272474","https://openalex.org/W2612690371","https://openalex.org/W2735318784","https://openalex.org/W2736601468","https://openalex.org/W2772303887","https://openalex.org/W2788686132","https://openalex.org/W2789833952","https://openalex.org/W2901639336","https://openalex.org/W2910982074","https://openalex.org/W2948978827","https://openalex.org/W2956371155","https://openalex.org/W2966048335","https://openalex.org/W2986514296","https://openalex.org/W2986748798","https://openalex.org/W2990138404","https://openalex.org/W2999905431","https://openalex.org/W3006334608","https://openalex.org/W3039563104","https://openalex.org/W3179550234","https://openalex.org/W3197594072","https://openalex.org/W3205626500","https://openalex.org/W3213330367","https://openalex.org/W4287122174","https://openalex.org/W4310922000","https://openalex.org/W6677285668","https://openalex.org/W6679227803","https://openalex.org/W6679716015","https://openalex.org/W6681769951","https://openalex.org/W6696346101","https://openalex.org/W6732417791","https://openalex.org/W6739585900","https://openalex.org/W6741002519","https://openalex.org/W6748034479","https://openalex.org/W6748210908","https://openalex.org/W6753221106","https://openalex.org/W6753960536","https://openalex.org/W6758233323","https://openalex.org/W6770555722","https://openalex.org/W6770824211","https://openalex.org/W6780559895","https://openalex.org/W6791194670","https://openalex.org/W6796168157","https://openalex.org/W6843699536","https://openalex.org/W6847353123"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2011676020","https://openalex.org/W2329895846"],"abstract_inverted_index":{"Human-in-the-loop":[0],"reinforcement":[1],"learning":[2,78],"(RL)":[3],"methods":[4,125],"actively":[5],"integrate":[6],"human":[7,48,61,166,174],"knowledge":[8],"to":[9,76,119,132,147,155,173],"create":[10],"reward":[11,112],"functions":[12],"for":[13],"various":[14],"robotic":[15],"tasks.":[16],"Learning":[17],"from":[18],"preferences":[19],"shows":[20],"promise":[21],"as":[22,55],"alleviates":[23],"the":[24,35,66,120,157],"requirement":[25],"of":[26,38,47,69,93,159],"demonstrations":[27],"by":[28],"querying":[29,49],"humans":[30],"on":[31,52,143],"state-action":[32],"sequences.":[33,95],"However,":[34],"limited":[36],"granularity":[37],"sequence-based":[39],"approaches":[40],"complicates":[41],"temporal":[42],"credit":[43],"assignment.":[44],"The":[45],"amount":[46],"is":[50,73],"contingent":[51],"query":[53,70,84,123,161],"quality,":[54],"redundant":[56],"queries":[57,101],"result":[58],"in":[59,105,126],"excessive":[60],"involvement.":[62],"This":[63],"paper":[64],"addresses":[65],"often-overlooked":[67],"aspect":[68],"selection,":[71],"which":[72],"closely":[74],"related":[75,172],"active":[77],"(AL).":[79],"We":[80,115],"propose":[81],"a":[82],"novel":[83],"selection":[85,124,162],"approach":[86,118,163],"that":[87,102],"leverages":[88],"variational":[89],"autoencoder":[90],"(VAE)":[91],"representations":[92],"state":[94],"In":[96],"this":[97],"manner,":[98],"we":[99,150],"formulate":[100],"are":[103],"diverse":[104],"nature":[106],"while":[107],"simultaneously":[108],"taking":[109],"into":[110],"account":[111],"model":[113],"estimations.":[114],"compare":[116],"our":[117,160],"current":[121],"state-of-the-art":[122],"preference-based":[127],"RL,":[128],"and":[129,168],"find":[130],"ours":[131],"be":[133],"either":[134],"on-par":[135],"or":[136],"more":[137],"sample":[138],"efficient":[139],"through":[140],"extensive":[141],"benchmarking":[142],"simulated":[144],"environments":[145],"relevant":[146],"robotics.":[148],"Lastly,":[149],"conduct":[151],"an":[152],"online":[153],"study":[154],"verify":[156],"effectiveness":[158],"with":[164],"real":[165],"feedback":[167],"examine":[169],"several":[170],"metrics":[171],"effort.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}