{"id":"https://openalex.org/W1861297722","doi":null,"title":"Continuous Time Associative Bandit Problems \u2217","display_name":"Continuous Time Associative Bandit Problems \u2217","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W1861297722","mag":"1861297722"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.420.4362","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.420.4362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://papersdb.cs.ualberta.ca/~papersdb/uploaded_files/632/paper_cbandit-ijcai07.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5041609088","display_name":"Andr\u00e1s Gy\u00f6rgy","orcid":"https://orcid.org/0000-0003-0586-4337","observed_orcids":["https://orcid.org/0000-0003-0586-4337"]},"institutions":[{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"government","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Andr\u00e1s Gy\u00f6rgy","raw_affiliation_strings":["Computer and Automation Research Institute of the Hungarian Academy of Sciences, Machine Learning Research Group#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer and Automation Research Institute of the Hungarian Academy of Sciences, Machine Learning Research Group#TAB#","institution_ids":["https://openalex.org/I7597260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102890948","display_name":"Levente Kocsis","orcid":"https://orcid.org/0000-0002-8700-5060","observed_orcids":["https://orcid.org/0000-0002-8700-5060"]},"institutions":[{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"government","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Levente Kocsis","raw_affiliation_strings":["Computer and Automation Research Institute of the Hungarian Academy of Sciences, Machine Learning Research Group#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer and Automation Research Institute of the Hungarian Academy of Sciences, Machine Learning Research Group#TAB#","institution_ids":["https://openalex.org/I7597260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109782632","display_name":"Ivett Szab\u00f3","orcid":"https://orcid.org/0009-0007-3041-0368","observed_orcids":["https://orcid.org/0009-0007-3041-0368"]},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"government","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Ivett Szab\u00f3","raw_affiliation_strings":["Computer and Automation Research Institute of the Hungarian Academy of Sciences, Machine Learning Research Group and Budapest University of Technology and Economics, Department of Stochastics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer and Automation Research Institute of the Hungarian Academy of Sciences, Machine Learning Research Group and Budapest University of Technology and Economics, Department of Stochastics","institution_ids":["https://openalex.org/I29770179","https://openalex.org/I7597260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069856068","display_name":"Csaba Szepesv\u00e1ri","orcid":"https://orcid.org/0000-0002-9286-2892","observed_orcids":["https://orcid.org/0000-0002-9286-2892"]},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"government","lineage":["https://openalex.org/I7597260"]}],"countries":["CA","HU"],"is_corresponding":false,"raw_author_name":"Csaba Szepesv\u00e1ri","raw_affiliation_strings":["Computer and Automation Research Institute of the Hungarian Academy of Sciences, Machine Learning Research Group and University of Alberta, Department of Computing Science#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer and Automation Research Institute of the Hungarian Academy of Sciences, Machine Learning Research Group and University of Alberta, Department of Computing Science#TAB#","institution_ids":["https://openalex.org/I154425047","https://openalex.org/I7597260"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":98},"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/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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-armed-bandits","display_name":"multi-armed bandits","score":0.7979999780654907},{"id":"https://openalex.org/keywords/side-information","display_name":"side information","score":0.7429999709129333},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.7429999709129333},{"id":"https://openalex.org/keywords/upper-confidence-bound","display_name":"upper confidence bound","score":0.7599999904632568},{"id":"https://openalex.org/keywords/regret-analysis","display_name":"regret analysis","score":0.7739999890327454}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7745969295501709},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.5808232426643372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5717602968215942},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5506366491317749},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5498490333557129},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5330601930618286},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5061060786247253},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5055453777313232},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.43231311440467834},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36305853724479675},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17929130792617798},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.420.4362","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.420.4362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://papersdb.cs.ualberta.ca/~papersdb/uploaded_files/632/paper_cbandit-ijcai07.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.76.4566","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.76.4566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ijcai.org/papers07/Papers/IJCAI07-133.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.96.1359","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.96.1359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://zaphod.aml.sztaki.hu/papers/ijcai07.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.sztaki.hu:5120","doi":null,"is_oa":false,"landing_page_url":"http://eprints.sztaki.hu/5120/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401907","display_name":"SZTAKI Publication Repository (Hungarian Academy of Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I7597260","host_organization_name":"Hungarian Academy of Sciences","host_organization_lineage":["https://openalex.org/I7597260"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W21934178","https://openalex.org/W1564947197","https://openalex.org/W1998498767","https://openalex.org/W2000080679","https://openalex.org/W2009551863","https://openalex.org/W2089415692","https://openalex.org/W2119567691","https://openalex.org/W2129239159","https://openalex.org/W2161704742","https://openalex.org/W2168405694"],"related_works":["https://openalex.org/W2158858912","https://openalex.org/W1979352993","https://openalex.org/W2997166982","https://openalex.org/W2978370697","https://openalex.org/W7098510815","https://openalex.org/W7100077618","https://openalex.org/W1503278348","https://openalex.org/W7095666781","https://openalex.org/W2519411794","https://openalex.org/W3185477207"],"abstract_inverted_index":{"In":[0,12],"this":[1,13,130],"paper":[2],"we":[3],"consider":[4,84],"an":[5,24,43,112],"extension":[6],"of":[7,49,81,121,129,148,172],"the":[8,16,38,66,78,85,90,99,119,122,127,134,142,146,162,170,173],"multiarmed":[9],"bandit":[10,40],"problem.":[11,123,174],"generalized":[14],"setting,":[15],"decision":[17,91],"maker":[18,92],"receives":[19,33],"some":[20],"side":[21],"information,":[22],"performs":[23],"action":[25,44],"chosen":[26],"from":[27],"a":[28,34,46,152],"finite":[29],"set":[30],"and":[31,59,108,166],"then":[32],"reward.":[35],"Unlike":[36],"in":[37,70],"standard":[39],"settings,":[41],"performing":[42],"takes":[45],"random":[47],"period":[48],"time.":[50],"The":[51,61],"environment":[52,100],"is":[53,63],"assumed":[54],"to":[55,64,76,133],"be":[56],"stationary,":[57],"stochastic":[58],"memoryless.":[60],"goal":[62],"maximize":[65,77],"average":[67,79],"reward":[68],"received":[69],"one":[71],"unit":[72],"time,":[73],"that":[74,117,126,137,156],"is,":[75,157],"rate":[80,153],"return.":[82],"We":[83,110,124],"on-line":[86],"learning":[87],"problem":[88,143],"where":[89],"initially":[93],"does":[94],"not":[95],"know":[96],"anything":[97],"about":[98,104,141],"but":[101],"must":[102],"learn":[103],"it":[105],"by":[106],"trial":[107],"error.":[109],"propose":[111],"\u201cupper":[113],"confidence":[114],"bound\u201d-style":[115],"algorithm":[116,131,136],"exploits":[118],"structure":[120],"show":[125],"regret":[128],"relative":[132],"optimal":[135,163],"has":[138],"perfect":[139],"knowledge":[140],"grows":[144],"with":[145,169],"number":[147],"decisions":[149],"n":[150],"at":[151],"\u00d5(log":[154],"n),":[155],"only":[158],"slightly":[159],"faster":[160],"than":[161],"logarithmic":[164],"rate,":[165],"scales":[167],"polynomially":[168],"parameters":[171],"1":[175]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}