{"id":"https://openalex.org/W3035083041","doi":"https://doi.org/10.48550/arxiv.2007.00953","title":"Gamification of Pure Exploration for Linear Bandits","display_name":"Gamification of Pure Exploration for Linear Bandits","publication_year":2020,"publication_date":"2020-07-02","ids":{"openalex":"https://openalex.org/W3035083041","doi":"https://doi.org/10.48550/arxiv.2007.00953","mag":"3035083041"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2007.00953","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.00953","pdf_url":"https://arxiv.org/pdf/2007.00953","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.00953","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050128377","display_name":"R\u00e9my Degenne","orcid":"https://orcid.org/0000-0003-4622-4184","observed_orcids":["https://orcid.org/0000-0003-4622-4184"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Degenne, R\u00e9my","raw_affiliation_strings":["INRIA -DIENS -PSL Research Uni- versity , Paris , France","Statistical Machine Learning and Parsimony"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA -DIENS -PSL Research Uni- versity , Paris , France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I2746051580"]},{"raw_affiliation_string":"Statistical Machine Learning and Parsimony","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037297959","display_name":"Pierre M\u00e9nard","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M\u00e9nard, Pierre","raw_affiliation_strings":["Scool","Sequential Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scool","institution_ids":[]},{"raw_affiliation_string":"Sequential Learning","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010187634","display_name":"Xuedong Shang","orcid":"https://orcid.org/0000-0002-1537-6540","observed_orcids":["https://orcid.org/0000-0002-1537-6540"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Shang, Xuedong","raw_affiliation_strings":["INRIA - Universit\u00e9 de Lille","Scool","Sequential Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA - Universit\u00e9 de Lille","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I2279609970"]},{"raw_affiliation_string":"Scool","institution_ids":[]},{"raw_affiliation_string":"Sequential Learning","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106038276","display_name":"Michal Valko","orcid":"https://orcid.org/0009-0009-2673-0144","observed_orcids":["https://orcid.org/0009-0009-2673-0144"]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Valko, Michal","raw_affiliation_strings":["DeepMind [Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind [Paris]","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.0,"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/T12288","display_name":"Optimization and Search Problems","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pure-exploration","display_name":"pure exploration","score":0.8059999942779541},{"id":"https://openalex.org/keywords/linear-bandits","display_name":"linear bandits","score":0.8830000162124634},{"id":"https://openalex.org/keywords/best-arm-identification","display_name":"best arm identification","score":0.9750000238418579},{"id":"https://openalex.org/keywords/asymptotic-optimality","display_name":"asymptotic optimality","score":0.8849999904632568},{"id":"https://openalex.org/keywords/g-optimality","display_name":"G-optimality","score":0.9869999885559082},{"id":"https://openalex.org/keywords/optimal-experimental-design","display_name":"optimal experimental design","score":0.9829999804496765},{"id":"https://openalex.org/keywords/bandit-algorithms","display_name":"bandit algorithms","score":0.47999998927116394},{"id":"https://openalex.org/keywords/exploration-exploitation-trade-off","display_name":"exploration-exploitation balance","score":0.5490000247955322}],"concepts":[{"id":"https://openalex.org/C181789720","wikidata":"https://www.wikidata.org/wiki/Q4812191","display_name":"Asymptotically optimal algorithm","level":2,"score":0.7371162176132202},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.643728494644165},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6397492289543152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6336008906364441},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5876314043998718},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5161920189857483},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3991440534591675},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34860509634017944},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2007.00953","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.00953","pdf_url":"https://arxiv.org/pdf/2007.00953","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-02884330v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-02884330","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICML 2020 - International Conference on Machine Learning, Aug 2020, Vienna / Virtual, Austria","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/29571","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/29571","pdf_url":null,"source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'\u00c9tudes en Civilisations, Langues et Lettres \u00c9trang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"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":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2007.00953","doi":"https://doi.org/10.48550/arxiv.2007.00953","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.00953","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.00953","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.00953","pdf_url":"https://arxiv.org/pdf/2007.00953","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320322727","display_name":"Minist\u00e8re de l'Education Nationale, de l'Enseignement Superieur et de la Recherche","ror":"https://ror.org/03sjk9a61"},{"id":"https://openalex.org/F4320338463","display_name":"CHIST-ERA","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3035083041.pdf","grobid_xml":"https://content.openalex.org/works/W3035083041.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1553290137","https://openalex.org/W1861050369","https://openalex.org/W1872867087","https://openalex.org/W1967662298","https://openalex.org/W1998498767","https://openalex.org/W2038110713","https://openalex.org/W2064380440","https://openalex.org/W2085499762","https://openalex.org/W2106663919","https://openalex.org/W2112387288","https://openalex.org/W2119738618","https://openalex.org/W2126559945","https://openalex.org/W2126774211","https://openalex.org/W2136885855","https://openalex.org/W2156195892","https://openalex.org/W2170341113","https://openalex.org/W2283386448","https://openalex.org/W2404446105","https://openalex.org/W2487141439","https://openalex.org/W2495653770","https://openalex.org/W2535496140","https://openalex.org/W2932291267","https://openalex.org/W2946506451","https://openalex.org/W2946602788","https://openalex.org/W2951046238","https://openalex.org/W2954234600","https://openalex.org/W2962993780","https://openalex.org/W2963486287","https://openalex.org/W2970245210","https://openalex.org/W2986376518","https://openalex.org/W3035035035","https://openalex.org/W3147532007","https://openalex.org/W4232896127"],"related_works":["https://openalex.org/W2765335312","https://openalex.org/W4225624975","https://openalex.org/W3164612845","https://openalex.org/W7133213755","https://openalex.org/W3169358264","https://openalex.org/W3103081406","https://openalex.org/W2106663919","https://openalex.org/W4391912446","https://openalex.org/W4387560695","https://openalex.org/W3034887607"],"abstract_inverted_index":{"We":[0],"investigate":[1],"an":[2,127,133,137],"active":[3],"pure-exploration":[4],"setting,":[5],"that":[6,107,135],"includes":[7],"best-arm":[8,33],"identification,":[9],"in":[10,35,61,88],"the":[11,26,32,62,79,98,122],"context":[12],"of":[13,28,59],"linear":[14,36,63,89],"stochastic":[15],"bandits.":[16,90],"While":[17],"asymptotically":[18,81],"optimal":[19,70,82,128],"algorithms":[20,30,110],"exist":[21],"for":[22,31,84],"standard":[23],"multi-arm":[24],"bandits,":[25],"existence":[27],"such":[29],"identification":[34],"bandits":[37],"has":[38],"been":[39],"elusive":[40],"despite":[41],"several":[42],"attempts":[43],"to":[44,112,115,124],"address":[45],"it.":[46],"First,":[47],"we":[48,77,120],"provide":[49],"a":[50,92,102],"thorough":[51],"comparison":[52],"and":[53,73],"new":[54],"insight":[55],"over":[56],"different":[57],"notions":[58],"optimality":[60,68],"case,":[64],"including":[65],"G-optimality,":[66],"transductive":[67],"from":[69],"experimental":[71],"design":[72,78,129],"asymptotic":[74],"optimality.":[75],"Second,":[76],"first":[80],"algorithm":[83,95],"fixed-confidence":[85],"pure":[86],"exploration":[87],"As":[91],"consequence,":[93],"our":[94],"naturally":[96],"bypasses":[97],"pitfall":[99],"caused":[100],"by":[101,131],"simple":[103],"but":[104],"difficult":[105],"instance,":[106],"most":[108],"prior":[109],"had":[111],"be":[113],"engineered":[114],"deal":[116],"with":[117],"explicitly.":[118],"Finally,":[119],"avoid":[121],"need":[123],"fully":[125],"solve":[126],"problem":[130],"providing":[132],"approach":[134],"entails":[136],"efficient":[138],"implementation.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":6}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2020-06-19T00:00:00"}