{"id":"https://openalex.org/W2962849870","doi":"https://doi.org/10.1109/hri.2019.8673234","title":"The Assistive Multi-Armed Bandit","display_name":"The Assistive Multi-Armed Bandit","publication_year":2019,"publication_date":"2019-03-01","ids":{"openalex":"https://openalex.org/W2962849870","doi":"https://doi.org/10.1109/hri.2019.8673234","mag":"2962849870"},"language":"en","primary_location":{"id":"doi:10.1109/hri.2019.8673234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hri.2019.8673234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","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/A5030763743","display_name":"Lawrence S. Chan","orcid":"https://orcid.org/0009-0007-0640-980X"},"institutions":[{"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lawrence Chan","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076757561","display_name":"Dylan Hadfield-Menell","orcid":"https://orcid.org/0000-0002-6168-4763"},"institutions":[{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dylan Hadfield-Menell","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077719529","display_name":"Siddhartha S Srinivasa","orcid":"https://orcid.org/0000-0002-5091-106X"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhartha Srinivasa","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005997281","display_name":"Anca D. Dragan","orcid":"https://orcid.org/0000-0001-6312-5466"},"institutions":[{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anca Dragan","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030763743"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":4.5235,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.94703483,"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":"354","last_page":"363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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/T11182","display_name":"Auction Theory and Applications","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7524455785751343},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.7166165709495544},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7063459157943726},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.682533860206604},{"id":"https://openalex.org/keywords/isolation","display_name":"Isolation (microbiology)","score":0.6230326890945435},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5943859219551086},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.5729743242263794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4998147487640381},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49735501408576965},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4732164442539215},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2451697289943695},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09713089466094971}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7524455785751343},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.7166165709495544},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7063459157943726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.682533860206604},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.6230326890945435},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5943859219551086},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.5729743242263794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4998147487640381},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49735501408576965},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4732164442539215},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2451697289943695},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09713089466094971},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C89423630","wikidata":"https://www.wikidata.org/wiki/Q7193","display_name":"Microbiology","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hri.2019.8673234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hri.2019.8673234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","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":65,"referenced_works":["https://openalex.org/W37428858","https://openalex.org/W187005120","https://openalex.org/W630739203","https://openalex.org/W1191599655","https://openalex.org/W1532688806","https://openalex.org/W1596763386","https://openalex.org/W1604268452","https://openalex.org/W1629317078","https://openalex.org/W1815076433","https://openalex.org/W1965035964","https://openalex.org/W1970916399","https://openalex.org/W1998498767","https://openalex.org/W1999874108","https://openalex.org/W2000080679","https://openalex.org/W2009551863","https://openalex.org/W2024390895","https://openalex.org/W2031571562","https://openalex.org/W2039522160","https://openalex.org/W2051296598","https://openalex.org/W2056760934","https://openalex.org/W2061562262","https://openalex.org/W2076337359","https://openalex.org/W2077148472","https://openalex.org/W2098258765","https://openalex.org/W2112420033","https://openalex.org/W2121284223","https://openalex.org/W2124029832","https://openalex.org/W2132876566","https://openalex.org/W2139622428","https://openalex.org/W2150339816","https://openalex.org/W2155027007","https://openalex.org/W2157477959","https://openalex.org/W2165628115","https://openalex.org/W2168359464","https://openalex.org/W2171084228","https://openalex.org/W2182000050","https://openalex.org/W2284050935","https://openalex.org/W2328283485","https://openalex.org/W2395937008","https://openalex.org/W2565370028","https://openalex.org/W2736601468","https://openalex.org/W2792089292","https://openalex.org/W2794190393","https://openalex.org/W2912748147","https://openalex.org/W2963436662","https://openalex.org/W2963685250","https://openalex.org/W2964199361","https://openalex.org/W3100329718","https://openalex.org/W3125634603","https://openalex.org/W4234228486","https://openalex.org/W4237910115","https://openalex.org/W4243534649","https://openalex.org/W4249575823","https://openalex.org/W4255827778","https://openalex.org/W4293405734","https://openalex.org/W6631864160","https://openalex.org/W6638545294","https://openalex.org/W6674868663","https://openalex.org/W6678106187","https://openalex.org/W6680020174","https://openalex.org/W6683204974","https://openalex.org/W6683608605","https://openalex.org/W6684973485","https://openalex.org/W6686227676","https://openalex.org/W6695676441"],"related_works":["https://openalex.org/W2398102130","https://openalex.org/W3213722473","https://openalex.org/W2110944602","https://openalex.org/W4287179229","https://openalex.org/W3205513966","https://openalex.org/W3120459843","https://openalex.org/W4366547574","https://openalex.org/W3200191727","https://openalex.org/W2245294024","https://openalex.org/W2963660546"],"abstract_inverted_index":{"Learning":[0],"preferences":[1],"implicit":[2],"in":[3,13,122,129],"the":[4,23,54,75,80,88,94,100,105,120,141,156],"choices":[5],"humans":[6,26],"make":[7],"is":[8],"a":[9,59,62,65,143,173],"well":[10],"studied":[11],"problem":[12],"both":[14],"economics":[15],"and":[16,114],"computer":[17],"science.":[18],"However,":[19],"most":[20],"work":[21,169],"makes":[22],"assumption":[24],"that":[25,162],"are":[27,42],"acting":[28],"(noisily)":[29],"optimally":[30],"with":[31,108],"respect":[32],"to":[33,68,135,155],"their":[34],"preferences.":[35],"Such":[36],"approaches":[37],"can":[38,84,146],"fail":[39],"when":[40,138],"people":[41],"themselves":[43],"learning":[44],"about":[45],"what":[46],"they":[47],"want.":[48],"In":[49,72],"this":[50,73,123,168],"work,":[51],"we":[52],"introduce":[53],"assistive":[55],"multi-armed":[56],"bandit,":[57],"where":[58],"robot":[60,95],"assists":[61],"human":[63,76,101,121,127,144],"playing":[64],"bandit":[66],"task":[67],"maximize":[69],"cumulative":[70],"reward.":[71],"problem,":[74],"does":[77,131],"not":[78,104,132],"know":[79],"reward":[81,106],"function":[82],"but":[83,103],"learn":[85],"it":[86],"through":[87],"rewards":[89,154],"received":[90],"from":[91],"arm":[92],"pulls;":[93],"only":[96],"observes":[97],"which":[98],"arms":[99],"pulls":[102],"associated":[107],"each":[109],"pull.":[110],"We":[111,158,166],"offer":[112],"sufficient":[113],"necessary":[115],"conditions":[116],"for":[117,177],"successfully":[118],"assisting":[119],"framework.":[124],"Surprisingly,":[125],"better":[126,136,148],"performance":[128,137],"isolation":[130],"necessarily":[133],"lead":[134],"assisted":[139],"by":[140,149],"robot:":[142],"policy":[145],"do":[147],"effectively":[150],"communicating":[151],"its":[152],"observed":[153],"robot.":[157],"conduct":[159],"proof-of-concept":[160],"experiments":[161],"support":[163],"these":[164],"results.":[165],"see":[167],"as":[170],"contributing":[171],"towards":[172],"theory":[174],"behind":[175],"algorithms":[176],"human-robot":[178],"interaction.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}
