{"id":"https://openalex.org/W4308080248","doi":"https://doi.org/10.1109/itsc55140.2022.9922382","title":"Cooperative Learning with Difference Reward in Large-Scale Traffic Signal Control","display_name":"Cooperative Learning with Difference Reward in Large-Scale Traffic Signal Control","publication_year":2022,"publication_date":"2022-10-08","ids":{"openalex":"https://openalex.org/W4308080248","doi":"https://doi.org/10.1109/itsc55140.2022.9922382"},"language":"en","primary_location":{"id":"doi:10.1109/itsc55140.2022.9922382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc55140.2022.9922382","pdf_url":null,"source":{"id":"https://openalex.org/S4363607737","display_name":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 25th 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/A5100400195","display_name":"Shuo Wang","orcid":"https://orcid.org/0000-0003-2746-7949"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuo Wang","raw_affiliation_strings":["Xidian University,State Key Laboratory of Integrated Services Networks,Xi'an,Shaanxi,China,710071","Research Institute of Smart Transportation, Xidian University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"Xidian University,State Key Laboratory of Integrated Services Networks,Xi'an,Shaanxi,China,710071","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Research Institute of Smart Transportation, Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034502293","display_name":"Wenwei Yue","orcid":"https://orcid.org/0000-0002-1890-5911"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwei Yue","raw_affiliation_strings":["Xidian University,State Key Laboratory of Integrated Services Networks,Xi'an,Shaanxi,China,710071","Research Institute of Smart Transportation, Xidian University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"Xidian University,State Key Laboratory of Integrated Services Networks,Xi'an,Shaanxi,China,710071","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Research Institute of Smart Transportation, Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454821","display_name":"Yue Chen","orcid":"https://orcid.org/0000-0002-7594-7587"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Chen","raw_affiliation_strings":["Xidian University,State Key Laboratory of Integrated Services Networks,Xi'an,Shaanxi,China,710071","Research Institute of Smart Transportation, Xidian University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"Xidian University,State Key Laboratory of Integrated Services Networks,Xi'an,Shaanxi,China,710071","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Research Institute of Smart Transportation, Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081899997","display_name":"Xingyi Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyi Ji","raw_affiliation_strings":["Xidian University,State Key Laboratory of Integrated Services Networks,Xi'an,Shaanxi,China,710071","Research Institute of Smart Transportation, Xidian University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"Xidian University,State Key Laboratory of Integrated Services Networks,Xi'an,Shaanxi,China,710071","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Research Institute of Smart Transportation, Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101512598","display_name":"Xinyang Chen","orcid":"https://orcid.org/0000-0003-1145-510X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyang Chen","raw_affiliation_strings":["Xidian University,State Key Laboratory of Integrated Services Networks,Xi'an,Shaanxi,China,710071","Research Institute of Smart Transportation, Xidian University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"Xidian University,State Key Laboratory of Integrated Services Networks,Xi'an,Shaanxi,China,710071","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Research Institute of Smart Transportation, Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091134121","display_name":"Yaokai Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaokai Jin","raw_affiliation_strings":["Tsinglan School,Dongguan,Guangdong,China,523808"],"affiliations":[{"raw_affiliation_string":"Tsinglan School,Dongguan,Guangdong,China,523808","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100400195"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.3538,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44074823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2307","last_page":"2312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10524","display_name":"Traffic control and management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10698","display_name":"Transportation Planning and Optimization","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8377190828323364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6975052952766418},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5837037563323975},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5050135254859924},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4946286380290985},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.44713330268859863},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4379349946975708},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4294765889644623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4160737991333008},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.38456180691719055},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3339540660381317},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12596634030342102}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8377190828323364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6975052952766418},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5837037563323975},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5050135254859924},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4946286380290985},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44713330268859863},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4379349946975708},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4294765889644623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4160737991333008},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.38456180691719055},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3339540660381317},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12596634030342102},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc55140.2022.9922382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc55140.2022.9922382","pdf_url":null,"source":{"id":"https://openalex.org/S4363607737","display_name":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4905520761","display_name":null,"funder_award_id":"U1801266","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1975853843","https://openalex.org/W2088595989","https://openalex.org/W2125001944","https://openalex.org/W2156737235","https://openalex.org/W2292533394","https://openalex.org/W2539998920","https://openalex.org/W2749604329","https://openalex.org/W2766381093","https://openalex.org/W2915117209","https://openalex.org/W2967474307","https://openalex.org/W3011019592","https://openalex.org/W3091240653","https://openalex.org/W3170622943","https://openalex.org/W3184932611","https://openalex.org/W3211938211","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6683195989","https://openalex.org/W6797032949"],"related_works":["https://openalex.org/W2937181779","https://openalex.org/W2947128950","https://openalex.org/W4362598698","https://openalex.org/W3170446423","https://openalex.org/W4362647313","https://openalex.org/W2482498454","https://openalex.org/W3201878770","https://openalex.org/W2353483528","https://openalex.org/W1996326480","https://openalex.org/W4360887216"],"abstract_inverted_index":{"Adaptive":[0],"traffic":[1],"signal":[2],"control":[3],"(ATSC)":[4],"can":[5,149],"ease":[6],"the":[7,57,68,78,90,95,114,136,153,159,166,174,183],"increasing":[8],"congestion":[9],"to":[10,37,61,105,113,122,164],"relieve":[11],"pressure":[12],"on":[13],"metropolitan":[14],"transportation":[15],"systems.":[16],"In":[17],"a":[18,24,98,127,132,144,192],"large-scale":[19,193],"road":[20,160],"network,":[21,161,194],"ATSC":[22,109],"has":[23],"high":[25],"dimensional":[26],"action":[27,59,70],"space,":[28],"which":[29,148],"makes":[30],"training":[31],"very":[32],"slow":[33],"and":[34,64,84,108,187,209],"algorithms":[35],"difficult":[36],"converge":[38,112],"for":[39],"conventional":[40],"centralized":[41],"deep":[42],"reinforcement":[43,48],"learning":[44,49],"(DRL)":[45],"approaches.":[46,215],"Multi-agent":[47],"(MARL)":[50],"approach":[51,186,198],"overcomes":[52,135],"this":[53,124],"issue":[54,139],"by":[55],"decomposing":[56],"joint":[58],"space":[60],"several":[62],"sub-spaces":[63],"each":[65],"agent":[66],"searches":[67],"optimal":[69,115],"in":[71,97,158,191,204],"its":[72,202],"own":[73,88],"space.":[74],"However,":[75],"if":[76],"all":[77],"agents":[79,120,151,177],"make":[80],"their":[81,87,156],"decisions":[82],"independently":[83],"only":[85],"maximize":[86],"reward,":[89,147],"state":[91],"transition":[92],"probability":[93],"of":[94,155,168,206],"environment":[96],"Markov":[99],"decision":[100],"process":[101],"(MDP)":[102],"will":[103,110],"come":[104],"be":[106],"unstable":[107],"not":[111],"policy":[116],"finally.":[117],"To":[118],"let":[119,150],"learn":[121],"cooperate,":[123],"paper":[125],"proposes":[126],"novel":[128],"MARL":[129,197],"method":[130],"where":[131],"difference":[133],"reward":[134,154,208],"credit":[137],"assignment":[138],"among":[140,176],"cooperated":[141],"agents.":[142],"Moreover,":[143],"spatially":[145],"weighted":[146],"consider":[152],"neighbors":[157],"is":[162,178,199,212],"designed":[163],"evaluate":[165],"policies":[167],"decentralized":[169],"actor":[170],"networks":[171],"such":[172],"that":[173,201],"cooperation":[175],"reinforced.":[179],"By":[180],"comparing":[181],"against":[182],"independent":[184],"DRL":[185],"other":[188,214],"multi-agent":[189],"approaches":[190],"our":[195],"proposed":[196],"demonstrated":[200],"effectiveness":[203],"terms":[205],"average":[207],"travel":[210],"delay":[211],"over":[213]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}