{"id":"https://openalex.org/W7138882375","doi":"https://doi.org/10.1109/globecom59602.2025.11432614","title":"Multi-State Bandit Reinforcement Learning for Decentralized Spectrum Access","display_name":"Multi-State Bandit Reinforcement Learning for Decentralized Spectrum Access","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7138882375","doi":"https://doi.org/10.1109/globecom59602.2025.11432614"},"language":"en","primary_location":{"id":"doi:10.1109/globecom59602.2025.11432614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom59602.2025.11432614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2025 - 2025 IEEE Global Communications Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1109/GLOBECOM59602.2025.11432614","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014134632","display_name":"Ashvin Srinivasan","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ashvin Srinivasan","raw_affiliation_strings":["Aalto University,Department of Information and Communications Engineering,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Information and Communications Engineering,Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117615225","display_name":"Junshan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junshan Zhang","raw_affiliation_strings":["University of California,College of Engineering,Davis,California,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,College of Engineering,Davis,California,USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006597250","display_name":"Olav Tirkkonen","orcid":"https://orcid.org/0000-0002-2611-1636"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Olav Tirkkonen","raw_affiliation_strings":["Aalto University,Department of Information and Communications Engineering,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Information and Communications Engineering,Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":2,"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":"2982","last_page":"2987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.955299973487854,"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":0.955299973487854,"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/T13553","display_name":"Age of Information Optimization","score":0.012500000186264515,"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":0.00430000014603138,"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/operator","display_name":"Operator (biology)","score":0.6241000294685364},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5806000232696533},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.5692999958992004},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.423799991607666},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4007999897003174},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.3961000144481659},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.38659998774528503},{"id":"https://openalex.org/keywords/frequency-allocation","display_name":"Frequency allocation","score":0.384799987077713}],"concepts":[{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.6241000294685364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6011000275611877},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5806000232696533},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.5692999958992004},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5401999950408936},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C134579502","wikidata":"https://www.wikidata.org/wiki/Q1455619","display_name":"Frequency allocation","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.3215000033378601},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.31619998812675476},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2565999925136566}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/globecom59602.2025.11432614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom59602.2025.11432614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2025 - 2025 IEEE Global Communications Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/144177","is_oa":true,"landing_page_url":"https://doi.org/10.1109/GLOBECOM59602.2025.11432614","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/144177","is_oa":true,"landing_page_url":"https://doi.org/10.1109/GLOBECOM59602.2025.11432614","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4421601891517639}],"awards":[],"funders":[{"id":"https://openalex.org/F4320328501","display_name":"Business Finland","ror":"https://ror.org/05bgf9v38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1882177676","https://openalex.org/W2035335961","https://openalex.org/W2169926276","https://openalex.org/W2400672140","https://openalex.org/W3090166564","https://openalex.org/W3120291272","https://openalex.org/W4214533690","https://openalex.org/W4237126822","https://openalex.org/W4245577611","https://openalex.org/W4319878686","https://openalex.org/W4397026359"],"related_works":[],"abstract_inverted_index":{"We":[0,120],"consider":[1,79],"spectrum":[2],"sharing":[3],"in":[4,14,86,103,165],"a":[5,22,26,54,80,147,160,181],"system":[6,145],"with":[7,146],"multiple":[8],"network":[9],"operators":[10,44,59,73,97],"serving":[11],"many":[12],"users":[13],"the":[15,31,41,46,58,62,66,72,94,104,122,128,144,156,166],"same":[16],"coverage":[17],"area.":[18],"Each":[19],"operator":[20,36],"selects":[21],"frequency":[23],"band":[24,47],"from":[25],"pool.":[27],"Due":[28],"to":[29,52,60,112,124,171],"interference,":[30],"aggregate":[32],"throughput":[33],"of":[34,43,71,116],"an":[35,114,172],"would":[37],"likely":[38],"deteriorate":[39],"as":[40,169],"number":[42],"using":[45,150],"increases.":[48],"The":[49],"objective":[50],"is":[51,163],"devise":[53],"decentralized":[55,81,157],"method":[56],"for":[57],"select":[61],"bands,":[63],"assuming":[64],"that":[65,155],"networks":[67],"and":[68,91,102,140,187],"user":[69],"populations":[70],"are":[74,110],"similar.":[75],"For":[76],"this,":[77],"we":[78,153,179],"multi-armed":[82],"bandit":[83],"algorithm":[84,158],"operating":[85],"two":[87],"phases,":[88],"namely":[89],"Estimation":[90],"Allocation.":[92],"In":[93,176],"estimation":[95,185],"phase,":[96,107],"learn":[98],"load-dependent":[99],"reward":[100,129],"distributions;":[101],"subsequent":[105],"allocation":[106,115,191],"these":[108],"estimates":[109],"used":[111],"determine":[113],"bands":[117],"across":[118],"operators.":[119],"extend":[121],"framework":[123],"multi-state":[125,177],"systems,":[126,178],"where":[127],"distribution":[130],"depends":[131],"on":[132],"additional":[133],"observable":[134],"state":[135],"variables":[136],"capturing":[137],"load":[138],"variations":[139],"environmental":[141],"factors.":[142],"Analyzing":[143],"variance-based":[148],"approach":[149],"Bernstein\u2019s":[151],"Inequality,":[152],"show":[154],"achieves":[159],"regret":[161,189],"which":[162],"sublinear":[164],"time":[167],"horizon":[168],"compared":[170],"optimal":[173],"centralized":[174],"decision.":[175],"demonstrate":[180],"trade-off":[182],"between":[183],"increasing":[184],"overhead":[186],"decreasing":[188],"during":[190],"phases.":[192]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-03-20T00:00:00"}