{"id":"https://openalex.org/W3175224103","doi":"https://doi.org/10.1109/tvt.2021.3090796","title":"Independent Reinforcement Learning for Weakly Cooperative Multiagent Traffic Control Problem","display_name":"Independent Reinforcement Learning for Weakly Cooperative Multiagent Traffic Control Problem","publication_year":2021,"publication_date":"2021-06-22","ids":{"openalex":"https://openalex.org/W3175224103","doi":"https://doi.org/10.1109/tvt.2021.3090796","mag":"3175224103"},"language":"en","primary_location":{"id":"doi:10.1109/tvt.2021.3090796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvt.2021.3090796","pdf_url":null,"source":{"id":"https://openalex.org/S10936095","display_name":"IEEE Transactions on Vehicular Technology","issn_l":"0018-9545","issn":["0018-9545","1939-9359"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Vehicular Technology","raw_type":"journal-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/A5007940280","display_name":"Chengwei Zhang","orcid":"https://orcid.org/0000-0002-9157-6050"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chengwei Zhang","raw_affiliation_strings":["School of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-9157-6050","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045118907","display_name":"Shan Jin","orcid":"https://orcid.org/0000-0002-4152-4498"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Jin","raw_affiliation_strings":["School of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027220635","display_name":"Wanli Xue","orcid":"https://orcid.org/0000-0002-6031-9334"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanli Xue","raw_affiliation_strings":["Key Laboratory of Computer Vision and Systems (Ministry of Education), School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-6031-9334","affiliations":[{"raw_affiliation_string":"Key Laboratory of Computer Vision and Systems (Ministry of Education), School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084396416","display_name":"Xiaofei Xie","orcid":"https://orcid.org/0000-0002-1288-6502"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaofei Xie","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055627037","display_name":"Shengyong Chen","orcid":"https://orcid.org/0000-0002-6705-3831"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyong Chen","raw_affiliation_strings":["Key Laboratory of Computer Vision and Systems (Ministry of Education), School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-6705-3831","affiliations":[{"raw_affiliation_string":"Key Laboratory of Computer Vision and Systems (Ministry of Education), School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418997","display_name":"Rong Chen","orcid":"https://orcid.org/0000-0001-5848-6398"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Chen","raw_affiliation_strings":["School of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5007940280"],"corresponding_institution_ids":["https://openalex.org/I43313876"],"apc_list":null,"apc_paid":null,"fwci":3.469,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.92806191,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"70","issue":"8","first_page":"7426","last_page":"7436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9998000264167786,"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":0.9998000264167786,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.9839000105857849,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8655861616134644},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.7304898500442505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6710085868835449},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5416392087936401},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4446236491203308},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4352490305900574},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4292716383934021},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42332321405410767},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3908849358558655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38565707206726074},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1612478494644165},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1565493941307068},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.1301402449607849}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8655861616134644},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.7304898500442505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6710085868835449},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5416392087936401},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4446236491203308},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4352490305900574},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4292716383934021},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42332321405410767},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3908849358558655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38565707206726074},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1612478494644165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1565493941307068},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.1301402449607849},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvt.2021.3090796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvt.2021.3090796","pdf_url":null,"source":{"id":"https://openalex.org/S10936095","display_name":"IEEE Transactions on Vehicular Technology","issn_l":"0018-9545","issn":["0018-9545","1939-9359"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Vehicular Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G158084726","display_name":null,"funder_award_id":"2019M661080","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G3462807737","display_name":null,"funder_award_id":"61906135","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7807189742","display_name":null,"funder_award_id":"61906027","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7851850124","display_name":null,"funder_award_id":"2020JQ-070","funder_id":"https://openalex.org/F4320324173","funder_display_name":"Natural Science Foundation of Shaanxi Province"},{"id":"https://openalex.org/G964132629","display_name":null,"funder_award_id":"61803295","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"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320324173","display_name":"Natural Science Foundation of Shaanxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W107853361","https://openalex.org/W1192553058","https://openalex.org/W1516835682","https://openalex.org/W1641379095","https://openalex.org/W1928215159","https://openalex.org/W2085046200","https://openalex.org/W2096145798","https://openalex.org/W2104602264","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2175545073","https://openalex.org/W2210077926","https://openalex.org/W2466211196","https://openalex.org/W2498017881","https://openalex.org/W2604873668","https://openalex.org/W2626637010","https://openalex.org/W2734878594","https://openalex.org/W2746553466","https://openalex.org/W2794842204","https://openalex.org/W2904065660","https://openalex.org/W2913364981","https://openalex.org/W2915117209","https://openalex.org/W2944633916","https://openalex.org/W2945991855","https://openalex.org/W2946606218","https://openalex.org/W2946764808","https://openalex.org/W2949963774","https://openalex.org/W2951799221","https://openalex.org/W2951896791","https://openalex.org/W2963715810","https://openalex.org/W2983178256","https://openalex.org/W2995815314","https://openalex.org/W3102059892","https://openalex.org/W3106357768","https://openalex.org/W4288357413","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W6604355337","https://openalex.org/W6628769285","https://openalex.org/W6637033378","https://openalex.org/W6675811377","https://openalex.org/W6685444567","https://openalex.org/W6688475801","https://openalex.org/W6719729129","https://openalex.org/W6736572398","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6741408367","https://openalex.org/W6749304979","https://openalex.org/W6754887573","https://openalex.org/W6762408531","https://openalex.org/W6762491519","https://openalex.org/W6763150730","https://openalex.org/W6771514159","https://openalex.org/W7001212498"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"The":[0,193],"adaptive":[1],"traffic":[2,25,86,109,151,229,234],"signal":[3],"control":[4],"(ATSC)":[5],"problem":[6,58,95,102],"can":[7],"be":[8],"modeled":[9],"as":[10,103],"a":[11,104,114],"multiagent":[12],"cooperative":[13,108,127,141,158],"game":[14],"among":[15],"urban":[16,85],"intersections,":[17],"where":[18],"intersections":[19,82],"cooperate":[20],"to":[21,44,92,138],"counter":[22],"the":[23,48,53,61,71,78,120,129,140,150,156,183,188,197,203,208,212,221],"city's":[24],"conditions.":[26],"Recently,":[27],"reinforcement":[28],"learning":[29,72,130],"(RL)":[30],"has":[31],"achieved":[32],"marked":[33],"successes":[34],"in":[35,47,83,96,125,135,202,226,242],"managing":[36],"sequential":[37],"decision":[38],"making":[39],"problems,":[40],"which":[41,69,145,174],"motivates":[42],"us":[43],"apply":[45],"RL":[46,75,91],"ATSC":[49,94,101],"problem.":[50],"One":[51],"of":[52,56,63,74,81,122,132,143,160,199,247],"largest":[54],"challenges":[55],"this":[57,97],"is":[59,65,137,146],"that":[60,118],"observation":[62],"intersection":[64,134],"typically":[66],"partially":[67,105],"observable,":[68],"limits":[70],"performance":[73,245],"algorithms.":[76],"Considering":[77],"large":[79],"scale":[80],"an":[84,164],"environment,":[87],"we":[88,162],"use":[89],"independent":[90],"solve":[93],"study.":[98],"We":[99],"model":[100,110],"observable":[106],"weak":[107],"(PO-WCTM).":[111],"Different":[112],"from":[113],"traditional":[115],"IRL":[116,165],"task":[117],"averages":[119],"returns":[121],"all":[123,244],"agents":[124],"fully":[126],"games,":[128],"goal":[131],"each":[133],"PO-WCTM":[136],"reduce":[139],"difficulty":[142],"learning,":[144],"also":[147],"consistent":[148],"with":[149,215],"environment":[152],"hypothesis.":[153],"To":[154],"achieve":[155],"optimal":[157],"strategy":[159],"PO-WCTM,":[161],"propose":[163],"algorithm":[166,179],"called":[167],"Cooperative":[168],"Important":[169],"Lenient":[170],"Double":[171,176],"DQN":[172,177],"(CIL-DDQN),":[173],"extends":[175],"(DDQN)":[178],"using":[180],"two":[181,227],"mechanisms:":[182],"forgetful":[184],"experience":[185,204],"mechanism":[186,195,210],"and":[187,218,231],"lenient":[189],"weight":[190,213],"training":[191],"mechanism.":[192],"former":[194],"decreases":[196],"importance":[198],"experiences":[200,214],"stored":[201],"reply":[205],"buffers,":[206],"while":[207],"latter":[209],"increases":[211],"high":[216],"estimation":[217],"`leniently'":[219],"trains":[220],"DDQN":[222],"neural":[223],"network.":[224],"Experiments":[225],"real":[228],"scenarios":[230,235],"one":[232],"simulated":[233],"show":[236],"that,":[237],"CIL-DDQN":[238],"outperforms":[239],"other":[240],"methods":[241],"almost":[243],"indicators":[246],"ATSC.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
