{"id":"https://openalex.org/W4414359573","doi":"https://doi.org/10.24963/ijcai.2025/564","title":"Multi-player Multi-armed Bandits with Delayed Feedback","display_name":"Multi-player Multi-armed Bandits with Delayed Feedback","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359573","doi":"https://doi.org/10.24963/ijcai.2025/564"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/564","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5108186403","display_name":"Junguo Fan","orcid":"https://orcid.org/0009-0006-3179-3498"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingqi Fan","raw_affiliation_strings":["Northeastern University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046033511","display_name":"Zilong Wang","orcid":"https://orcid.org/0000-0002-7875-0704"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilong Wang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059952787","display_name":"Shuai Li","orcid":"https://orcid.org/0000-0001-8871-3272"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Li","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072308822","display_name":"Linghe Kong","orcid":"https://orcid.org/0000-0001-9266-3044"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linghe Kong","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5065","last_page":"5073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9991000294685364,"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":0.9991000294685364,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9485999941825867,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9139000177383423,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7894999980926514},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6198999881744385},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6115000247955322},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5995000004768372},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4316999912261963}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7894999980926514},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6198999881744385},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6115000247955322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6033999919891357},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5995000004768372},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4316999912261963},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3433000147342682},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3151000142097473},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2775999903678894},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2676999866962433}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/564","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-player":[0],"multi-armed":[1],"bandits":[2],"(MP-MAB)":[3],"have":[4],"been":[5],"extensively":[6],"studied":[7],"due":[8,37],"to":[9,38,121,139,157],"their":[10,104],"application":[11],"in":[12,29,82,90],"cognitive":[13],"radio":[14],"networks.":[15],"In":[16,75],"this":[17,76],"setting,":[18],"multiple":[19],"players":[20,138],"simultaneously":[21],"select":[22],"arms":[23,111],"and":[24,41,52,70,152,168],"instantly":[25],"receive":[26],"feedback.":[27,87],"However,":[28],"realistic":[30],"decentralized":[31],"networks,":[32],"feedback":[33,54],"is":[34,50,161],"often":[35],"delayed":[36,53,106],"sensing":[39],"latency":[40],"signal":[42],"processing.":[43],"Without":[44],"a":[45,65,148,154],"central":[46],"coordinator,":[47],"explicit":[48],"communication":[49],"impossible,":[51],"disrupts":[55],"implicit":[56,135],"coordination,":[57],"since":[58],"it":[59],"depends":[60],"on":[61,103,165],"synchronous":[62],"observations.":[63],"As":[64],"result,":[66],"collisions":[67],"are":[68],"frequent":[69],"system":[71],"performance":[72],"degrades":[73],"significantly.":[74],"paper,":[77],"we":[78],"propose":[79],"an":[80,95],"algorithm":[81,92,160],"MP-MAB":[83],"with":[84,117],"stochastic":[85],"delay":[86],"Each":[88],"player":[89],"the":[91,98,113,141,159,172],"independently":[93],"maintains":[94],"estimate":[96],"of":[97,123,144,174],"optimal":[99],"arm":[100,131],"set":[101,132],"based":[102],"own":[105],"rewards":[107],"but":[108],"only":[109],"pulls":[110],"from":[112],"set,":[114],"which":[115],"is,":[116],"high":[118],"probability,":[119],"identical":[120,130],"those":[122],"other":[124],"players,":[125],"thus":[126],"avoiding":[127],"collisions.":[128],"The":[129],"also":[133],"enables":[134],"communication,":[136],"allowing":[137],"utilize":[140],"exploration":[142],"results":[143],"others.":[145],"We":[146],"establish":[147],"regret":[149],"upper":[150],"bound":[151,156],"derive":[153],"lower":[155],"prove":[158],"near-optimal.":[162],"Numerical":[163],"experiments":[164],"both":[166],"synthetic":[167],"real-world":[169],"datasets":[170],"validate":[171],"effectiveness":[173],"our":[175],"algorithm.":[176]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}