{"id":"https://openalex.org/W4385815493","doi":"https://doi.org/10.1109/vtc2023-spring57618.2023.10199985","title":"Stochastic Graph Neural Network-Based Value Decomposition for Multi-Agent Reinforcement Learning in Urban Traffic Control","display_name":"Stochastic Graph Neural Network-Based Value Decomposition for Multi-Agent Reinforcement Learning in Urban Traffic Control","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4385815493","doi":"https://doi.org/10.1109/vtc2023-spring57618.2023.10199985"},"language":"en","primary_location":{"id":"doi:10.1109/vtc2023-spring57618.2023.10199985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vtc2023-spring57618.2023.10199985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring)","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/A5038569685","display_name":"Baidi Xiao","orcid":"https://orcid.org/0009-0004-5913-1109"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Baidi Xiao","raw_affiliation_strings":["Zhejiang University,College of Information Science and Electronic Engineering","College of Information Science and Electronic Engineering, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Information Science and Electronic Engineering","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014842979","display_name":"Rongpeng Li","orcid":"https://orcid.org/0000-0003-4297-5060"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongpeng Li","raw_affiliation_strings":["Zhejiang University,College of Information Science and Electronic Engineering","College of Information Science and Electronic Engineering, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Information Science and Electronic Engineering","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455816","display_name":"Fei Wang","orcid":"https://orcid.org/0009-0002-3022-3101"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fei Wang","raw_affiliation_strings":["Huawei Technologies"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059795762","display_name":"Chenghui Peng","orcid":"https://orcid.org/0000-0002-1080-4665"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chenghui Peng","raw_affiliation_strings":["Huawei Technologies"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100599435","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3394-1507"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianjun Wu","raw_affiliation_strings":["Huawei Technologies"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036831868","display_name":"Zhifeng Zhao","orcid":"https://orcid.org/0000-0002-5479-7890"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Zhao","raw_affiliation_strings":["Zhejiang University,Zhejiang Lab","Zhejiang Lab, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Zhejiang Lab","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang Lab, Zhejiang University","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100626780","display_name":"Honggang Zhang","orcid":"https://orcid.org/0000-0003-1492-1364"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honggang Zhang","raw_affiliation_strings":["Zhejiang University,Zhejiang Lab","Zhejiang Lab, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Zhejiang Lab","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang Lab, Zhejiang University","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5038569685"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.0474,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81173102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9948999881744385,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.9850000143051147,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7786520719528198},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.629002034664154},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5485854148864746},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5439742207527161},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.49401718378067017},{"id":"https://openalex.org/keywords/stochastic-neural-network","display_name":"Stochastic neural network","score":0.4649936258792877},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.4498717188835144},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44057127833366394},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.43204164505004883},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.4029008746147156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3619442582130432},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3503517210483551},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.3379591405391693},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22930559515953064},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20470961928367615},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.1929033398628235}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7786520719528198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.629002034664154},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5485854148864746},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5439742207527161},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.49401718378067017},{"id":"https://openalex.org/C86582703","wikidata":"https://www.wikidata.org/wiki/Q7617824","display_name":"Stochastic neural network","level":4,"score":0.4649936258792877},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.4498717188835144},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44057127833366394},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.43204164505004883},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.4029008746147156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3619442582130432},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3503517210483551},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.3379591405391693},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22930559515953064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20470961928367615},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.1929033398628235},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vtc2023-spring57618.2023.10199985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vtc2023-spring57618.2023.10199985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.8299999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W2610267922","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2747213132","https://openalex.org/W2899076365","https://openalex.org/W2907492528","https://openalex.org/W2951799221","https://openalex.org/W2963186244","https://openalex.org/W2964015378","https://openalex.org/W2969525674","https://openalex.org/W2997070234","https://openalex.org/W3091266930","https://openalex.org/W3118993660","https://openalex.org/W3176265013","https://openalex.org/W3176675329","https://openalex.org/W4206560593","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W4301204068","https://openalex.org/W6685444567","https://openalex.org/W6726873649","https://openalex.org/W6738796088","https://openalex.org/W6749304979","https://openalex.org/W6755921573","https://openalex.org/W6787618087"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548"],"abstract_inverted_index":{"Multi-Agent":[0],"Reinforcement":[1],"Learning":[2],"(MARL)":[3],"has":[4],"reached":[5],"astonishing":[6],"achievements":[7],"in":[8,18,77,95,141],"various":[9],"fields":[10],"such":[11],"as":[12],"the":[13,33,43,48,51,54,63,71,108,113,117,127,146,151,155],"traffic":[14],"control":[15],"of":[16,36,42,50,148,157],"vehicles":[17],"a":[19,29,90,100,121],"wireless":[20,58],"connected":[21],"environment.":[22],"In":[23,125],"MARL,":[24],"how":[25],"to":[26,40,79,88,135],"effectively":[27,136],"decompose":[28],"global":[30],"feedback":[31],"into":[32,112,120],"relative":[34],"contributions":[35],"individual":[37],"agents":[38],"belongs":[39],"one":[41],"most":[44],"fundamental":[45],"problems.":[46],"However,":[47],"volatility":[49],"environment":[52,152],"(e.g.,":[53],"vehicle":[55],"movement":[56],"and":[57,115,144],"disturbance)":[59],"could":[60],"significantly":[61],"shape":[62],"time-varying":[64],"topological":[65,110,142],"relationships":[66],"among":[67],"agents,":[68],"thus":[69],"making":[70],"Value":[72],"Decomposition":[73],"(VD)":[74],"challenging.":[75],"Therefore,":[76],"order":[78],"cope":[80],"with":[81],"this":[82,96],"annoying":[83],"volatility,":[84],"it":[85],"becomes":[86],"imperative":[87],"design":[89],"dynamic":[91,109],"VD":[92,114,149],"framework.":[93],"Hence,":[94],"paper,":[97],"we":[98],"propose":[99],"novel":[101],"Stochastic":[102,128],"VMIX":[103],"(SVMIX)":[104],"methodology":[105],"by":[106],"embedding":[107],"features":[111,143],"incorporating":[116],"corresponding":[118],"components":[119],"multi-agent":[122],"actor-critic":[123],"architecture.":[124],"particular,":[126],"Graph":[129],"Neural":[130],"Network":[131],"(SGNN)":[132],"is":[133,159],"leveraged":[134],"extract":[137],"underlying":[138],"dynamics":[139],"embedded":[140],"improve":[145],"flexibility":[147],"against":[150],"volatility.":[153],"Finally,":[154],"superiority":[156],"SVMIX":[158],"verified":[160],"through":[161],"extensive":[162],"simulations.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}