{"id":"https://openalex.org/W4383108778","doi":"https://doi.org/10.1109/icra48891.2023.10161261","title":"Aligning Human Preferences with Baseline Objectives in Reinforcement Learning","display_name":"Aligning Human Preferences with Baseline Objectives in Reinforcement Learning","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108778","doi":"https://doi.org/10.1109/icra48891.2023.10161261"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161261","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://kth.diva-portal.org/smash/get/diva2:1744884/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,11428","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,11428","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,11428","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,11428","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,11428","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,11428","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,11428","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,11428","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,11428","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,11428","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":2.2269,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90150565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7562","last_page":"7568"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9147999882698059,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9083999991416931,"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/baseline","display_name":"Baseline (sea)","score":0.8457143902778625},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7498757839202881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6663227081298828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4328828752040863},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42913079261779785},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32790955901145935},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3249247074127197},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13983386754989624},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05971077084541321}],"concepts":[{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.8457143902778625},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7498757839202881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6663227081298828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4328828752040863},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42913079261779785},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32790955901145935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3249247074127197},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13983386754989624},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05971077084541321},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra48891.2023.10161261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161261","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"},{"id":"pmh:oai:DiVA.org:kth-324924","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-324924","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1744884/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-324924","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-324924","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1744884/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":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"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"},{"id":"https://openalex.org/G455710082","display_name":null,"funder_award_id":"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"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4383108778.pdf"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1999874108","https://openalex.org/W2098774185","https://openalex.org/W2148961728","https://openalex.org/W2167052694","https://openalex.org/W2462906003","https://openalex.org/W2604216058","https://openalex.org/W2735318784","https://openalex.org/W2736601468","https://openalex.org/W2762221702","https://openalex.org/W2889987506","https://openalex.org/W2902143777","https://openalex.org/W2903838810","https://openalex.org/W2962759351","https://openalex.org/W2962889474","https://openalex.org/W2963391602","https://openalex.org/W2963544079","https://openalex.org/W2963864421","https://openalex.org/W2964177756","https://openalex.org/W2972981152","https://openalex.org/W2986748798","https://openalex.org/W3006334608","https://openalex.org/W3023096123","https://openalex.org/W3024539867","https://openalex.org/W3032881759","https://openalex.org/W3035644784","https://openalex.org/W3044290186","https://openalex.org/W3091272913","https://openalex.org/W3135252453","https://openalex.org/W3170197122","https://openalex.org/W3170555463","https://openalex.org/W3192145739","https://openalex.org/W3195433024","https://openalex.org/W3199438654","https://openalex.org/W3210994662","https://openalex.org/W3213330367","https://openalex.org/W4225346712","https://openalex.org/W4287122174","https://openalex.org/W4287266177","https://openalex.org/W4287708441","https://openalex.org/W4289288058","https://openalex.org/W4295264289","https://openalex.org/W4300110528","https://openalex.org/W4321392130","https://openalex.org/W6638018090","https://openalex.org/W6674884181","https://openalex.org/W6684921986","https://openalex.org/W6718836005","https://openalex.org/W6732417791","https://openalex.org/W6738860160","https://openalex.org/W6739585900","https://openalex.org/W6741002519","https://openalex.org/W6748210908","https://openalex.org/W6752013740","https://openalex.org/W6753960536","https://openalex.org/W6756714161","https://openalex.org/W6767425681","https://openalex.org/W6768749362","https://openalex.org/W6770555722","https://openalex.org/W6771598146","https://openalex.org/W6777159553","https://openalex.org/W6781014336","https://openalex.org/W6784131548","https://openalex.org/W6796168157","https://openalex.org/W6796274626","https://openalex.org/W6796487486","https://openalex.org/W6799308143","https://openalex.org/W6800349239","https://openalex.org/W6800875786","https://openalex.org/W6803162731","https://openalex.org/W6803928713"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2380820513","https://openalex.org/W2920061524","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239"],"abstract_inverted_index":{"Practical":[0],"implementations":[1],"of":[2,15,32,47,53,94,122],"deep":[3],"reinforcement":[4],"learning":[5],"(deep":[6],"RL)":[7],"have":[8],"been":[9],"challenging":[10],"due":[11],"to":[12,38,64,71,133,154,162],"an":[13,110],"amplitude":[14],"factors,":[16],"such":[17],"as":[18],"designing":[19],"reward":[20,34,56,131],"functions":[21],"that":[22,138],"cover":[23],"every":[24],"possible":[25],"interaction.":[26],"To":[27,87],"address":[28],"the":[29,45,74,85,92],"heavy":[30],"burden":[31],"robot":[33],"engineering,":[35],"we":[36,68,149,160],"aim":[37],"leverage":[39],"subjective":[40],"human":[41,79,140,157],"preferences":[42],"gathered":[43],"in":[44],"context":[46],"human-robot":[48],"interaction,":[49],"while":[50],"taking":[51],"advantage":[52],"a":[54,100,114,130,151,164,167],"baseline":[55,62,115],"function":[57],"when":[58,81],"available.":[59],"By":[60],"considering":[61],"objectives":[63],"be":[65],"designed":[66],"beforehand,":[67],"are":[69,126],"able":[70],"narrow":[72],"down":[73],"policy":[75,112,165],"space,":[76],"solely":[77],"requesting":[78],"attention":[80],"their":[82],"input":[83],"matters":[84],"most.":[86],"allow":[88],"for":[89],"control":[90],"over":[91],"optimization":[93],"different":[95],"objectives,":[96],"our":[97],"approach":[98,144],"contemplates":[99],"multi-objective":[101],"setting.":[102],"We":[103],"achieve":[104],"human-compliant":[105],"policies":[106,125,137],"by":[107,128],"sequentially":[108],"training":[109,129],"optimal":[111,136],"from":[113],"specification":[116],"and":[117,148],"collecting":[118],"queries":[119],"on":[120,166],"pairs":[121],"trajectories.":[123],"These":[124],"obtained":[127],"estimator":[132],"generate":[134],"Pareto":[135],"include":[139],"preferred":[141],"behaviours.":[142],"Our":[143],"ensures":[145],"sample":[146],"efficiency":[147],"conducted":[150],"user":[152],"study":[153],"collect":[155],"real":[156],"preferences,":[158],"which":[159],"utilized":[161],"obtain":[163],"social":[168],"navigation":[169],"environment.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}