{"id":"https://openalex.org/W4408697192","doi":"https://doi.org/10.1109/itsc58415.2024.10920085","title":"Efficient Replay Memory Architectures in Multi-Agent Reinforcement Learning for Traffic Congestion Control","display_name":"Efficient Replay Memory Architectures in Multi-Agent Reinforcement Learning for Traffic Congestion Control","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4408697192","doi":"https://doi.org/10.1109/itsc58415.2024.10920085"},"language":"en","primary_location":{"id":"doi:10.1109/itsc58415.2024.10920085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc58415.2024.10920085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","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/A5093459980","display_name":"Mukul Chodhary","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Mukul Chodhary","raw_affiliation_strings":["University of Melbourne,Department of Electrical and Electronic Engineering,Australia"],"affiliations":[{"raw_affiliation_string":"University of Melbourne,Department of Electrical and Electronic Engineering,Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099380883","display_name":"Kevin Octavian","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kevin Octavian","raw_affiliation_strings":["School of Electrical Engineering, KAIST,S. Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST,S. Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014662969","display_name":"SooJean Han","orcid":"https://orcid.org/0000-0003-1195-6465"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"SooJean Han","raw_affiliation_strings":["School of Electrical Engineering, KAIST,S. Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST,S. Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093459980"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":0.3755,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67494975,"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":"1932","last_page":"1937"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10138","display_name":"Network Traffic and Congestion Control","score":0.9412000179290771,"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"}},"topics":[{"id":"https://openalex.org/T10138","display_name":"Network Traffic and Congestion Control","score":0.9412000179290771,"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":0.8078886270523071},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7562939524650574},{"id":"https://openalex.org/keywords/network-congestion","display_name":"Network congestion","score":0.5539358258247375},{"id":"https://openalex.org/keywords/slow-start","display_name":"Slow-start","score":0.4902794659137726},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4297224283218384},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.36379700899124146},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3372410535812378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3265197277069092},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.058641284704208374}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8078886270523071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562939524650574},{"id":"https://openalex.org/C195563490","wikidata":"https://www.wikidata.org/wiki/Q180368","display_name":"Network congestion","level":3,"score":0.5539358258247375},{"id":"https://openalex.org/C15195413","wikidata":"https://www.wikidata.org/wiki/Q2835766","display_name":"Slow-start","level":4,"score":0.4902794659137726},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4297224283218384},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.36379700899124146},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3372410535812378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3265197277069092},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.058641284704208374}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc58415.2024.10920085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc58415.2024.10920085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2346736747","https://openalex.org/W3099689767","https://openalex.org/W4214717370","https://openalex.org/W6637967152","https://openalex.org/W6677145610","https://openalex.org/W6694954494","https://openalex.org/W6718359804","https://openalex.org/W6734330393","https://openalex.org/W6747473740","https://openalex.org/W6751796012","https://openalex.org/W6780404908","https://openalex.org/W6878564044"],"related_works":["https://openalex.org/W2104259103","https://openalex.org/W2185024549","https://openalex.org/W2355205438","https://openalex.org/W2369428326","https://openalex.org/W2356339667","https://openalex.org/W2398114535","https://openalex.org/W2152957590","https://openalex.org/W2915792401","https://openalex.org/W2391249904","https://openalex.org/W2082861166"],"abstract_inverted_index":{"Episodic":[0],"control,":[1],"inspired":[2],"by":[3,25],"the":[4,10,18,31,107,132],"role":[5],"of":[6,21,34,82,91],"episodic":[7,35],"memory":[8,32,54,142],"in":[9,39,106],"human":[11,83],"brain,":[12],"has":[13],"been":[14],"shown":[15],"to":[16,60,62,99,120],"improve":[17],"sample":[19],"inefficiency":[20],"model-free":[22],"reinforcement":[23,64],"learning":[24,65],"reusing":[26],"high-return":[27,101],"past":[28],"experiences.":[29],"However,":[30],"growth":[33,143],"control":[36,69],"is":[37],"undesirable":[38],"large-scale":[40],"multi-agent":[41,63],"problems":[42],"such":[43],"as":[44],"vehicle":[45,157],"traffic":[46],"management.":[47],"This":[48],"paper":[49],"proposes":[50],"a":[51],"novel":[52],"replay":[53],"architecture":[55,77],"called":[56],"Dual-Memory":[57],"Integrated":[58],"Learning,":[59],"augment":[61],"methods":[66],"for":[67],"congestion":[68,154],"via":[70],"adaptive":[71],"light":[72,136],"signal":[73,137],"scheduling.":[74],"Our":[75],"dual-memory":[76],"mimics":[78],"two":[79],"core":[80],"capabilities":[81],"decision-making.":[84],"First,":[85],"it":[86,116],"relies":[87],"on":[88,148],"diverse":[89],"types":[90],"memory\u2013semantic":[92],"and":[93,96,109,126,145],"episodic,":[94],"short-term":[95],"long-term\u2013in":[97],"order":[98],"remember":[100],"states":[102,112],"that":[103,113,127],"occur":[104],"often":[105],"network":[108],"filter":[110],"out":[111],"don't.":[114],"Second,":[115],"employs":[117],"equivalence":[118],"classes":[119],"group":[121],"together":[122],"similar":[123],"state-action":[124],"pairs":[125],"can":[128],"be":[129],"controlled":[130],"using":[131],"same":[133],"action":[134],"(i.e.,":[135],"sequence).":[138],"Theoretical":[139],"analyses":[140],"establish":[141],"bounds,":[144],"simulation":[146],"experiments":[147],"several":[149],"intersection":[150],"networks":[151],"showcase":[152],"improved":[153],"performance":[155],"(e.g.,":[156],"throughput)":[158],"from":[159],"our":[160],"method.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}