{"id":"https://openalex.org/W2734884790","doi":"https://doi.org/10.23919/acc.2017.7963745","title":"Traffic signal control by distributed Reinforcement Learning with min-sum communication","display_name":"Traffic signal control by distributed Reinforcement Learning with min-sum communication","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2734884790","doi":"https://doi.org/10.23919/acc.2017.7963745","mag":"2734884790"},"language":"en","primary_location":{"id":"doi:10.23919/acc.2017.7963745","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2017.7963745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 American Control Conference (ACC)","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/A5101737502","display_name":"Tianshu Chu","orcid":"https://orcid.org/0000-0002-9404-3348"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianshu Chu","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Stanford University, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101422661","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0003-1857-5569"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Stanford University, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101737502"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.207,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.80158015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5095","last_page":"5100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9937999844551086,"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/T10698","display_name":"Transportation Planning and Optimization","score":0.9907000064849854,"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":0.9060883522033691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7787564992904663},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6585313677787781},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.6045510172843933},{"id":"https://openalex.org/keywords/information-exchange","display_name":"Information exchange","score":0.5523786544799805},{"id":"https://openalex.org/keywords/decentralised-system","display_name":"Decentralised system","score":0.5040084719657898},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46586206555366516},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44854021072387695},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43182051181793213},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4273260235786438},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.40948688983917236},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35679107904434204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23556149005889893},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09548842906951904},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08560642600059509}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9060883522033691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7787564992904663},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6585313677787781},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.6045510172843933},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.5523786544799805},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.5040084719657898},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46586206555366516},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44854021072387695},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43182051181793213},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4273260235786438},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40948688983917236},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35679107904434204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23556149005889893},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09548842906951904},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08560642600059509},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc.2017.7963745","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2017.7963745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W33871791","https://openalex.org/W1575592356","https://openalex.org/W1678713393","https://openalex.org/W1928215159","https://openalex.org/W2027628482","https://openalex.org/W2076337359","https://openalex.org/W2110906765","https://openalex.org/W2120346334","https://openalex.org/W2125001944","https://openalex.org/W2146544184","https://openalex.org/W2152430560","https://openalex.org/W2153160520","https://openalex.org/W2160085675","https://openalex.org/W2201282128","https://openalex.org/W2404646363","https://openalex.org/W2485902895","https://openalex.org/W3103910758","https://openalex.org/W4211221179","https://openalex.org/W4214717370","https://openalex.org/W4245296547","https://openalex.org/W6634413486","https://openalex.org/W6637319420","https://openalex.org/W6676769901","https://openalex.org/W6677737365","https://openalex.org/W6682809161","https://openalex.org/W6688215866","https://openalex.org/W7001212498","https://openalex.org/W7011621630"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2928233854","https://openalex.org/W1865684701","https://openalex.org/W2570940879","https://openalex.org/W2889555279","https://openalex.org/W2095708324"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,51],"(RL)":[2],"is":[3,111,124,132],"a":[4,42,104],"promising":[5],"technique":[6,45],"for":[7,102],"adaptive":[8],"signal":[9,24,77],"control":[10,162],"based":[11,85],"on":[12,86],"real-time":[13],"traffic":[14,23],"data.":[15],"However,":[16],"the":[17,32,50,68,92],"implementation":[18],"of":[19,55],"RL":[20,47,149,153],"in":[21],"large-scale":[22,56],"network":[25],"remains":[26],"an":[27],"open":[28],"challenge":[29],"due":[30],"to":[31,97,117,144],"extremely":[33],"high":[34],"computational":[35],"cost.":[36],"In":[37,63],"this":[38,118,147],"paper,":[39],"we":[40,65,140],"integrate":[41],"distributed":[43,148],"communication":[44],"into":[46,71],"so":[48,74],"that":[49,110,146],"and":[52,106,130],"searching":[53],"cost":[54],"multi-agent":[57],"system":[58],"can":[59,79],"be":[60],"significantly":[61],"reduced.":[62],"particular,":[64],"first":[66],"decompose":[67],"global":[69,108],"Q-function":[70],"local":[72,76,87],"Q-functions,":[73],"each":[75],"agent":[78],"compute":[80],"its":[81],"own":[82],"optimal":[83,107,126],"policy":[84,109],"observations.":[88],"We":[89],"then":[90],"apply":[91],"max-sum":[93],"message":[94],"passing":[95],"algorithm":[96],"share":[98],"information":[99,119],"among":[100],"agents,":[101],"finding":[103],"stable":[105],"accepted":[112],"by":[113],"all":[114],"agents.":[115],"Due":[116],"sharing":[120],"characteristic,":[121],"our":[122],"approach":[123,150],"more":[125,134],"than":[127,136],"decentralized":[128,152,161],"RL,":[129],"it":[131],"much":[133],"efficient":[135],"centralized":[137],"RL.":[138],"Further,":[139],"perform":[141],"realistic":[142],"simulation":[143],"demonstrate":[145],"outperforms":[151],"algorithm,":[154],"as":[155,157],"well":[156],"some":[158],"typical":[159],"heuristic":[160],"methods.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}