{"id":"https://openalex.org/W4313547795","doi":"https://doi.org/10.1109/tkde.2022.3232711","title":"MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal Control","display_name":"MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal Control","publication_year":2023,"publication_date":"2023-01-04","ids":{"openalex":"https://openalex.org/W4313547795","doi":"https://doi.org/10.1109/tkde.2022.3232711"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2022.3232711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3232711","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Knowledge and Data Engineering","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/A5043087288","display_name":"Liwen Zhu","orcid":"https://orcid.org/0000-0001-7818-0767"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liwen Zhu","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7818-0767","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070755370","display_name":"Peixi Peng","orcid":"https://orcid.org/0000-0002-7427-8764"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peixi Peng","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","Pengcheng Laboratory, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-7427-8764","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089642905","display_name":"Zongqing Lu","orcid":"https://orcid.org/0000-0003-3967-2704"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongqing Lu","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","Pengcheng Laboratory, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0003-3967-2704","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023918894","display_name":"Yonghong Tian","orcid":"https://orcid.org/0000-0002-2978-5935"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Tian","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","Pengcheng Laboratory, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-2978-5935","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8884,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.96788926,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"35","issue":"11","first_page":"11570","last_page":"11584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9994999766349792,"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":0.9994999766349792,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9932000041007996,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9902999997138977,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7817010879516602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7679606676101685},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.47465449571609497},{"id":"https://openalex.org/keywords/traffic-signal","display_name":"Traffic signal","score":0.4517742991447449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33325356245040894},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.11073389649391174}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7817010879516602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7679606676101685},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.47465449571609497},{"id":"https://openalex.org/C2987419075","wikidata":"https://www.wikidata.org/wiki/Q8004","display_name":"Traffic signal","level":2,"score":0.4517742991447449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33325356245040894},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.11073389649391174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2022.3232711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3232711","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4587952244","display_name":null,"funder_award_id":"62027804","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6662223526","display_name":null,"funder_award_id":"61825101","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":103,"referenced_works":["https://openalex.org/W5525483","https://openalex.org/W138497752","https://openalex.org/W573924038","https://openalex.org/W1516835682","https://openalex.org/W1639167632","https://openalex.org/W1959608418","https://openalex.org/W2022686149","https://openalex.org/W2074500080","https://openalex.org/W2078895652","https://openalex.org/W2088595989","https://openalex.org/W2114014700","https://openalex.org/W2116459397","https://openalex.org/W2141205378","https://openalex.org/W2146544184","https://openalex.org/W2236244207","https://openalex.org/W2480177474","https://openalex.org/W2498688231","https://openalex.org/W2518481136","https://openalex.org/W2536412503","https://openalex.org/W2578206533","https://openalex.org/W2596982695","https://openalex.org/W2604763608","https://openalex.org/W2736601468","https://openalex.org/W2747213132","https://openalex.org/W2788904251","https://openalex.org/W2809148419","https://openalex.org/W2885550588","https://openalex.org/W2900019936","https://openalex.org/W2904065660","https://openalex.org/W2913682358","https://openalex.org/W2914351253","https://openalex.org/W2915117209","https://openalex.org/W2945991855","https://openalex.org/W2949475445","https://openalex.org/W2950149761","https://openalex.org/W2952526277","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2964749398","https://openalex.org/W2980555752","https://openalex.org/W2982172847","https://openalex.org/W2983178256","https://openalex.org/W2985159211","https://openalex.org/W2988973041","https://openalex.org/W2998187693","https://openalex.org/W2998332605","https://openalex.org/W3005980215","https://openalex.org/W3016406232","https://openalex.org/W3022124161","https://openalex.org/W3022718705","https://openalex.org/W3026400623","https://openalex.org/W3032694630","https://openalex.org/W3034604283","https://openalex.org/W3039969618","https://openalex.org/W3041789421","https://openalex.org/W3086530824","https://openalex.org/W3088611441","https://openalex.org/W3092592791","https://openalex.org/W3093139241","https://openalex.org/W3098136553","https://openalex.org/W3108204548","https://openalex.org/W3149457451","https://openalex.org/W3169864268","https://openalex.org/W3172485314","https://openalex.org/W3173760308","https://openalex.org/W3183523595","https://openalex.org/W3188474345","https://openalex.org/W3208966735","https://openalex.org/W3211801683","https://openalex.org/W3212678506","https://openalex.org/W3216065394","https://openalex.org/W4287692003","https://openalex.org/W4288357413","https://openalex.org/W4297791094","https://openalex.org/W4297804636","https://openalex.org/W4300799055","https://openalex.org/W6605711098","https://openalex.org/W6616526780","https://openalex.org/W6638893446","https://openalex.org/W6640963894","https://openalex.org/W6687236050","https://openalex.org/W6717230150","https://openalex.org/W6730641667","https://openalex.org/W6731982132","https://openalex.org/W6734097942","https://openalex.org/W6735033012","https://openalex.org/W6736057607","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6748271565","https://openalex.org/W6748600884","https://openalex.org/W6753925943","https://openalex.org/W6758763022","https://openalex.org/W6760698134","https://openalex.org/W6762408531","https://openalex.org/W6769269530","https://openalex.org/W6776731554","https://openalex.org/W6783867858","https://openalex.org/W6783962090","https://openalex.org/W6784051664","https://openalex.org/W6790269317","https://openalex.org/W6797876208","https://openalex.org/W6803206360"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W4367838498","https://openalex.org/W4293167677"],"abstract_inverted_index":{"Traffic":[0],"signal":[1,30,40,72,231],"control":[2,31,96,232],"aims":[3],"to":[4,10,28,91,118,150,178,193,229,254,271,283,292],"coordinate":[5],"traffic":[6,13,29,39,71,104,230],"signals":[7,105],"across":[8],"intersections":[9],"improve":[11],"the":[12,59,63,66,69,82,85,95,123,127,135,141,143,151,159,170,195,212,241,245,256,265,273,308],"efficiency":[14],"of":[15,68,97,102,222,244],"a":[16,19,98,110,174,182,206,216,220,248,277],"district":[17],"or":[18],"city.":[20],"Deep":[21],"reinforcement":[22],"learning":[23,214,275],"(RL)":[24],"has":[25],"been":[26],"applied":[27],"recently":[32],"and":[33,81,87,113,154,260,289,315],"demonstrated":[34],"promising":[35],"performance":[36],"where":[37,225],"each":[38,199,226,285],"is":[41,73,106,130,191,252,261,281],"regarded":[42,239],"as":[43,109,215,240],"an":[44,234],"agent.":[45],"However,":[46],"there":[47],"are":[48,238],"still":[49],"several":[50],"challenges":[51],"that":[52,201,307],"may":[53],"limit":[54],"its":[55,78,88,298],"large-scale":[56],"application":[57],"in":[58,161,205],"real":[60],"world.":[61],"On":[62,122],"one":[64],"hand,":[65,125],"policy":[67,128,144,171,197,213,266,274],"current":[70,136],"often":[74,164],"heavily":[75],"influenced":[76],"by":[77],"neighbor":[79,203],"agents,":[80],"coordination":[83],"between":[84],"agent":[86],"neighbors":[89,237],"needs":[90],"be":[92,119,147,293],"considered.":[93],"Hence,":[94],"road":[99],"network":[100],"composed":[101],"multiple":[103],"naturally":[107],"modeled":[108],"multi-agent":[111],"system,":[112],"all":[114],"agents\u2019":[115],"policies":[116],"need":[117],"optimized":[120],"simultaneously.":[121],"other":[124],"once":[126],"function":[129,145],"conditioned":[131,296],"on":[132,297,304],"not":[133],"only":[134,295],"agent's":[137,286],"observation":[138,290],"but":[139],"also":[140],"neighbors\u2019,":[142],"would":[146],"closely":[148],"related":[149,223],"training":[152,175],"scenario":[153,176],"cause":[155],"poor":[156],"generalizability":[157],"because":[158],"agents":[160],"various":[162],"scenarios":[163],"have":[165],"heterogeneous":[166],"neighbors.":[167],"To":[168],"make":[169,272],"learned":[172,249],"from":[173],"generalizable":[177],"new":[179],"unseen":[180],"scenarios,":[181],"novel":[183,278],"Meta":[184],"Variationally":[185],"Intrinsic":[186],"Motivated":[187],"(MetaVIM)":[188],"RL":[189],"method":[190,310],"proposed":[192,309],"learn":[194],"decentralized":[196],"for":[198,267],"intersection":[200,235],"considers":[202],"information":[204,259],"latent":[207,250],"way.":[208],"Specifically,":[209],"we":[210],"formulate":[211],"meta-learning":[217],"problem":[218],"over":[219],"set":[221],"tasks,":[224],"task":[227],"corresponds":[228],"at":[233],"whose":[236],"unobserved":[242],"part":[243],"state.":[246],"Then,":[247],"variable":[251],"introduced":[253],"represent":[255],"task's":[257],"specific":[258],"further":[262],"brought":[263],"into":[264],"learning.":[268],"In":[269],"addition,":[270],"stable,":[276],"intrinsic":[279],"reward":[280],"designed":[282],"encourage":[284],"received":[287],"rewards":[288],"transition":[291],"predictable":[294],"own":[299],"history.":[300],"Extensive":[301],"experiments":[302],"conducted":[303],"CityFlow":[305],"demonstrate":[306],"substantially":[311],"outperforms":[312],"existing":[313],"approaches":[314],"shows":[316],"superior":[317],"generalizability.":[318]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}