{"id":"https://openalex.org/W4407988036","doi":"https://doi.org/10.1109/cdc56724.2024.10885907","title":"Optimal Cooperative Multiplayer Learning Bandits with Noisy Rewards and No Communication","display_name":"Optimal Cooperative Multiplayer Learning Bandits with Noisy Rewards and No Communication","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407988036","doi":"https://doi.org/10.1109/cdc56724.2024.10885907"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10885907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10885907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-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/A5056463978","display_name":"William K. Chang","orcid":"https://orcid.org/0000-0003-2231-9023"},"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":true,"raw_author_name":"William Chang","raw_affiliation_strings":["University of California,Los Angeles"],"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042153523","display_name":"Yuanhao Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanhao Lu","raw_affiliation_strings":["Princeton University"],"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056463978"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34069448,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"823","last_page":"830"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9991999864578247,"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":0.9991999864578247,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9830999970436096,"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/T12676","display_name":"Machine Learning and ELM","score":0.9623000025749207,"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/computer-science","display_name":"Computer science","score":0.7892543077468872},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5287808179855347},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3883781135082245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7892543077468872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5287808179855347},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3883781135082245}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10885907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10885907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1882177676","https://openalex.org/W2009551863","https://openalex.org/W2025356004","https://openalex.org/W2056568177","https://openalex.org/W2061641373","https://openalex.org/W2093562354","https://openalex.org/W2140571193","https://openalex.org/W2168405694","https://openalex.org/W2169926276","https://openalex.org/W2499002200","https://openalex.org/W2683628546","https://openalex.org/W2742000570","https://openalex.org/W2900893952","https://openalex.org/W2964146343","https://openalex.org/W2970781853","https://openalex.org/W2972216047","https://openalex.org/W3127540145","https://openalex.org/W3154681813","https://openalex.org/W4206530644","https://openalex.org/W4232620022","https://openalex.org/W4315488911","https://openalex.org/W6632992360","https://openalex.org/W6682793069","https://openalex.org/W6692447168","https://openalex.org/W6705013792","https://openalex.org/W6754620478","https://openalex.org/W6754700216","https://openalex.org/W6773999918","https://openalex.org/W6780141059","https://openalex.org/W6802654881","https://openalex.org/W6803726439","https://openalex.org/W6840107105","https://openalex.org/W6840596938","https://openalex.org/W6846524154"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"We":[0,126,136],"consider":[1],"a":[2,17,49,64],"cooperative":[3],"multiplayer":[4],"bandit":[5],"learning":[6,25],"problem":[7],"where":[8],"the":[9,24,38,44,55,68,88,110,120,123,145],"players":[10,47,56,78,111],"are":[11,57],"only":[12],"allowed":[13],"to":[14,91,114],"agree":[15],"on":[16,37,103],"strategy":[18],"beforehand,":[19],"but":[20],"cannot":[21,71],"communicate":[22],"during":[23],"process.":[26],"In":[27,95],"this":[28,96,129,150],"problem,":[29],"each":[30,61],"player":[31,62],"simultaneously":[32],"selects":[33],"an":[34,85,100],"action.":[35],"Based":[36],"actions":[39,52,118],"selected":[40],"by":[41],"all":[42,54],"players,":[43],"team":[45],"of":[46,53,67],"receives":[48,63],"reward.":[50],"The":[51],"commonly":[58],"observed.":[59],"However,":[60],"noisy":[65],"version":[66],"reward":[69,124],"which":[70],"be":[72],"shared":[73],"with":[74],"other":[75],"players.":[76],"Since":[77],"receive":[79],"potentially":[80],"different":[81],"rewards,":[82],"there":[83],"is":[84,131],"asymmetry":[86,121],"in":[87,122,134],"information":[89],"used":[90],"select":[92,115],"their":[93,116],"actions.":[94],"paper,":[97],"we":[98],"provide":[99],"algorithm":[101,130,148],"based":[102],"upper":[104],"and":[105],"lower":[106],"confidence":[107],"bounds":[108],"that":[109,128,139],"can":[112],"use":[113],"optimal":[117,133],"despite":[119],"information.":[125],"show":[127,138],"asymptotically":[132],"T.":[135],"also":[137],"it":[140],"performs":[141],"empirically":[142],"better":[143],"than":[144],"current":[146],"state-of-the-art":[147],"for":[149],"environment.":[151]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}