{"id":"https://openalex.org/W4388458590","doi":"https://doi.org/10.1177/02783649231208729","title":"Active preference-based Gaussian process regression for reward learning and optimization","display_name":"Active preference-based Gaussian process regression for reward learning and optimization","publication_year":2023,"publication_date":"2023-11-07","ids":{"openalex":"https://openalex.org/W4388458590","doi":"https://doi.org/10.1177/02783649231208729"},"language":"en","primary_location":{"id":"doi:10.1177/02783649231208729","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649231208729","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/02783649231208729?download=true","source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://journals.sagepub.com/doi/pdf/10.1177/02783649231208729?download=true","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031426401","display_name":"Erdem B\u0131y\u0131k","orcid":"https://orcid.org/0000-0002-9516-3130"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Erdem B\u0131y\u0131k","raw_affiliation_strings":["Center for Human-Compatible Artificial Intelligence, UC Berkeley, Berkeley, CA, USA","Department of Electrical Engineering, Stanford University, Stanford, CA, USA","Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9516-3130","affiliations":[{"raw_affiliation_string":"Center for Human-Compatible Artificial Intelligence, UC Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109681954","display_name":"Nicolas Huynh","orcid":null},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["FR","GB"],"is_corresponding":false,"raw_author_name":"Nicolas Huynh","raw_affiliation_strings":["Department of Applied Mathematics, \u00c9cole Polytechnique, Palaiseau, France","Department of Computer Science and Technology, University of Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, \u00c9cole Polytechnique, Palaiseau, France","institution_ids":["https://openalex.org/I142476485"]},{"raw_affiliation_string":"Department of Computer Science and Technology, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068326377","display_name":"Mykel J. Kochenderfer","orcid":"https://orcid.org/0000-0002-7238-9663"},"institutions":[{"id":"https://openalex.org/I13805885","display_name":"Vaughn College of Aeronautics and Technology","ror":"https://ror.org/056e22e24","country_code":"US","type":"education","lineage":["https://openalex.org/I13805885"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mykel J. Kochenderfer","raw_affiliation_strings":["Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I13805885","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080725225","display_name":"Dorsa Sadigh","orcid":"https://orcid.org/0000-0002-7802-9183"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dorsa Sadigh","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, CA, USA","Department of Electrical Engineering, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5031426401"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I95457486","https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":4.2829,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.95205384,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"43","issue":"5","first_page":"665","last_page":"684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9904999732971191,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9904999732971191,"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":0.9776999950408936,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9674000144004822,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/computer-science","display_name":"Computer science","score":0.6878478527069092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6766411662101746},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5801857113838196},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5285165309906006},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5173761248588562},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.502511739730835},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5011227130889893},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49640756845474243},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4843350648880005},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.48084983229637146},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4678509831428528},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.46034765243530273},{"id":"https://openalex.org/keywords/kriging","display_name":"Kriging","score":0.4420260488986969},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43619304895401},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.2419126033782959},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1504111886024475},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10773167014122009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6878478527069092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6766411662101746},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5801857113838196},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5285165309906006},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5173761248588562},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.502511739730835},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5011227130889893},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49640756845474243},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4843350648880005},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.48084983229637146},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4678509831428528},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.46034765243530273},{"id":"https://openalex.org/C81692654","wikidata":"https://www.wikidata.org/wiki/Q225926","display_name":"Kriging","level":2,"score":0.4420260488986969},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43619304895401},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2419126033782959},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1504111886024475},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10773167014122009},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/02783649231208729","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649231208729","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/02783649231208729?download=true","source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1177/02783649231208729","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649231208729","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/02783649231208729?download=true","source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3169313910","display_name":null,"funder_award_id":"#1941722","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3989609131","display_name":null,"funder_award_id":"#2218760","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6022427645","display_name":"CAREER: Safe and Influencing Interactions for Human-Robot Systems","funder_award_id":"1941722","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8977957641","display_name":"Collaborative Research: CPS: Small: Risk-Aware Planning and Control for Safety-Critical Human-CPS","funder_award_id":"2218760","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388458590.pdf","grobid_xml":"https://content.openalex.org/works/W4388458590.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W174941419","https://openalex.org/W187005120","https://openalex.org/W1155403144","https://openalex.org/W1583953806","https://openalex.org/W1937188251","https://openalex.org/W1965520710","https://openalex.org/W1980969546","https://openalex.org/W1996625075","https://openalex.org/W1999874108","https://openalex.org/W2110074961","https://openalex.org/W2140539195","https://openalex.org/W2158782408","https://openalex.org/W2185657542","https://openalex.org/W2302703641","https://openalex.org/W2735318784","https://openalex.org/W2754351509","https://openalex.org/W2792089292","https://openalex.org/W2913737986","https://openalex.org/W2925362180","https://openalex.org/W2933663337","https://openalex.org/W2963725546","https://openalex.org/W2964177756","https://openalex.org/W3000508506","https://openalex.org/W3004361447","https://openalex.org/W3023698287","https://openalex.org/W3039563104","https://openalex.org/W3090359064","https://openalex.org/W3091627088","https://openalex.org/W3101338847","https://openalex.org/W3129827477","https://openalex.org/W3130335129","https://openalex.org/W3196191018","https://openalex.org/W3197594072","https://openalex.org/W4211049957","https://openalex.org/W4212774754","https://openalex.org/W4220972421","https://openalex.org/W4242073862","https://openalex.org/W4283788970","https://openalex.org/W4383108621"],"related_works":["https://openalex.org/W1968523686","https://openalex.org/W566010457","https://openalex.org/W2600092203","https://openalex.org/W4300066510","https://openalex.org/W2056958800","https://openalex.org/W2803685231","https://openalex.org/W4293503520","https://openalex.org/W3134152097","https://openalex.org/W4311388919","https://openalex.org/W2966696655"],"abstract_inverted_index":{"Designing":[0],"reward":[1,37,58,74,102,137,148,191,211,235,246,249],"functions":[2,38,59,75,236],"is":[3,34,45,85,120,196],"a":[4,21,113,142,152,176,204,225],"difficult":[5,86],"task":[6,13],"in":[7,63,121,185,203,219,244],"AI":[8],"and":[9,150,172,224,240,248],"robotics.":[10],"The":[11],"complex":[12],"of":[14,67,81,97,124,208],"directly":[15],"specifying":[16],"all":[17],"the":[18,122,136,147,158,194,199,210,242],"desirable":[19],"behaviors":[20],"robot":[22,201],"needs":[23],"to":[24,35,89,145,155,168,187,197],"optimize":[25],"often":[26],"proves":[27],"challenging":[28],"for":[29,56,87,104,213,237],"humans.":[30],"A":[31],"popular":[32],"solution":[33],"learn":[36,233],"using":[39,160],"expert":[40],"demonstrations.":[41],"This":[42],"approach,":[43,116],"however,":[44],"fraught":[46],"with":[47,94],"many":[48],"challenges.":[49],"Some":[50],"methods":[51],"require":[52],"heavily":[53],"structured":[54,73],"models,":[55],"example,":[57],"that":[60,76],"are":[61],"linear":[62],"some":[64],"predefined":[65],"set":[66],"features,":[68],"while":[69],"others":[70],"adopt":[71],"less":[72],"may":[77],"necessitate":[78],"tremendous":[79],"amounts":[80],"data.":[82],"Moreover,":[83],"it":[84],"humans":[88],"provide":[90],"demonstrations":[91],"on":[92,135,190],"robots":[93],"high":[95],"degrees":[96],"freedom,":[98],"or":[99],"even":[100],"quantifying":[101],"values":[103],"given":[105],"trajectories.":[106,127],"To":[107],"address":[108],"these":[109],"challenges,":[110],"we":[111,140],"present":[112],"preference-based":[114,177],"learning":[115,178,209,247],"where":[117,193],"human":[118,162],"feedback":[119],"form":[123],"comparisons":[125],"between":[126],"We":[128,180],"do":[129],"not":[130],"assume":[131],"highly":[132],"constrained":[133],"structures":[134],"function.":[138],"Instead,":[139],"employ":[141],"Gaussian":[143],"process":[144],"model":[146,159],"function":[149,212],"propose":[151],"mathematical":[153],"formulation":[154],"actively":[156],"fit":[157],"only":[161],"preferences.":[163],"Our":[164,217],"approach":[165,230],"enables":[166],"us":[167],"tackle":[169],"both":[170,245],"inflexibility":[171],"data-inefficiency":[173],"problems":[174],"within":[175],"framework.":[179],"further":[181],"analyze":[182],"our":[183,229],"algorithm":[184],"comparison":[186],"several":[188],"baselines":[189,243],"optimization,":[192],"goal":[195],"find":[198],"optimal":[200],"trajectory":[202],"data-efficient":[205],"way":[206],"instead":[207],"every":[214],"possible":[215],"trajectory.":[216],"results":[218],"three":[220],"different":[221],"simulation":[222],"experiments":[223],"user":[226],"study":[227],"show":[228],"can":[231],"efficiently":[232],"expressive":[234],"robotic":[238],"tasks,":[239],"outperform":[241],"optimization.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}