{"id":"https://openalex.org/W4323521126","doi":"https://doi.org/10.1109/ieeeconf56349.2022.10051992","title":"Multi-Agent Reinforcement Learning for Wireless User Scheduling: Performance, Scalablility, and Generalization","display_name":"Multi-Agent Reinforcement Learning for Wireless User Scheduling: Performance, Scalablility, and Generalization","publication_year":2022,"publication_date":"2022-10-31","ids":{"openalex":"https://openalex.org/W4323521126","doi":"https://doi.org/10.1109/ieeeconf56349.2022.10051992"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf56349.2022.10051992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf56349.2022.10051992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 56th Asilomar Conference on Signals, Systems, and Computers","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/A5100691438","display_name":"Kun Yang","orcid":"https://orcid.org/0000-0001-8732-0979"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Yang","raw_affiliation_strings":["University of Virginia,Department of Electrical and Computer Engineering,USA","Department of Electrical and Computer Engineering, University of Virginia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Virginia, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100607522","display_name":"Donghao Li","orcid":"https://orcid.org/0000-0002-1861-5746"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donghao Li","raw_affiliation_strings":["the Pennsylvania State University,Department of Electrical Engineering,USA","Department of Electrical Engineering, the Pennsylvania State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"the Pennsylvania State University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Electrical Engineering, the Pennsylvania State University, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016749653","display_name":"Cong Shen","orcid":"https://orcid.org/0000-0002-3148-4453"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Shen","raw_affiliation_strings":["University of Virginia,Department of Electrical and Computer Engineering,USA","Department of Electrical and Computer Engineering, University of Virginia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Virginia, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645589","display_name":"Jing Yang","orcid":"https://orcid.org/0000-0002-6009-864X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":["the Pennsylvania State University,Department of Electrical Engineering,USA","Department of Electrical Engineering, the Pennsylvania State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"the Pennsylvania State University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Electrical Engineering, the Pennsylvania State University, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032337158","display_name":"Shu\u2010ping Yeh","orcid":"https://orcid.org/0000-0001-5255-2681"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shu-ping Yeh","raw_affiliation_strings":["Intel Corporation,USA","Intel Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation,USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Corporation, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114101923","display_name":"Jerry Sydir","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jerry Sydir","raw_affiliation_strings":["Intel Corporation,USA","Intel Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation,USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Corporation, USA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7386,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.69929208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9998999834060669,"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/T11409","display_name":"Advanced Wireless Network Optimization","score":0.9993000030517578,"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/T11158","display_name":"Wireless Networks and Protocols","score":0.996399998664856,"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":0.8736358284950256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7969256639480591},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.7254121899604797},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6306264996528625},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6191407442092896},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5593328475952148},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.522772490978241},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4316319227218628},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.37430456280708313},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36444926261901855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30244338512420654},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2869378328323364},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24119797348976135},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.18226158618927002},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07057702541351318},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06977894902229309}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8736358284950256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7969256639480591},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7254121899604797},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6306264996528625},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6191407442092896},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5593328475952148},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.522772490978241},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4316319227218628},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37430456280708313},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36444926261901855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30244338512420654},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2869378328323364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24119797348976135},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.18226158618927002},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07057702541351318},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06977894902229309},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf56349.2022.10051992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf56349.2022.10051992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 56th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W195399875","https://openalex.org/W1598140581","https://openalex.org/W2552014313","https://openalex.org/W2772721022","https://openalex.org/W2791827017","https://openalex.org/W2914552210","https://openalex.org/W2919567238","https://openalex.org/W2962710874","https://openalex.org/W2963079995","https://openalex.org/W2963246369","https://openalex.org/W2969195240","https://openalex.org/W2969525674","https://openalex.org/W2992674761","https://openalex.org/W3005761304","https://openalex.org/W3122789033","https://openalex.org/W3123582921","https://openalex.org/W6677939520","https://openalex.org/W6746809867","https://openalex.org/W6749304979"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W3096874164","https://openalex.org/W1589140671","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W1985560493","https://openalex.org/W2294884454","https://openalex.org/W2937181779"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,28,39,67,109,115,120],"multi-agent":[3],"reinforcement":[4],"learning":[5],"(MARL)":[6],"solution":[7,62],"for":[8,46],"the":[9,25,75,89],"user":[10],"scheduling":[11],"problem":[12,26],"in":[13,27,66],"cellular":[14],"networks.":[15],"Incorporating":[16],"features":[17],"of":[18,42,52,91,96,122],"this":[19],"particular":[20],"use":[21],"case,":[22],"we":[23],"cast":[24],"decentralized":[29,48],"partially":[30],"observable":[31],"Markov":[32],"decision":[33],"process":[34],"(Dec-POMDP)":[35],"framework,":[36],"and":[37,58,99,108],"present":[38],"detailed":[40],"design":[41],"MARL":[43,53,72,98],"that":[44],"allows":[45],"fully":[47],"execution.":[49],"The":[50,94],"performance":[51,133],"against":[54],"both":[55,97],"centralized":[56,81,100],"RL":[57,101,137],"an":[59],"engineering":[60],"heuristic":[61],"is":[63,105,124],"comprehensively":[64],"evaluated":[65],"system-level":[68],"simulation.":[69],"In":[70],"particular,":[71],"achieves":[73],"almost":[74],"same":[76],"total":[77],"system":[78],"reward":[79],"as":[80],"RL,":[82],"while":[83,130],"enjoying":[84],"much":[85],"better":[86],"scalability":[87],"with":[88,134],"number":[90],"base":[92],"stations.":[93],"transferability":[95],"to":[102,126],"new":[103],"environments":[104,123],"also":[106],"investigated,":[107],"simple":[110],"fine-tuning":[111],"approach":[112],"based":[113],"on":[114,119],"general":[116],"model":[117],"trained":[118,136],"pool":[121],"shown":[125],"have":[127],"faster":[128],"convergence":[129],"achieving":[131],"comparable":[132],"individually":[135],"agents,":[138],"demonstrating":[139],"its":[140],"generalization":[141],"capability.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}