{"id":"https://openalex.org/W573908607","doi":null,"title":"Online Learning in Bandit Problems.","display_name":"Online Learning in Bandit Problems.","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W573908607","mag":"573908607"},"language":"en","primary_location":{"id":"pmh:oai:deepblue.lib.umich.edu:2027.42/97798","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2027.42/97798","pdf_url":"https://hdl.handle.net/2027.42/97798","source":{"id":"https://openalex.org/S4306400393","display_name":"Deep Blue (University of Michigan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I27837315","host_organization_name":"University of Michigan","host_organization_lineage":["https://openalex.org/I27837315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2027.42/97798","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053015746","display_name":"Cem Tekin","orcid":"https://orcid.org/0000-0003-4361-4021","observed_orcids":["https://orcid.org/0000-0003-4361-4021"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cem Tekin","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4361-4021","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5053015746"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/bandit-problems","display_name":"bandit problems","score":0.7689999938011169},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.9480000138282776},{"id":"https://openalex.org/keywords/exploration-exploitation-trade-off","display_name":"exploration-exploitation balance","score":0.9079999923706055},{"id":"https://openalex.org/keywords/distributed-online-learning","display_name":"distributed online learning","score":0.8069999814033508},{"id":"https://openalex.org/keywords/sequential-decision-making-under-uncertainty","display_name":"sequential decision making under uncertainty","score":0.8820000290870667}],"concepts":[{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.48306018114089966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4309220016002655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37335336208343506},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.34346216917037964},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33366328477859497},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2160884141921997}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:deepblue.lib.umich.edu:2027.42/97798","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2027.42/97798","pdf_url":"https://hdl.handle.net/2027.42/97798","source":{"id":"https://openalex.org/S4306400393","display_name":"Deep Blue (University of Michigan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I27837315","host_organization_name":"University of Michigan","host_organization_lineage":["https://openalex.org/I27837315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},{"id":"mag:573908607","doi":null,"is_oa":false,"landing_page_url":"https://deepblue.lib.umich.edu/handle/2027.42/97798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:deepblue.lib.umich.edu:2027.42/97798","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2027.42/97798","pdf_url":"https://hdl.handle.net/2027.42/97798","source":{"id":"https://openalex.org/S4306400393","display_name":"Deep Blue (University of Michigan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I27837315","host_organization_name":"University of Michigan","host_organization_lineage":["https://openalex.org/I27837315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W573908607.pdf","grobid_xml":"https://content.openalex.org/works/W573908607.grobid-xml"},"referenced_works_count":85,"referenced_works":["https://openalex.org/W50486269","https://openalex.org/W131745075","https://openalex.org/W166250193","https://openalex.org/W172143579","https://openalex.org/W1488797257","https://openalex.org/W1501823362","https://openalex.org/W1517645949","https://openalex.org/W1521084402","https://openalex.org/W1528133536","https://openalex.org/W1567092208","https://openalex.org/W1575658237","https://openalex.org/W1751431909","https://openalex.org/W1850488217","https://openalex.org/W1861050369","https://openalex.org/W1944301273","https://openalex.org/W1945796651","https://openalex.org/W1960351623","https://openalex.org/W1965208040","https://openalex.org/W1967962702","https://openalex.org/W1975779216","https://openalex.org/W1977989560","https://openalex.org/W1991354823","https://openalex.org/W1996859119","https://openalex.org/W1998376807","https://openalex.org/W1998498767","https://openalex.org/W2000080679","https://openalex.org/W2010189695","https://openalex.org/W2013532620","https://openalex.org/W2025702744","https://openalex.org/W2029199203","https://openalex.org/W2039522160","https://openalex.org/W2040774021","https://openalex.org/W2041205077","https://openalex.org/W2048628967","https://openalex.org/W2049687551","https://openalex.org/W2049689520","https://openalex.org/W2054129049","https://openalex.org/W2056237576","https://openalex.org/W2056921512","https://openalex.org/W2061753713","https://openalex.org/W2068823761","https://openalex.org/W2077902449","https://openalex.org/W2078945272","https://openalex.org/W2093562354","https://openalex.org/W2096382242","https://openalex.org/W2097487180","https://openalex.org/W2097931172","https://openalex.org/W2101379030","https://openalex.org/W2103581319","https://openalex.org/W2105556121","https://openalex.org/W2109643282","https://openalex.org/W2113733815","https://openalex.org/W2115293355","https://openalex.org/W2115519224","https://openalex.org/W2120125372","https://openalex.org/W2122422466","https://openalex.org/W2125724988","https://openalex.org/W2132876566","https://openalex.org/W2138859735","https://openalex.org/W2139964991","https://openalex.org/W2140571193","https://openalex.org/W2142971854","https://openalex.org/W2145049547","https://openalex.org/W2151299863","https://openalex.org/W2151323275","https://openalex.org/W2153107031","https://openalex.org/W2156588232","https://openalex.org/W2157146750","https://openalex.org/W2158807713","https://openalex.org/W2159471113","https://openalex.org/W2159674005","https://openalex.org/W2168405694","https://openalex.org/W2169926276","https://openalex.org/W2181151646","https://openalex.org/W2268509491","https://openalex.org/W2317700292","https://openalex.org/W2400672140","https://openalex.org/W2519411794","https://openalex.org/W2555652361","https://openalex.org/W2753514269","https://openalex.org/W2770673272","https://openalex.org/W2914156981","https://openalex.org/W2962764550","https://openalex.org/W2963007414","https://openalex.org/W3017750102"],"related_works":["https://openalex.org/W2989972589","https://openalex.org/W6945576717","https://openalex.org/W6945900738","https://openalex.org/W2978465060","https://openalex.org/W1979352993","https://openalex.org/W4297972217","https://openalex.org/W4285717078","https://openalex.org/W7117250523","https://openalex.org/W7100697693","https://openalex.org/W3185477207"],"abstract_inverted_index":{"In":[0,31],"a":[1,6,72,87,96,175],"bandit":[2,36,88,118,170,184],"problem":[3,89],"there":[4,173],"is":[5,90,158,174],"set":[7],"of":[8,11,51,54,61,65,79,107,146,151,207,239,268],"arms,":[9,189],"each":[10,149],"which":[12,26,42,94,186,242],"when":[13],"played":[14],"by":[15,197],"an":[16,39,161],"agent":[17],"yields":[18],"some":[19],"reward":[20],"depending":[21,271],"on":[22,76,183,203,272],"its":[23,122],"internal":[24],"state":[25],"evolves":[27],"stochastically":[28],"over":[29],"time.":[30],"this":[32,52,255],"thesis":[33],"we":[34,190,210,233,257],"consider":[35,235],"problems":[37,119,185],"in":[38,86,164,219,251,266],"online":[40,166,260],"framework":[41],"involves":[43],"sequential":[44],"decision-making":[45],"under":[46],"uncertainty.":[47],"Within":[48],"the":[49,62,66,77,91,144,180,199,204,208,236],"context":[50],"class":[53],"problems,":[55],"agents":[56,147],"who":[57],"are":[58,154,264],"initially":[59],"unaware":[60],"stochastic":[63],"evolution":[64],"environment":[67],"(arms),":[68],"aim":[69],"to":[70,100,110,116,159,222],"maximize":[71],"common":[73],"objective":[74],"based":[75],"history":[78],"actions":[80],"and":[81,104,140,246,274],"observations.":[82],"The":[83,114],"classical":[84,181,230],"difficulty":[85],"exploration-exploitation":[92],"dilemma,":[93],"necessitates":[95],"careful":[97],"algorithm":[98],"design":[99,139],"balance":[101],"information":[102,109],"gathering":[103],"best":[105],"use":[106],"available":[108],"achieve":[111],"optimal":[112,265],"performance.":[113],"motivation":[115],"study":[117],"comes":[120],"from":[121,179,217,229],"diverse":[123],"applications":[124,153],"including":[125],"cognitive":[126],"radio":[127],"networks,":[128],"opportunistic":[129],"spectrum":[130],"access,":[131],"network":[132],"routing,":[133],"web":[134],"advertising,":[135],"clinical":[136],"trials,":[137],"contract":[138],"many":[141],"others.":[142],"Since":[143],"characteristics":[145],"for":[148,169,194],"one":[150],"these":[152],"different,":[155],"our":[156],"goal":[157],"provide":[160],"agent-centric":[162],"approach":[163],"designing":[165],"learning":[167,192,261],"algorithms":[168,193,262],"problems.":[171],"When":[172],"single":[176],"agent,":[177,209],"different":[178,213],"work":[182],"assumes":[187],"IID":[188],"develop":[191,258],"Markovian":[195],"arms":[196],"considering":[198],"computational":[200,205],"complexity.":[201],"Depending":[202],"power":[206],"show":[211],"that":[212,263],"performance":[214],"levels":[215],"ranging":[216],"optimality":[218,224],"weak":[220,269],"regret,":[221],"strong":[223],"can":[225],"be":[226],"achieved.":[227],"Apart":[228],"single-agent":[231,252],"bandits,":[232],"also":[234],"novel":[237],"area":[238],"multi-agent":[240],"bandits":[241],"has":[243],"informational":[244],"decentralization":[245],"communication":[247,273],"aspects":[248],"not":[249],"present":[250],"bandits.":[253],"For":[254],"setting,":[256],"distributed":[259],"terms":[267],"regret":[270],"computation":[275],"constraints.":[276]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}