{"id":"https://openalex.org/W2131958277","doi":"https://doi.org/10.1007/s10994-011-5257-4","title":"An asymptotically optimal policy for finite support models in the multiarmed bandit problem","display_name":"An asymptotically optimal policy for finite support models in the multiarmed bandit problem","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W2131958277","doi":"https://doi.org/10.1007/s10994-011-5257-4","mag":"2131958277"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-011-5257-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-011-5257-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-011-5257-4.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-011-5257-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Junya Honda","raw_affiliation_strings":["Graduate School of Frontier Sciences, The University of Tokyo, Kashiwa-shi Chiba, 277\u20138561, Japan","Graduate School of Frontier Sciences, The University of Tokyo, Kashiwa-shi, Chiba, Japan 277-8561"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences, The University of Tokyo, Kashiwa-shi Chiba, 277\u20138561, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Frontier Sciences, The University of Tokyo, Kashiwa-shi, Chiba, Japan 277-8561","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025039029","display_name":"Akimichi Takemura","orcid":"https://orcid.org/0000-0002-5216-4969"},"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":"Akimichi Takemura","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku Tokyo, 113-8656, Japan","Graduate School of Information Science and Technology, The University of Tokyo Bunkyo-ku,Tokyo,Japan,113-8656"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku Tokyo, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo Bunkyo-ku,Tokyo,Japan,113-8656","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112464181"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":2.5397,"has_fulltext":true,"cited_by_count":86,"citation_normalized_percentile":{"value":0.89816776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"85","issue":"3","first_page":"361","last_page":"391"},"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":0.9976000189781189,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/regret","display_name":"Regret","score":0.8676775097846985},{"id":"https://openalex.org/keywords/asymptotically-optimal-algorithm","display_name":"Asymptotically optimal algorithm","score":0.7723487615585327},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.6679624915122986},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6374350786209106},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6032395362854004},{"id":"https://openalex.org/keywords/finite-set","display_name":"Finite set","score":0.5616832375526428},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.541753351688385},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4851182699203491},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.47437459230422974},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46350187063217163},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22575414180755615},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13257816433906555}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8676775097846985},{"id":"https://openalex.org/C181789720","wikidata":"https://www.wikidata.org/wiki/Q4812191","display_name":"Asymptotically optimal algorithm","level":2,"score":0.7723487615585327},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.6679624915122986},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6374350786209106},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6032395362854004},{"id":"https://openalex.org/C162392398","wikidata":"https://www.wikidata.org/wiki/Q272404","display_name":"Finite set","level":2,"score":0.5616832375526428},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.541753351688385},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4851182699203491},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.47437459230422974},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46350187063217163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22575414180755615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13257816433906555},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10994-011-5257-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-011-5257-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-011-5257-4.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.250.4573","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.250.4573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/0905.2776v1.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/s10994-011-5257-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-011-5257-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-011-5257-4.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2131958277.pdf","grobid_xml":"https://content.openalex.org/works/W2131958277.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1510812122","https://openalex.org/W1515933446","https://openalex.org/W1516061453","https://openalex.org/W1572204513","https://openalex.org/W1582436621","https://openalex.org/W1583882820","https://openalex.org/W1699297496","https://openalex.org/W1861050369","https://openalex.org/W1970097186","https://openalex.org/W1977823770","https://openalex.org/W1983962754","https://openalex.org/W1994325510","https://openalex.org/W1998498767","https://openalex.org/W2000080679","https://openalex.org/W2009551863","https://openalex.org/W2010029425","https://openalex.org/W2010189695","https://openalex.org/W2059120410","https://openalex.org/W2077902449","https://openalex.org/W2097487180","https://openalex.org/W2099111195","https://openalex.org/W2118309135","https://openalex.org/W2168405694","https://openalex.org/W2296319761","https://openalex.org/W2317700292","https://openalex.org/W2478708596","https://openalex.org/W4250589301","https://openalex.org/W4292025355","https://openalex.org/W6634907821","https://openalex.org/W6724046077"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2101991911","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2155070487","https://openalex.org/W4292701710","https://openalex.org/W2102931639","https://openalex.org/W2131958277"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":55},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}