{"id":"https://openalex.org/W7214089876","doi":"https://doi.org/10.48550/arxiv.2609.26213","title":"Improved Multiplayer Bandit Algorithm for Bernoulli Rewards","display_name":"Improved Multiplayer Bandit Algorithm for Bernoulli Rewards","publication_year":2026,"publication_date":"2026-08-11","ids":{"openalex":"https://openalex.org/W7214089876","doi":"https://doi.org/10.48550/arxiv.2609.26213"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.26213","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.26213","pdf_url":"https://arxiv.org/pdf/2609.26213","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.26213","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152569566","display_name":"Khang Nguyen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nguyen, Khang","raw_affiliation_strings":["Dept. of Computer Science University of California , Los Angeles Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science University of California , Los Angeles Los Angeles , CA , USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114484349","display_name":"Ricardo Parada","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parada, Ricardo","raw_affiliation_strings":["Dept. of Computer Science University of California , Los Angeles Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science University of California , Los Angeles Los Angeles , CA , USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5146959106","display_name":"William Chang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chang, William","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering University of California , Los Angeles Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering University of California , Los Angeles Los Angeles , CA , USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161318765"],"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/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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/information-asymmetry","display_name":"information asymmetry","score":0.9100000262260437},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.7210000157356262},{"id":"https://openalex.org/keywords/umbilical-cord-blood","display_name":"umbilical cord blood","score":0.5270000100135803}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8205000162124634},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.796999990940094},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.555400013923645},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5016999840736389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48350000381469727},{"id":"https://openalex.org/C38976095","wikidata":"https://www.wikidata.org/wiki/Q752641","display_name":"Asymmetry","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C27956954","wikidata":"https://www.wikidata.org/wiki/Q391371","display_name":"Bernoulli distribution","level":3,"score":0.35010001063346863},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C23990920","wikidata":"https://www.wikidata.org/wiki/Q518831","display_name":"Bernoulli process","level":3,"score":0.31619998812675476},{"id":"https://openalex.org/C46802686","wikidata":"https://www.wikidata.org/wiki/Q1077800","display_name":"Bernoulli trial","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.26213","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.26213","pdf_url":"https://arxiv.org/pdf/2609.26213","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2609.26213","doi":"https://doi.org/10.48550/arxiv.2609.26213","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.26213","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.26213","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.26213","pdf_url":"https://arxiv.org/pdf/2609.26213","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214089876.pdf","grobid_xml":"https://content.openalex.org/works/W7214089876.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4407988036","https://openalex.org/W4415101226","https://openalex.org/W4416030384"],"related_works":["https://openalex.org/W4416030384","https://openalex.org/W4415101226","https://openalex.org/W4407988036","https://openalex.org/W2767931851","https://openalex.org/W7133192078","https://openalex.org/W4315488911","https://openalex.org/W1912030372","https://openalex.org/W4289655147","https://openalex.org/W4389065325","https://openalex.org/W2593425276"],"abstract_inverted_index":{"We":[0,46],"study":[1],"the":[2,26,55],"multiplayer":[3],"multi-armed":[4],"bandit":[5],"problem":[6],"with":[7,33],"information":[8,15],"asymmetry":[9,17,77],"under":[10],"Bernoulli":[11],"rewards,":[12,21],"for":[13],"three":[14],"structures:":[16],"in":[18,20,23,43,78],"actions,":[19],"and":[22,50,52,65,94],"both.":[24],"Replacing":[25],"Hoeffding-style":[27],"confidence":[28],"intervals":[29,86],"of":[30,92],"prior":[31],"work":[32],"Kullback--Leibler":[34],"(KL)":[35],"divergence-based":[36],"bounds":[37],"gives":[38],"strictly":[39],"tighter":[40],"regret":[41],"guarantees":[42],"each":[44],"case.":[45],"propose":[47],"\\texttt{mKL-UCB},":[48],"\\texttt{mKL-UCB-Intervals}":[49],"\\texttt{mKL-DSEE},":[51],"show":[53],"that":[54,82,95],"improvement":[56],"factor":[57],"is":[58],"at":[59],"least":[60],"two":[61,83],"by":[62],"Pinsker's":[63],"inequality":[64],"far":[66],"larger":[67],"when":[68],"reward":[69],"means":[70],"are":[71],"near":[72],"zero":[73],"or":[74],"one.":[75],"For":[76],"rewards":[79],"we":[80],"prove":[81],"arms'":[84],"KL":[85],"separate":[87],"after":[88],"a":[89],"deterministic":[90],"number":[91],"samples,":[93],"$M$":[96],"independent":[97],"players":[98],"accelerate":[99],"elimination":[100],"further.":[101]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-24T00:00:00"}