{"id":"https://openalex.org/W2766155949","doi":"https://doi.org/10.1007/s10994-019-05784-4","title":"Good arm identification via bandit feedback","display_name":"Good arm identification via bandit feedback","publication_year":2019,"publication_date":"2019-03-06","ids":{"openalex":"https://openalex.org/W2766155949","doi":"https://doi.org/10.1007/s10994-019-05784-4","mag":"2766155949"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-019-05784-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05784-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05784-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05784-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014287499","display_name":"Hideaki Kano","orcid":"https://orcid.org/0000-0003-3682-7627"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hideaki Kano","raw_affiliation_strings":["RIKEN, Tokyo, Japan","University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210110652"]},{"raw_affiliation_string":"University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112464181","display_name":"Junya Honda","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junya Honda","raw_affiliation_strings":["RIKEN, Tokyo, Japan","University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210110652"]},{"raw_affiliation_string":"University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066841617","display_name":"Kentaro Sakamaki","orcid":"https://orcid.org/0000-0002-4443-9993"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kentaro Sakamaki","raw_affiliation_strings":["University of Tokyo, Tokyo, Japan","University of Tokyo,    Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"University of Tokyo,    Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102786576","display_name":"Kentaro Matsuura","orcid":"https://orcid.org/0000-0001-5262-055X"},"institutions":[{"id":"https://openalex.org/I4210113259","display_name":"Johnson Controls (Japan)","ror":"https://ror.org/026jg0516","country_code":"JP","type":"company","lineage":["https://openalex.org/I142262071","https://openalex.org/I4210113259"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kentaro Matsuura","raw_affiliation_strings":["Johnson & Johnson, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Johnson & Johnson, Tokyo, Japan","institution_ids":["https://openalex.org/I4210113259"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067632149","display_name":"Atsuyoshi Nakamura","orcid":"https://orcid.org/0000-0001-7078-8655"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsuyoshi Nakamura","raw_affiliation_strings":["Hokkaido University, Sapporo, Japan"],"affiliations":[{"raw_affiliation_string":"Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072744508","display_name":"Masashi Sugiyama","orcid":"https://orcid.org/0000-0001-6658-6743"},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Sugiyama","raw_affiliation_strings":["RIKEN, Tokyo, Japan","University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210110652"]},{"raw_affiliation_string":"University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5014287499"],"corresponding_institution_ids":["https://openalex.org/I4210110652","https://openalex.org/I74801974"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.2063,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55467882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"108","issue":"5","first_page":"721","last_page":"745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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":1.0,"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":0.9975000023841858,"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/sample-complexity","display_name":"Sample complexity","score":0.7512543201446533},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.7101112604141235},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6687985062599182},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5487882494926453},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5293242335319519},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.46534264087677},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46022137999534607},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4539371430873871},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.451055645942688},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3881869316101074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3062252998352051}],"concepts":[{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.7512543201446533},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.7101112604141235},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6687985062599182},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5487882494926453},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5293242335319519},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.46534264087677},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46022137999534607},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4539371430873871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.451055645942688},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3881869316101074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3062252998352051},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10994-019-05784-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05784-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05784-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1710.06360","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.06360","pdf_url":"https://arxiv.org/pdf/1710.06360","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2766155949","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1710.06360.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1710.06360","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1710.06360","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s10994-019-05784-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05784-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05784-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2792802287","display_name":null,"funder_award_id":"KAKENHI","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G3282004645","display_name":null,"funder_award_id":"JPMJCR","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G3538458246","display_name":null,"funder_award_id":"17H00757","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4616974242","display_name":null,"funder_award_id":"JPMJCR1662","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G5824517811","display_name":null,"funder_award_id":"KAKENHI 16H00881","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8941621529","display_name":null,"funder_award_id":"KAKENHI 17H00757","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2766155949.pdf","grobid_xml":"https://content.openalex.org/works/W2766155949.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1504908594","https://openalex.org/W1506859583","https://openalex.org/W1515851193","https://openalex.org/W1531859564","https://openalex.org/W1858303725","https://openalex.org/W1911551976","https://openalex.org/W1969525589","https://openalex.org/W1990344145","https://openalex.org/W2009551863","https://openalex.org/W2029530218","https://openalex.org/W2029604041","https://openalex.org/W2077148472","https://openalex.org/W2131168761","https://openalex.org/W2137209912","https://openalex.org/W2147967768","https://openalex.org/W2159788225","https://openalex.org/W2168405694","https://openalex.org/W2168810201","https://openalex.org/W2404446105","https://openalex.org/W2418983643","https://openalex.org/W2606318404","https://openalex.org/W2762290718","https://openalex.org/W2949186496"],"related_works":["https://openalex.org/W2921489523","https://openalex.org/W3038036515","https://openalex.org/W3035109066","https://openalex.org/W2604946918","https://openalex.org/W3037351657","https://openalex.org/W2618731134","https://openalex.org/W2126559945","https://openalex.org/W3043459363","https://openalex.org/W3099255161","https://openalex.org/W3103945479","https://openalex.org/W3037952574","https://openalex.org/W3169893105","https://openalex.org/W3175597316","https://openalex.org/W1858303725","https://openalex.org/W2946950117","https://openalex.org/W2231190415","https://openalex.org/W3159979150","https://openalex.org/W3033539533","https://openalex.org/W2783292962","https://openalex.org/W3172241543"],"abstract_inverted_index":{"Abstract":[0],"We":[1,84,128,175,188],"consider":[2],"a":[3,15,31,36,41,45,58,89,109,130,204],"novel":[4],"stochastic":[5],"multi-armed":[6],"bandit":[7,206],"problem":[8,38,207],"called":[9],"good":[10,16,59],"arm":[11,17,22,50,106,126],"identification":[12],"(GAI),":[13],"where":[14],"is":[18,35,55,74,101,118,140],"defined":[19],"as":[20,51,53,57],"an":[21,49,111,178],"with":[23],"expected":[24],"reward":[25],"greater":[26],"than":[27],"or":[28],"equal":[29],"to":[30,75,143],"given":[32],"threshold.":[33],"GAI":[34,73,87,117,138],"pure-exploration":[37],"in":[39,199],"which":[40,100],"single":[42],"agent":[43],"repeats":[44],"process":[46],"of":[47,72,79,92,97,114,137],"outputting":[48],"soon":[52],"it":[54],"identified":[56],"one":[60],"before":[61],"confirming":[62],"the":[63,77,94,104,124,134,144,185],"other":[64],"arms":[65],"are":[66],"actually":[67],"not":[68],"good.":[69],"The":[70],"objective":[71],"minimize":[76],"number":[78],"samples":[80],"for":[81,116,123,164,212],"each":[82],"process.":[83],"find":[85],"that":[86,122,139,192],"faces":[88],"new":[90],"kind":[91],"dilemma,":[93],"exploration-exploitation":[95],"dilemma":[96],"confidence":[98],",":[99],"different":[102,120],"from":[103,121],"best":[105,125],"identification.":[107,127],"As":[108],"result,":[110],"efficient":[112],"design":[113],"algorithms":[115,198],"quite":[119],"derive":[129],"lower":[131,186],"bound":[132],"on":[133,203],"sample":[135,181],"complexity":[136,182],"tight":[141],"up":[142],"logarithmic":[145],"factor":[146],"$$\\mathrm":[147],"{O}(\\log":[148],"\\frac{1}{\\delta":[149],"})$$":[150],"<mml:math":[151,170],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[152,171],"<mml:mrow>":[153],"<mml:mi>O</mml:mi>":[154],"<mml:mo>(</mml:mo>":[155],"<mml:mo>log</mml:mo>":[156],"<mml:mfrac>":[157],"<mml:mn>1</mml:mn>":[158],"<mml:mi>\u03b4</mml:mi>":[159,172],"</mml:mfrac>":[160],"<mml:mo>)</mml:mo>":[161],"</mml:mrow>":[162],"</mml:math>":[163,173],"acceptance":[165],"error":[166],"rate":[167],"$$\\delta":[168],"$$":[169],".":[174],"also":[176,189],"develop":[177],"algorithm":[179,195],"whose":[180],"almost":[183],"matches":[184],"bound.":[187],"confirm":[190],"experimentally":[191],"our":[193],"proposed":[194],"outperforms":[196],"naive":[197],"synthetic":[200],"settings":[201],"based":[202],"conventional":[205],"and":[208],"clinical":[209],"trial":[210],"researches":[211],"rheumatoid":[213],"arthritis.":[214]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}