{"id":"https://openalex.org/W4391770468","doi":"https://doi.org/10.1109/itsc57777.2023.10422534","title":"Large-Scale Traffic Signal Control by a Nash Deep Q-network Approach","display_name":"Large-Scale Traffic Signal Control by a Nash Deep Q-network Approach","publication_year":2023,"publication_date":"2023-09-24","ids":{"openalex":"https://openalex.org/W4391770468","doi":"https://doi.org/10.1109/itsc57777.2023.10422534"},"language":"en","primary_location":{"id":"doi:10.1109/itsc57777.2023.10422534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc57777.2023.10422534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 26th 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/A5101851956","display_name":"Yuli Zhang","orcid":"https://orcid.org/0000-0001-9060-9933"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuli Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054565395","display_name":"Shangbo Wang","orcid":"https://orcid.org/0000-0003-4347-6669"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shangbo Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100873331","display_name":"Xiaoguang Ma","orcid":"https://orcid.org/0009-0009-6839-5428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoguang Ma","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034502293","display_name":"Wenwei Yue","orcid":"https://orcid.org/0000-0002-1890-5911"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenwei Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029311850","display_name":"Ruiyuan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiyuan Jiang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101851956"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3098,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90898079,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4584","last_page":"4591"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9046000242233276,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9046000242233276,"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/computer-science","display_name":"Computer science","score":0.671472430229187},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5347453951835632},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5320141315460205},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.35118329524993896},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.20713138580322266},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15672022104263306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.671472430229187},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5347453951835632},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5320141315460205},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.35118329524993896},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.20713138580322266},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15672022104263306},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc57777.2023.10422534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc57777.2023.10422534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2037067712","https://openalex.org/W2078895652","https://openalex.org/W2120846115","https://openalex.org/W2145339207","https://openalex.org/W2153160520","https://openalex.org/W2485902895","https://openalex.org/W2604427121","https://openalex.org/W2747046834","https://openalex.org/W2794247037","https://openalex.org/W2794842204","https://openalex.org/W2915117209","https://openalex.org/W2945442007","https://openalex.org/W2967474307","https://openalex.org/W2997922319","https://openalex.org/W3011019592","https://openalex.org/W3106357768","https://openalex.org/W3184932611","https://openalex.org/W4212833789","https://openalex.org/W4285104771","https://openalex.org/W4313036208","https://openalex.org/W4394834775","https://openalex.org/W6678168664","https://openalex.org/W6736372492","https://openalex.org/W6838407234"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"is":[3,37,167,208],"currently":[4],"one":[5],"of":[6,46,68,82,108,160,164,174,205,212,224,234,244,254],"the":[7,61,86,106,119,144,161,165,172,182,193,202,206,241,245],"most":[8],"commonly":[9],"used":[10,126],"techniques":[11],"for":[12,196],"traffic":[13,21,29,131,200],"signal":[14,22],"control":[15,67],"(TSC),":[16],"which":[17,104,151],"can":[18,59,170],"adaptively":[19],"adjust":[20],"phase":[23],"and":[24,112,239,261],"duration":[25],"according":[26],"to":[27,142,156],"real-time":[28],"data.":[30],"However,":[31],"a":[32,42,135,198],"fully":[33,110],"centralized":[34,111],"RL":[35,71],"approach":[36,138],"beset":[38],"with":[39,52],"difficulties":[40],"in":[41,49,127,252],"multi-network":[43],"scenario":[44],"because":[45,179,216],"exponential":[47],"growth":[48],"state-action":[50,129],"space":[51,130],"increasing":[53],"intersections.":[54],"Multi-agent":[55],"reinforcement":[56],"learning":[57],"(MARL)":[58],"overcome":[60],"high-dimension":[62],"problem":[63,120],"by":[64,85,133,150,188,231],"employing":[65],"global":[66],"each":[69,140,225],"local":[70],"agent,":[72],"but":[73],"it":[74,169,180,217],"also":[75],"brings":[76],"new":[77],"challenges,":[78],"such":[79],"as":[80],"failures":[81],"convergence":[83,203],"caused":[84],"non-stationary":[87],"Markov":[88,177],"Decision":[89],"Process":[90],"(MDP).":[91],"In":[92],"this":[93],"paper,":[94],"we":[95],"introduce":[96],"an":[97],"off-policy":[98],"nash":[99,145],"deep":[100],"Q-Network":[101],"(OPNDQN)":[102],"algorithm,":[103],"mitigates":[105],"weakness":[107],"both":[109],"MARL":[113,214,250],"approaches.":[114],"The":[115],"OPNDQN":[116,166,207,246],"algorithm":[117],"solves":[118],"that":[121,168,211],"traditional":[122],"algorithms":[123],"cannot":[124],"be":[125],"large":[128,199],"models":[132],"utilizing":[134],"fictitious":[136],"game":[137],"at":[139],"iteration":[141],"find":[143],"equilibrium":[146],"among":[147,185],"neighboring":[148,186],"intersections,":[149],"no":[152],"intersection":[153],"has":[154],"incentive":[155],"unilaterally":[157],"deviate.":[158],"One":[159],"main":[162],"advantages":[163],"mitigate":[171],"non-stationarity":[173],"multi":[175],"agent":[176],"process":[178],"considers":[181],"mutual":[183],"influence":[184],"intersections":[187],"sharing":[189],"their":[190],"actions.":[191],"On":[192],"other":[194],"hand,":[195],"training":[197,259],"network,":[201],"rate":[204],"higher":[209],"than":[210],"existing":[213,249],"approaches":[215,251],"does":[218],"not":[219],"incorporate":[220],"all":[221],"state":[222],"information":[223],"agent.":[226],"We":[227],"conduct":[228],"extensive":[229],"experiments":[230],"using":[232],"Simulation":[233],"Urban":[235],"MObility":[236],"simulator":[237],"(SUMO),":[238],"show":[240],"dominant":[242],"superiority":[243],"over":[247],"several":[248],"terms":[253],"average":[255,262],"queue":[256],"length,":[257],"episode":[258],"reward":[260],"waiting":[263],"time.":[264]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}