{"id":"https://openalex.org/W7134805772","doi":"https://doi.org/10.1145/3757279.3785630","title":"Learning Human Preferences over a Human-Robot Collaboration Based on Explicit and Implicit Human Feedback","display_name":"Learning Human Preferences over a Human-Robot Collaboration Based on Explicit and Implicit Human Feedback","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134805772","doi":"https://doi.org/10.1145/3757279.3785630"},"language":null,"primary_location":{"id":"doi:10.1145/3757279.3785630","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757279.3785630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","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/A5062054967","display_name":"Kate Candon","orcid":"https://orcid.org/0000-0002-0152-053X"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kate Candon","raw_affiliation_strings":["Yale University, New Haven, USA"],"raw_orcid":"https://orcid.org/0000-0002-0152-053X","affiliations":[{"raw_affiliation_string":"Yale University, New Haven, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128646100","display_name":"Qiping Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiping Zhang","raw_affiliation_strings":["Yale University, New Haven, USA"],"raw_orcid":"https://orcid.org/0000-0002-8535-2771","affiliations":[{"raw_affiliation_string":"Yale University, New Haven, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Alexander Lew","orcid":"https://orcid.org/0009-0008-8557-3348"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Lew","raw_affiliation_strings":["Yale University, New Haven, USA"],"raw_orcid":"https://orcid.org/0009-0008-8557-3348","affiliations":[{"raw_affiliation_string":"Yale University, New Haven, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046765947","display_name":"Houston Claure","orcid":"https://orcid.org/0000-0002-6292-4706"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Houston Claure","raw_affiliation_strings":["Yale University, New Haven, USA"],"raw_orcid":"https://orcid.org/0000-0002-6292-4706","affiliations":[{"raw_affiliation_string":"Yale University, New Haven, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084978057","display_name":"Lena Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lena Qian","raw_affiliation_strings":["Yale University, New Haven, USA"],"raw_orcid":"https://orcid.org/0009-0001-9753-154X","affiliations":[{"raw_affiliation_string":"Yale University, New Haven, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128661889","display_name":"Alyssa Quarles","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alyssa Quarles","raw_affiliation_strings":["Yale University, New Haven, USA"],"raw_orcid":"https://orcid.org/0009-0000-3060-1745","affiliations":[{"raw_affiliation_string":"Yale University, New Haven, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128665202","display_name":"Chayan Sarkar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chayan Sarkar","raw_affiliation_strings":["TCS Research, New Delhi, India"],"raw_orcid":"https://orcid.org/0000-0003-4777-2086","affiliations":[{"raw_affiliation_string":"TCS Research, New Delhi, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041256504","display_name":"Marynel V\u00e1zquez","orcid":"https://orcid.org/0000-0003-0698-5472"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marynel V\u00e1zquez","raw_affiliation_strings":["Yale University, New Haven, USA"],"raw_orcid":"https://orcid.org/0000-0003-0698-5472","affiliations":[{"raw_affiliation_string":"Yale University, New Haven, USA","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5062054967"],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":null,"apc_paid":null,"fwci":35.3865,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.99406735,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1040","last_page":"1049"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2721000015735626,"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":0.2721000015735626,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.2590000033378601,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.13259999454021454,"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/control","display_name":"Control (management)","score":0.3813000023365021},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.2992999851703644},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.28760001063346863},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.27709999680519104},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.25929999351501465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5199000239372253},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3610999882221222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3427000045776367},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30880001187324524},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2858999967575073},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.27959999442100525},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757279.3785630","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757279.3785630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8864109547","display_name":null,"funder_award_id":"IIS-2143109","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"},{"id":"https://openalex.org/F4320313903","display_name":"Tata Consultancy Services","ror":"https://ror.org/01b9n8m42"},{"id":"https://openalex.org/F4320325807","display_name":"Tata Sons","ror":"https://ror.org/000628g58"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2084777029","https://openalex.org/W2121110499","https://openalex.org/W2143427281","https://openalex.org/W2148962857","https://openalex.org/W2151516755","https://openalex.org/W2156869222","https://openalex.org/W2604382266","https://openalex.org/W2794663059","https://openalex.org/W2796864868","https://openalex.org/W2803451925","https://openalex.org/W2945173102","https://openalex.org/W2964132611","https://openalex.org/W2993247505","https://openalex.org/W3039519178","https://openalex.org/W3142599250","https://openalex.org/W3145123113","https://openalex.org/W3187113103","https://openalex.org/W3208223622","https://openalex.org/W4224270712","https://openalex.org/W4312772252","https://openalex.org/W4323870627","https://openalex.org/W4323870917","https://openalex.org/W4383213708","https://openalex.org/W4392633415","https://openalex.org/W4393117285","https://openalex.org/W4408023869"],"related_works":[],"abstract_inverted_index":{"There":[0],"is":[1,28,55],"significant":[2],"interest":[3],"in":[4,37,133,174,180,211],"enabling":[5,221],"robots":[6,222],"to":[7,9,29,32,70,85,120,154,199,223,225],"learn":[8],"perform":[10],"tasks":[11],"directly":[12],"from":[13,63,124,168],"interactions":[14],"with":[15,45,149,177,206],"non-expert":[16],"users.":[17],"Typically,":[18],"a":[19,23,33,90,94,181,196,207,217,226,238,243],"human":[20,42,87,108,152,193,201],"serves":[21],"as":[22,93,136],"teacher":[24],"whose":[25],"only":[26],"task":[27,47,135],"provide":[30],"feedback":[31,62,123,148,153,172,194],"robot":[34,73,115],"learner.":[35],"However,":[36],"real-world":[38,212],"human-robot":[39,91],"collaborations,":[40],"the":[41,46,64,68,72,77,130,134,140,157,204,234],"often":[43],"assists":[44],"while":[48],"also":[49],"offering":[50],"feedback.":[51],"Our":[52,184],"key":[53],"insight":[54],"that":[56,106,112,138,188],"we":[57,82,144],"can":[58],"extract":[59,121],"additional,":[60],"implicit":[61,122,147],"human\u2019s":[65,131,141,158],"actions":[66,132,137],"during":[67],"collaboration":[69,92],"augment":[71],"learning":[74,167],"process.":[75],"Under":[76],"assumption":[78],"of":[79,97,192,236],"fixed-role":[80],"assignments,":[81],"first":[83],"propose":[84],"formalize":[86],"preferences":[88,202],"over":[89,203],"shared":[95],"set":[96],"parameters":[98],"encoding":[99],"alignment":[100],"between":[101],"two":[102],"reward":[103],"functions:":[104],"one":[105],"drives":[107],"behavior,":[109],"and":[110,170,176],"another":[111],"should":[113],"direct":[114],"behavior.":[116],"This":[117],"allows":[118],"us":[119],"an":[125],"interaction":[126],"by":[127],"reasoning":[128],"about":[129],"reveal":[139],"preferences.":[142,159],"Then,":[143],"combine":[145],"this":[146],"traditional":[150],"explicit":[151],"facilitate":[155],"estimating":[156],"We":[160],"evaluated":[161],"our":[162],"proposed":[163],"approach":[164],"for":[165,220],"Preference":[166],"Implicit":[169],"Explicit":[171],"(PIE)":[173],"simulations":[175],"real":[178],"users":[179],"cooking":[182],"scenario.":[183],"simulation":[185],"results":[186],"indicate":[187],"combining":[189],"multiple":[190],"modalities":[191],"improves":[195],"robot\u2019s":[197],"ability":[198],"estimate":[200],"collaboration,":[205],"similar":[208],"trend":[209],"observed":[210],"evaluations.":[213],"These":[214],"findings":[215],"highlight":[216],"promising":[218],"direction":[219],"adapt":[224],"user\u2019s":[227],"preference":[228],"model":[229],"more":[230],"quickly,":[231],"thereby":[232],"reducing":[233],"amount":[235],"time":[237],"person":[239],"must":[240],"spend":[241],"teaching":[242],"robot.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-24T08:23:43.765630","created_date":"2026-03-11T00:00:00"}