{"id":"https://openalex.org/W2962748815","doi":"https://doi.org/10.1109/jstsp.2013.2263494","title":"Deterministic Sequencing of Exploration and Exploitation for Multi-Armed Bandit Problems","display_name":"Deterministic Sequencing of Exploration and Exploitation for Multi-Armed Bandit Problems","publication_year":2013,"publication_date":"2013-05-16","ids":{"openalex":"https://openalex.org/W2962748815","doi":"https://doi.org/10.1109/jstsp.2013.2263494","mag":"2962748815"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2013.2263494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2013.2263494","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5009337709","display_name":"Sattar Vakili","orcid":"https://orcid.org/0000-0001-7085-1191"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sattar Vakili","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Davis, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007144865","display_name":"Keqin Liu","orcid":"https://orcid.org/0000-0002-7995-7125"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keqin Liu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Davis, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013788255","display_name":"Qing Zhao","orcid":"https://orcid.org/0000-0002-9590-4285"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Zhao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Davis, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009337709"],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":6.8294,"has_fulltext":false,"cited_by_count":94,"citation_normalized_percentile":{"value":0.96967535,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"7","issue":"5","first_page":"759","last_page":"767"},"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":0.9979000091552734,"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":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8545610904693604},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.7038196921348572},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.6301336288452148},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.5246696472167969},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5207386016845703},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5183447599411011},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.4777492880821228},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4624721109867096},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4544641375541687},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4208727180957794},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4078008532524109},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.38823041319847107},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35734498500823975},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.11898627877235413},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11230102181434631},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08984255790710449},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07853776216506958}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8545610904693604},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.7038196921348572},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.6301336288452148},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.5246696472167969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5207386016845703},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5183447599411011},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.4777492880821228},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4624721109867096},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4544641375541687},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4208727180957794},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4078008532524109},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.38823041319847107},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35734498500823975},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.11898627877235413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11230102181434631},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08984255790710449},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07853776216506958},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2013.2263494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2013.2263494","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1845959409","display_name":null,"funder_award_id":"W911NF-12-1-0271","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8998121839","display_name":null,"funder_award_id":"911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W32448098","https://openalex.org/W131745075","https://openalex.org/W1751431909","https://openalex.org/W1950398167","https://openalex.org/W1980829002","https://openalex.org/W1998498767","https://openalex.org/W2000080679","https://openalex.org/W2009551863","https://openalex.org/W2010189695","https://openalex.org/W2012731843","https://openalex.org/W2015056750","https://openalex.org/W2019923980","https://openalex.org/W2038586864","https://openalex.org/W2041205077","https://openalex.org/W2049689520","https://openalex.org/W2093562354","https://openalex.org/W2103012681","https://openalex.org/W2132418266","https://openalex.org/W2140571193","https://openalex.org/W2150328967","https://openalex.org/W2168405694","https://openalex.org/W2169926276","https://openalex.org/W2400672140","https://openalex.org/W2555652361","https://openalex.org/W2614055648","https://openalex.org/W2950381540","https://openalex.org/W2962764550","https://openalex.org/W3100779200","https://openalex.org/W3102381603","https://openalex.org/W3103604572","https://openalex.org/W4233413206","https://openalex.org/W6640542924","https://openalex.org/W6654532046","https://openalex.org/W6712545651"],"related_works":["https://openalex.org/W2947263763","https://openalex.org/W4288373430","https://openalex.org/W4287753704","https://openalex.org/W3036260055","https://openalex.org/W3158925485","https://openalex.org/W2996735312","https://openalex.org/W4287273005","https://openalex.org/W3135784370","https://openalex.org/W4289341771","https://openalex.org/W2776473626"],"abstract_inverted_index":{"In":[0],"the":[1,30,71,76,83,89,109,112,118,133,144,150,181,184,230,233,238],"Multi-Armed":[2],"Bandit":[3],"(MAB)":[4],"problem,":[5],"there":[6],"is":[7,52,61,80,187],"a":[8,20,35,44,140,174],"given":[9],"set":[10,240],"of":[11,37,47,75,111,135,143,180,192],"arms":[12,220],"with":[13,92,173,196,201,212,218],"unknown":[14,213,243],"reward":[15,33,67,86,94,98,113,146,170,206],"models.":[16,95],"At":[17],"each":[18],"time,":[19],"player":[21],"selects":[22],"one":[23],"arm":[24,57],"to":[25,28,117,190],"play,":[26],"aiming":[27],"maximize":[29],"total":[31,84],"expected":[32,85],"over":[34],"horizon":[36],"length":[38],"T.":[39],"An":[40],"approach":[41,158,186],"based":[42],"on":[43,139,162],"Deterministic":[45],"Sequencing":[46],"Exploration":[48],"and":[49,122,204,215,237],"Exploitation":[50],"(DSEE)":[51],"developed":[53],"for":[54,64,121,128,168],"constructing":[55],"sequential":[56],"selection":[58],"policies.":[59],"It":[60],"shown":[62],"that":[63,221],"all":[65],"light-tailed":[66],"distributions,":[68,99,147],"DSEE":[69,100,148,157,185],"achieves":[70,101],"optimal":[72,151],"logarithmic":[73,152],"order":[74,120],"regret,":[77],"where":[78],"regret":[79,107,153],"defined":[81,176],"as":[82,229],"loss":[87],"against":[88],"ideal":[90],"case":[91],"known":[93],"For":[96],"heavy-tailed":[97,145],"O(T":[102,123],"<sup":[103,124],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[104,125],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1/p</sup>":[105],")":[106,127],"when":[108],"moments":[110],"distributions":[114],"exist":[115],"up":[116],"pth":[119],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1/(1+p/2)</sup>":[126],"p":[129],">":[130],"2.":[131],"With":[132],"knowledge":[134],"an":[136],"upper":[137],"bound":[138],"finite":[141],"moment":[142],"offers":[149],"order.":[154],"The":[155],"proposed":[156],"complements":[159],"existing":[160],"work":[161],"MAB":[163,195,200,211,217],"by":[164],"providing":[165],"corresponding":[166],"results":[167],"general":[169],"distributions.":[171],"Furthermore,":[172],"clearly":[175],"tunable":[177],"parameter-the":[178],"cardinality":[179],"exploration":[182],"sequence,":[183],"easily":[188],"extendable":[189],"variations":[191],"MAB,":[193],"including":[194],"various":[197],"objectives,":[198],"decentralized":[199],"multiple":[202],"players":[203],"incomplete":[205],"observations":[207],"under":[208,242],"collisions,":[209],"restless":[210],"dynamics,":[214],"combinatorial":[216],"dependent":[219],"often":[222],"arise":[223],"in":[224],"network":[225],"optimization":[226],"problems":[227,241],"such":[228],"shortest":[231],"path,":[232],"minimum":[234],"spanning":[235],"tree,":[236],"dominating":[239],"random":[244],"weights.":[245]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}