{"id":"https://openalex.org/W4406012113","doi":"https://doi.org/10.1109/tac.2024.3525417","title":"Decentralized Upper Confidence Bound Algorithms for Homogeneous Multi-agent Multi-armed Bandits","display_name":"Decentralized Upper Confidence Bound Algorithms for Homogeneous Multi-agent Multi-armed Bandits","publication_year":2025,"publication_date":"2025-01-02","ids":{"openalex":"https://openalex.org/W4406012113","doi":"https://doi.org/10.1109/tac.2024.3525417"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2024.3525417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3525417","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/A5046954454","display_name":"Jingxuan Zhu","orcid":"https://orcid.org/0000-0003-3354-1578"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jingxuan Zhu","raw_affiliation_strings":["Department of Applied Mathematics and Statistics, Stony Brook University, Stony Brook, NY, USA","E-Surfing Digital Life Technology Co., Ltd., Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics, Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]},{"raw_affiliation_string":"E-Surfing Digital Life Technology Co., Ltd., Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010884698","display_name":"Ethan Mulle","orcid":null},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ethan Mulle","raw_affiliation_strings":["Department of Applied Mathematics, University of California Santa Cruz, Santa Cruz, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, University of California Santa Cruz, Santa Cruz, CA, USA","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101997341","display_name":"C. W. Smith","orcid":"https://orcid.org/0009-0008-4783-1764"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher S. Smith","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stony Brook, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025896653","display_name":"Alec Koppel","orcid":"https://orcid.org/0000-0003-2447-2873"},"institutions":[{"id":"https://openalex.org/I2802755631","display_name":"Morgan Stanley (United States)","ror":"https://ror.org/00aphdz18","country_code":"US","type":"company","lineage":["https://openalex.org/I2802755631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alec Koppel","raw_affiliation_strings":["J.P. Morgan AI Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"J.P. Morgan AI Research, New York, NY, USA","institution_ids":["https://openalex.org/I2802755631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396338","display_name":"Ji Liu","orcid":"https://orcid.org/0000-0003-2871-9888"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ji Liu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Stony Brook University, Stony Brook, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5046954454"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":4.4044,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91962292,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"70","issue":"7","first_page":"4360","last_page":"4375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9970999956130981,"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":0.9944000244140625,"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":0.624257504940033},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5667973160743713},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.5245147943496704},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.5007140636444092},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5002710819244385},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4639195203781128},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.45744770765304565},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.45519909262657166},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.437358558177948},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4360661506652832},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3220791816711426},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.31082800030708313},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3025347590446472},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25703227519989014},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.133883535861969}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.624257504940033},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5667973160743713},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.5245147943496704},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.5007140636444092},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5002710819244385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4639195203781128},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.45744770765304565},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.45519909262657166},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.437358558177948},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4360661506652832},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3220791816711426},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31082800030708313},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3025347590446472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25703227519989014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.133883535861969},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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":1,"locations":[{"id":"doi:10.1109/tac.2024.3525417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3525417","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G340967780","display_name":null,"funder_award_id":"FA9550-23-1-0175","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G8053630600","display_name":null,"funder_award_id":"2230101","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/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1571416372","https://openalex.org/W1882177676","https://openalex.org/W1998039896","https://openalex.org/W2009551863","https://openalex.org/W2011301426","https://openalex.org/W2044212084","https://openalex.org/W2061641373","https://openalex.org/W2123681024","https://openalex.org/W2132022337","https://openalex.org/W2140571193","https://openalex.org/W2142971854","https://openalex.org/W2148087609","https://openalex.org/W2159050893","https://openalex.org/W2160643434","https://openalex.org/W2164642931","https://openalex.org/W2165744313","https://openalex.org/W2168405694","https://openalex.org/W2238973924","https://openalex.org/W2946038967","https://openalex.org/W2963554715","https://openalex.org/W2963767621","https://openalex.org/W2963832131","https://openalex.org/W2964008919","https://openalex.org/W2964146343","https://openalex.org/W2991046523","https://openalex.org/W3003257820","https://openalex.org/W3035965352","https://openalex.org/W3038426846","https://openalex.org/W3046298489","https://openalex.org/W3080710500","https://openalex.org/W3094364818","https://openalex.org/W3099878876","https://openalex.org/W3102449016","https://openalex.org/W3109979887","https://openalex.org/W3118244830","https://openalex.org/W3119432456","https://openalex.org/W3121953620","https://openalex.org/W3174647784","https://openalex.org/W3185115592","https://openalex.org/W4206275166","https://openalex.org/W4206530644","https://openalex.org/W4210323337","https://openalex.org/W4238472918","https://openalex.org/W4244375620","https://openalex.org/W4281685977","https://openalex.org/W4283789700","https://openalex.org/W4321484158","https://openalex.org/W4406012113","https://openalex.org/W4407950459","https://openalex.org/W6630117878","https://openalex.org/W6678532988","https://openalex.org/W6682793069","https://openalex.org/W6762907276","https://openalex.org/W6772577700","https://openalex.org/W6781849426","https://openalex.org/W6784774785","https://openalex.org/W6790524457","https://openalex.org/W6876120286","https://openalex.org/W7036764036"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2947263763","https://openalex.org/W4288373430","https://openalex.org/W3036260055","https://openalex.org/W4287753704","https://openalex.org/W3158925485","https://openalex.org/W2996735312"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"a":[3,10,27,62,109,165],"decentralized":[4,67,96,169],"homogeneous":[5],"multi-armed":[6],"bandit":[7],"problem":[8,14],"in":[9,104],"multi-agent":[11],"network.":[12],"The":[13,94,150],"is":[15,144,155],"simultaneously":[16],"solved":[17],"by":[18,61],"<inline-formula":[19,31],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[20,32],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[21,33],"notation=\"LaTeX\">$N$</tex-math></inline-formula>":[22],"agents":[23,58],"assuming":[24],"they":[25],"face":[26],"common":[28],"set":[29],"of":[30,164,167],"notation=\"LaTeX\">$M$</tex-math></inline-formula>":[34],"arms":[35],"and":[36,85,98,127],"share":[37],"the":[38,53,57,81,86,105,120,128,134,142,162,168,174],"same":[39,151],"arms'":[40],"reward":[41],"distributions.":[42],"Each":[43],"agent":[44,103,121,132],"can":[45],"receive":[46],"information":[47],"only":[48],"from":[49],"its":[50,147],"neighbors,":[51],"where":[52],"neighbor":[54],"relationships":[55],"among":[56],"are":[59,73],"described":[60],"fixed":[63],"graph.":[64],"Two":[65],"fully":[66],"upper":[68,89],"confidence":[69,90],"bound":[70,91],"(UCB)":[71],"algorithms":[72,100],"proposed":[74,95],"for":[75],"undirected":[76],"graphs,":[77],"respectively":[78],"based":[79],"on":[80],"classic":[82],"UCB1":[83,97,170,176],"algorithm":[84,152],"state-of-the-art":[87],"Kullback-Leibler":[88],"(KL-UCB)":[92],"algorithm.":[93,177],"KL-UCB":[99],"permit":[101],"each":[102],"network":[106],"to":[107,158],"achieve":[108],"better":[110,135],"logarithmic":[111],"asymptotic":[112],"regret":[113,136],"than":[114,146],"their":[115],"single-agent":[116,175],"counterparts,":[117],"provided":[118],"that":[119,141],"has":[122],"at":[123],"least":[124],"one":[125],"neighbor,":[126],"more":[129,145],"neighbors":[130],"an":[131],"has,":[133],"it":[137],"will":[138],"have,":[139],"meaning":[140],"sum":[143],"component":[148],"parts.":[149],"design":[153,163],"framework":[154],"also":[156],"extended":[157],"directed":[159],"graphs":[160],"through":[161],"variant":[166],"algorithm,":[171],"which":[172],"outperforms":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}