{"id":"https://openalex.org/W4390044888","doi":"https://doi.org/10.1109/icast57874.2023.10359301","title":"Multi-Agent Reinforcement Learning for a Multichannel Uplink Random Access: Congestion Game Perspective","display_name":"Multi-Agent Reinforcement Learning for a Multichannel Uplink Random Access: Congestion Game Perspective","publication_year":2023,"publication_date":"2023-11-09","ids":{"openalex":"https://openalex.org/W4390044888","doi":"https://doi.org/10.1109/icast57874.2023.10359301"},"language":"en","primary_location":{"id":"doi:10.1109/icast57874.2023.10359301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icast57874.2023.10359301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 12th International Conference on Awareness Science and Technology (iCAST)","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/A5021844700","display_name":"Yu Zhao","orcid":"https://orcid.org/0000-0003-2235-8807"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yu Zhao","raw_affiliation_strings":["Hanyang University,Department of Electrical and Electronic Engineering,Ansan,15588"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electrical and Electronic Engineering,Ansan,15588","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318495","display_name":"Joohyun Lee","orcid":"https://orcid.org/0000-0002-7698-1568"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joohyun Lee","raw_affiliation_strings":["Hanyang University,Department of Electrical and Electronic Engineering,Ansan,15588"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electrical and Electronic Engineering,Ansan,15588","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051565721","display_name":"Jun-Bae Seo","orcid":"https://orcid.org/0000-0001-7789-1778"},"institutions":[{"id":"https://openalex.org/I189442560","display_name":"Gyeongsang National University","ror":"https://ror.org/00saywf64","country_code":"KR","type":"education","lineage":["https://openalex.org/I189442560"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jun-Bae Seo","raw_affiliation_strings":["Gyeongsang National University,Department of Information and Communication Engineering,Jinju,52828"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gyeongsang National University,Department of Information and Communication Engineering,Jinju,52828","institution_ids":["https://openalex.org/I189442560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5024,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65273266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9986000061035156,"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":0.9986000061035156,"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/T11031","display_name":"Game Theory and Applications","score":0.9984999895095825,"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/T10579","display_name":"Cognitive Radio Networks and Spectrum Sensing","score":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8936524391174316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7652527689933777},{"id":"https://openalex.org/keywords/telecommunications-link","display_name":"Telecommunications link","score":0.6741631627082825},{"id":"https://openalex.org/keywords/random-access","display_name":"Random access","score":0.6470450162887573},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6283053755760193},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6225899457931519},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6062307357788086},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4642786383628845},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.44786542654037476},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3287905752658844},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2912207841873169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2799382507801056},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13347938656806946},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.10219061374664307}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8936524391174316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7652527689933777},{"id":"https://openalex.org/C138660444","wikidata":"https://www.wikidata.org/wiki/Q5607897","display_name":"Telecommunications link","level":2,"score":0.6741631627082825},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.6470450162887573},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6283053755760193},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6225899457931519},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6062307357788086},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4642786383628845},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.44786542654037476},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3287905752658844},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2912207841873169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2799382507801056},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13347938656806946},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.10219061374664307},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icast57874.2023.10359301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icast57874.2023.10359301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 12th International Conference on Awareness Science and Technology (iCAST)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2054129049","https://openalex.org/W2151688082","https://openalex.org/W2798219148","https://openalex.org/W2889496030","https://openalex.org/W2892466769","https://openalex.org/W2898754723","https://openalex.org/W2948327724","https://openalex.org/W2969459099","https://openalex.org/W2970905513","https://openalex.org/W2971910510","https://openalex.org/W3016251777","https://openalex.org/W4205993435","https://openalex.org/W4206530644","https://openalex.org/W4246520098","https://openalex.org/W4252284432","https://openalex.org/W4285248774"],"related_works":["https://openalex.org/W2548963335","https://openalex.org/W2159941915","https://openalex.org/W1995129237","https://openalex.org/W4312141693","https://openalex.org/W1536009559","https://openalex.org/W2103821767","https://openalex.org/W1969185016","https://openalex.org/W2037619003","https://openalex.org/W2111030377","https://openalex.org/W1965856819"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,45,83],"propose":[4,46],"a":[5,74],"time-slotted":[6],"multichannel":[7],"uplink":[8],"random":[9],"access":[10],"(RA)":[11],"game":[12,28],"model":[13],"where":[14,61],"players":[15],"do":[16],"not":[17],"cooperate.":[18],"We":[19],"first":[20],"analyze":[21],"its":[22],"sum":[23,93],"throughput":[24,94],"from":[25],"the":[26,33,59,66,96],"congestion":[27],"(CG)":[29],"perspective":[30],"and":[31],"obtain":[32,90],"pure":[34],"strategy":[35],"Nash":[36],"equilibria":[37],"(PNEs)":[38],"that":[39,70,85],"fully":[40],"utilize":[41],"each":[42,78],"slot.":[43],"Then,":[44],"an":[47],"Upper":[48],"Confidence":[49],"Bound":[50],"(UCB)-based":[51],"multi-agent":[52],"reinforcement":[53],"learning":[54],"(MARL)":[55],"algorithm":[56,88],"to":[57],"realize":[58],"PNEs,":[60],"UCB":[62],"is":[63],"one":[64],"of":[65],"multi-armed":[67],"bandit":[68],"algorithms":[69],"work":[71],"by":[72],"assigning":[73],"confidence":[75],"level":[76],"for":[77],"action.":[79],"Finally,":[80],"via":[81],"simulation,":[82],"show":[84],"our":[86],"proposed":[87],"can":[89],"near-optimal":[91],"average":[92],"in":[95],"long":[97],"run.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}