{"id":"https://openalex.org/W2950929549","doi":"https://doi.org/10.1561/2200000024","title":"Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems","display_name":"Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems","publication_year":2012,"publication_date":"2012-12-12","ids":{"openalex":"https://openalex.org/W2950929549","doi":"https://doi.org/10.1561/2200000024","mag":"2950929549"},"language":"en","primary_location":{"id":"doi:10.1561/2200000024","is_oa":false,"landing_page_url":"https://doi.org/10.1561/2200000024","pdf_url":null,"source":{"id":"https://openalex.org/S4210188176","display_name":"Foundations and Trends\u00ae in Machine Learning","issn_l":"1935-8237","issn":["1935-8237","1935-8245"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318575","host_organization_name":"Now Publishers","host_organization_lineage":["https://openalex.org/P4310318575"],"host_organization_lineage_names":["Now Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations and Trends\u00ae in Machine Learning","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/A5021842384","display_name":"S\u00e9bastien Bubeck","orcid":"https://orcid.org/0000-0001-9122-4410"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"S\u00e9bastien Bubeck","raw_affiliation_strings":["Department of Operations Research and Financial Engineering, Princeton University , Princeton, 08544,","Department of Operations Research and Financial Engineering, Princeton University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Operations Research and Financial Engineering, Princeton University , Princeton, 08544,","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Department of Operations Research and Financial Engineering, Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":null,"display_name":"Nicol\u00f2 Cesa-Bianchi","orcid":null},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicol\u00f2 Cesa-Bianchi","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 degli Studi di Milano , Milano 20135,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Milano , Milano 20135,","institution_ids":["https://openalex.org/I189158943"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021842384"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":40.139,"has_fulltext":false,"cited_by_count":1234,"citation_normalized_percentile":{"value":0.99900818,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"5","issue":"1","first_page":"1","last_page":"122"},"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/T12288","display_name":"Optimization and Search Problems","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8996948003768921},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4644278287887573},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.38906678557395935},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3258397579193115},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.2518751323223114},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11864331364631653}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8996948003768921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4644278287887573},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.38906678557395935},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3258397579193115},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2518751323223114},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11864331364631653}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1561/2200000024","is_oa":false,"landing_page_url":"https://doi.org/10.1561/2200000024","pdf_url":null,"source":{"id":"https://openalex.org/S4210188176","display_name":"Foundations and Trends\u00ae in Machine Learning","issn_l":"1935-8237","issn":["1935-8237","1935-8245"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318575","host_organization_name":"Now Publishers","host_organization_lineage":["https://openalex.org/P4310318575"],"host_organization_lineage_names":["Now Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations and Trends\u00ae in Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.749.8362","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.749.8362","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/1204.5721.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1595135966","https://openalex.org/W2119738618","https://openalex.org/W2406356034","https://openalex.org/W2952454753"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","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/W4311589891","https://openalex.org/W3123835761"],"abstract_inverted_index":{"Multi-armed":[0],"bandit":[1,48,74,133],"problems":[2,11,49],"are":[3],"the":[4,18,23,30,42,45,53,78,96,111,123,131],"most":[5,124],"basic":[6,112],"examples":[7],"of":[8,47,98,114,122],"sequential":[9],"decision":[10],"with":[12,22,82],"an":[13],"exploration\u2013exploitation":[14,55],"trade-off.":[15],"This":[16],"is":[17,75,100],"balance":[19],"between":[20],"staying":[21],"option":[24],"that":[25,36],"gave":[26],"highest":[27],"payoffs":[28,40,79,106],"in":[29,41,58,94],"past":[31],"and":[32,68,103,107,127],"exploring":[33],"new":[34],"options":[35],"might":[37],"give":[38],"higher":[39],"future.":[43],"Although":[44],"study":[46],"dates":[50],"back":[51],"to":[52],"1930s,":[54],"trade-offs":[56],"arise":[57],"several":[59],"modern":[60],"applications,":[61],"such":[62,129],"as":[63,130],"ad":[64],"placement,":[65],"website":[66],"optimization,":[67],"packet":[69],"routing.":[70],"Mathematically,":[71],"a":[72],"multi-armed":[73],"defined":[76],"by":[77],"process":[80],"associated":[81],"each":[83],"option.":[84],"In":[85],"this":[86],"monograph,":[87],"we":[88,118],"focus":[89],"on":[90],"two":[91],"extreme":[92],"cases":[93],"which":[95],"analysis":[97],"regret":[99],"particularly":[101],"simple":[102],"elegant:":[104],"i.i.d.":[105],"adversarial":[108],"payoffs.":[109],"Besides":[110],"setting":[113],"finitely":[115],"many":[116],"actions,":[117],"also":[119],"analyze":[120],"some":[121],"important":[125],"variants":[126],"extensions,":[128],"contextual":[132],"model.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":30},{"year":2025,"cited_by_count":85},{"year":2024,"cited_by_count":89},{"year":2023,"cited_by_count":128},{"year":2022,"cited_by_count":126},{"year":2021,"cited_by_count":126},{"year":2020,"cited_by_count":167},{"year":2019,"cited_by_count":118},{"year":2018,"cited_by_count":103},{"year":2017,"cited_by_count":83},{"year":2016,"cited_by_count":71},{"year":2015,"cited_by_count":52},{"year":2014,"cited_by_count":39},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}