{"id":"https://openalex.org/W2159209451","doi":"https://doi.org/10.1109/icmla.2008.67","title":"A Bayesian Learning Automaton for Solving Two-Armed Bernoulli Bandit Problems","display_name":"A Bayesian Learning Automaton for Solving Two-Armed Bernoulli Bandit Problems","publication_year":2008,"publication_date":"2008-12-01","ids":{"openalex":"https://openalex.org/W2159209451","doi":"https://doi.org/10.1109/icmla.2008.67","mag":"2159209451"},"language":"en","primary_location":{"id":"doi:10.1109/icmla.2008.67","doi":"https://doi.org/10.1109/icmla.2008.67","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla.2008.67","pdf_url":null,"source":{"id":"https://openalex.org/S4306419645","display_name":"International Conference on Machine Learning and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Seventh International Conference on Machine Learning and Applications","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5071922620","display_name":"Ole\u2010Christoffer Granmo","orcid":"https://orcid.org/0000-0002-7287-030X","observed_orcids":["https://orcid.org/0000-0002-7287-030X"]},"institutions":[{"id":"https://openalex.org/I200650556","display_name":"University of Agder","ror":"https://ror.org/03x297z98","country_code":"NO","type":"education","lineage":["https://openalex.org/I200650556"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Ole-Christoffer Granmo","raw_affiliation_strings":["Department of ICT, University of Agder, Grimstad, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of ICT, University of Agder, Grimstad, Norway","institution_ids":["https://openalex.org/I200650556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071922620"],"corresponding_institution_ids":["https://openalex.org/I200650556"],"apc_list":null,"apc_paid":null,"fwci":4.1784,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.94686361,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"30"},"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/learning-automata","display_name":"learning automata","score":0.8889999985694885},{"id":"https://openalex.org/keywords/exploration-exploitation-trade-off","display_name":"exploration-exploitation balance","score":0.8349999785423279},{"id":"https://openalex.org/keywords/regret-analysis","display_name":"regret analysis","score":0.5659999847412109},{"id":"https://openalex.org/keywords/sequential-decision-making","display_name":"sequential decision making","score":0.625}],"concepts":[{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.6977460384368896},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6960707306861877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6761027574539185},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.6731472015380859},{"id":"https://openalex.org/C2776807809","wikidata":"https://www.wikidata.org/wiki/Q6510160","display_name":"Learning automata","level":3,"score":0.6288380026817322},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6095863580703735},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5657312870025635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5273838043212891},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4524400234222412},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.4500765800476074},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.4203818440437317},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40780109167099},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.3887089192867279},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1856737732887268},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmla.2008.67","doi":"https://doi.org/10.1109/icmla.2008.67","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla.2008.67","pdf_url":null,"source":{"id":"https://openalex.org/S4306419645","display_name":"International Conference on Machine Learning and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Seventh International Conference on Machine Learning and Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W140232297","https://openalex.org/W1516020365","https://openalex.org/W1516061453","https://openalex.org/W1538558539","https://openalex.org/W1583882820","https://openalex.org/W1625390266","https://openalex.org/W1931792391","https://openalex.org/W2015061583","https://openalex.org/W2017334681","https://openalex.org/W2121863487","https://openalex.org/W2125930088","https://openalex.org/W2129358994","https://openalex.org/W2150365829","https://openalex.org/W2158832545","https://openalex.org/W2162964807","https://openalex.org/W2164636053","https://openalex.org/W2168405694","https://openalex.org/W2224879568","https://openalex.org/W2484003876","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W1602539399","https://openalex.org/W2030501831","https://openalex.org/W2491825702","https://openalex.org/W2478245965","https://openalex.org/W2470901141","https://openalex.org/W96734643","https://openalex.org/W2480658558","https://openalex.org/W2304696039","https://openalex.org/W2102933744","https://openalex.org/W2327828747"],"abstract_inverted_index":{"The":[0,36,110,140],"two-armed":[1],"Bernoulli":[2],"bandit":[3],"(TABB)":[4],"problem":[5,10,71],"is":[6,142,169],"a":[7,22,31,34,118,158,220,230],"classical":[8],"optimization":[9],"where":[11],"an":[12],"agent":[13],"sequentially":[14],"pulls":[15],"one":[16,46],"of":[17,39,160,222,233],"two":[18],"arms":[19],"attached":[20],"to":[21,127,173,188],"gambling":[23],"machine,":[24],"with":[25,74,179],"each":[26,40],"pull":[27],"resulting":[28],"either":[29],"in":[30,95,100,106,122,145,186,219],"reward":[32,37],"or":[33],"penalty.":[35],"probabilities":[38],"arm":[41,178],"are":[42],"unknown,":[43],"and":[44,56,83,103,153,171],"thus":[45,210],"must":[47],"balance":[48],"between":[49],"exploiting":[50],"existing":[51],"knowledge":[52],"about":[53],"the":[54,61,135,176,227],"arms,":[55],"obtaining":[57],"new":[58,231],"information.":[59],"In":[60],"last":[62],"decades,":[63],"several":[64],"computationally":[65,128],"efficient":[66],"algorithms":[67],"for":[68,80,87,216,229],"tackling":[69],"this":[70],"have":[72],"emerged,":[73],"learning":[75,137,197],"automata":[76],"(LA)":[77],"being":[78],"known":[79],"their":[81],"\u00bf-optimality,":[82],"confidence":[84,205],"interval":[85,206],"based":[86,207],"logarithmically":[88],"growing":[89],"regret.":[90],"Applications":[91],"include":[92],"treatment":[93],"selection":[94,99],"clinical":[96],"trials,":[97],"route":[98],"adaptive":[101],"routing,":[102],"plan":[104],"exploration":[105],"games":[107],"like":[108],"Go.":[109],"TABB":[111],"has":[112],"also":[113,201],"been":[114],"extensively":[115],"studied":[116],"from":[117,157],"Bayesian":[119,136,144],"perspective,":[120],"however,":[121],"general,":[123],"such":[124],"analysis":[125],"leads":[126],"inefficient":[129],"solution":[130],"policies.":[131],"This":[132],"paper":[133],"introduces":[134],"automaton":[138],"(BLA).":[139],"BLA":[141,168,191,213],"inherently":[143],"nature,":[146],"yet":[147],"relies":[148],"simply":[149],"on":[150,154,195],"counting":[151],"rewards/penalties":[152],"random":[155],"sampling":[156],"pair":[159],"twin":[161],"beta":[162],"distributions.":[163],"Furthermore,":[164],"we":[165],"report":[166],"that":[167,212,224],"self-correcting":[170],"converges":[172],"only":[174],"pulling":[175],"optimal":[177],"probability":[180],"1.":[181],"Extensive":[182],"experiments":[183],"demonstrate":[184],"that,":[185],"contrast":[187],"most":[189],"LA,":[190],"does":[192],"not":[193],"rely":[194],"external":[196],"speed/accuracy":[198],"control.":[199],"It":[200],"outperforms":[202],"recently":[203],"proposed":[204],"algorithms.":[208],"We":[209],"believe":[211],"opens":[214],"up":[215],"improved":[217],"performance":[218],"number":[221],"applications,and":[223],"it":[225],"forms":[226],"basis":[228],"avenue":[232],"research.":[234]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}