{"id":"https://openalex.org/W2115293355","doi":"https://doi.org/10.1109/tac.2009.2031725","title":"A Structured Multiarmed Bandit Problem and the Greedy Policy","display_name":"A Structured Multiarmed Bandit Problem and the Greedy Policy","publication_year":2009,"publication_date":"2009-11-06","ids":{"openalex":"https://openalex.org/W2115293355","doi":"https://doi.org/10.1109/tac.2009.2031725","mag":"2115293355"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2009.2031725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2009.2031725","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Transactions on Automatic Control","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/A5082470463","display_name":"Adam J. Mersereau","orcid":"https://orcid.org/0000-0002-8349-0388"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"A.J. Mersereau","raw_affiliation_strings":["Kenan-Flagler Business School, North Carolina State University, Chapel Hill, NC, USA","Kenan Flagler Business School, University of North Carolina, Chapel Hill, NC, USA"],"affiliations":[{"raw_affiliation_string":"Kenan-Flagler Business School, North Carolina State University, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Kenan Flagler Business School, University of North Carolina, Chapel Hill, NC, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041224387","display_name":"Paat Rusmevichientong","orcid":"https://orcid.org/0000-0001-9584-4203"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Rusmevichientong","raw_affiliation_strings":["School of Operations Research and Information Engineering, Cornell University, Ithaca, NY, USA","Sch. of Oper. Res. & Inf. Eng., Cornell Univ., Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"School of Operations Research and Information Engineering, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Sch. of Oper. Res. & Inf. Eng., Cornell Univ., Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108523422","display_name":"John N. Tsitsiklis","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.N. Tsitsiklis","raw_affiliation_strings":["Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","Labs. for Inf. & Decision Syst., Massachusetts Inst. of Technol., Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Labs. for Inf. & Decision Syst., Massachusetts Inst. of Technol., Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082470463"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":7.4886,"has_fulltext":false,"cited_by_count":99,"citation_normalized_percentile":{"value":0.9727113,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"54","issue":"12","first_page":"2787","last_page":"2802"},"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/T12072","display_name":"Machine Learning and Algorithms","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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9957000017166138,"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/bayes-theorem","display_name":"Bayes' theorem","score":0.4881342351436615},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.4856528043746948},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.48437318205833435},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4713430106639862},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43796506524086},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.40585365891456604},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.38176414370536804},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37323397397994995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3342256247997284},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.24220842123031616}],"concepts":[{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.4881342351436615},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.4856528043746948},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.48437318205833435},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4713430106639862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43796506524086},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40585365891456604},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.38176414370536804},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37323397397994995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3342256247997284},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.24220842123031616},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tac.2009.2031725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2009.2031725","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Transactions on Automatic Control","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.141.6792","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.6792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.mit.edu/jnt/www/Papers/P-08-greedy-bandits-sub2.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.7633","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.7633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mit.edu/people/jnt/Papers/J125-09-greedy-bandits.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.473.5338","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.473.5338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dspace.mit.edu/openaccess-disseminate/1721.1/54813/","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1654229139","display_name":"CAREER: Real-Time Stochastic Optimization with Large Structured Strategy Sets and High-Volume Data Streams","funder_award_id":"0746844","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2389698156","display_name":"MSPA-MCS:  Collaborative Research: Algorithms for Near-Optimal Multistage Decision-Making under Uncertainty: Online Learning from Historical Samples","funder_award_id":"0732196","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5169581235","display_name":null,"funder_award_id":"and ECCS-","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5954070948","display_name":null,"funder_award_id":"CMMI-","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671146666","display_name":null,"funder_award_id":"844, and","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G68571969","display_name":"Data Fusion Architectures","funder_award_id":"0701623","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309626","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28"},{"id":"https://openalex.org/F4320337391","display_name":"Division of Civil, Mechanical and Manufacturing Innovation","ror":"https://ror.org/028yd4c30"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W166250193","https://openalex.org/W1496720559","https://openalex.org/W1575658237","https://openalex.org/W1964505956","https://openalex.org/W1965270141","https://openalex.org/W1973885534","https://openalex.org/W1996859119","https://openalex.org/W1998498767","https://openalex.org/W2000080679","https://openalex.org/W2004001705","https://openalex.org/W2009551863","https://openalex.org/W2012731843","https://openalex.org/W2025702744","https://openalex.org/W2034878116","https://openalex.org/W2039522160","https://openalex.org/W2045097767","https://openalex.org/W2049687551","https://openalex.org/W2052664405","https://openalex.org/W2058879737","https://openalex.org/W2066315081","https://openalex.org/W2077902449","https://openalex.org/W2082247722","https://openalex.org/W2097487180","https://openalex.org/W2109174772","https://openalex.org/W2109643282","https://openalex.org/W2129036575","https://openalex.org/W2135730283","https://openalex.org/W2145049547","https://openalex.org/W2158049833","https://openalex.org/W2158807713","https://openalex.org/W2159471113","https://openalex.org/W2168405694","https://openalex.org/W2169071224","https://openalex.org/W2490159962","https://openalex.org/W2576544140","https://openalex.org/W3122984617","https://openalex.org/W4234228486","https://openalex.org/W4235273215","https://openalex.org/W4237780889","https://openalex.org/W4245777296","https://openalex.org/W4246270964","https://openalex.org/W6629680116","https://openalex.org/W6651597697","https://openalex.org/W6674560329"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2980963558"],"abstract_inverted_index":{"We":[0,43,162],"consider":[1],"a":[2,14,22,30,48,154],"multiarmed":[3],"bandit":[4,160],"problem":[5],"where":[6],"the":[7,36,45,55,61,64,73,84,92,97,103,110,120,138,165,176,184],"expected":[8,37],"reward":[9,68,105],"of":[10,17,32,47,54,99,141,159,167,178,183,186],"each":[11],"arm":[12],"is":[13,27,88,123,135],"linear":[15],"function":[16],"an":[18],"unknown":[19],"scalar":[20],"with":[21,91],"prior":[23],"distribution.":[24],"The":[25],"objective":[26],"to":[28],"choose":[29],"sequence":[31],"arms":[33],"that":[34,51,72,109,175],"maximizes":[35],"total":[38,104],"(or":[39],"discounted":[40,67],"total)":[41],"reward.":[42],"demonstrate":[44],"effectiveness":[46],"greedy":[49,74,121],"policy":[50,122,180],"takes":[52],"advantage":[53],"known":[56],"statistical":[57],"correlation":[58],"structure":[59],"among":[60],"arms.":[62,101,187],"In":[63,102],"infinite":[65],"horizon":[66],"setting,":[69,106],"we":[70,107],"show":[71,108,174],"and":[75,80,171],"optimal":[76],"policies":[77],"eventually":[78],"coincide,":[79],"both":[81],"settle":[82],"on":[83],"best":[85],"arm.":[86],"This":[87],"in":[89],"contrast":[90],"Incomplete":[93],"Learning":[94],"Theorem":[95],"for":[96,153],"case":[98],"independent":[100],"cumulative":[111],"Bayes":[112],"risk":[113],"after":[114],"<i":[115,126,130,146],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[116,127,131,144,147],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">T</i>":[117,132,148],"periods":[118],"under":[119],"at":[124],"most":[125],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">O</i>":[128],"(log":[129],"),":[133],"which":[134],"smaller":[136],"than":[137],"lower":[139],"bound":[140],"\u00bf(log":[142],"<sup":[143],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[145],")":[149],"established":[150],"by":[151],"Lai":[152],"general,":[155],"but":[156],"different,":[157],"class":[158],"problems.":[161],"also":[163],"establish":[164],"tightness":[166],"our":[168,179],"bounds.":[169],"Theoretical":[170],"numerical":[172],"results":[173],"performance":[177],"scales":[181],"independently":[182],"number":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}