{"id":"https://openalex.org/W3114499307","doi":"https://doi.org/10.1109/itsc45102.2020.9294623","title":"Multi-Agent Reinforcement Learning for Traffic Signal Control: Algorithms and Robustness Analysis","display_name":"Multi-Agent Reinforcement Learning for Traffic Signal Control: Algorithms and Robustness Analysis","publication_year":2020,"publication_date":"2020-09-20","ids":{"openalex":"https://openalex.org/W3114499307","doi":"https://doi.org/10.1109/itsc45102.2020.9294623","mag":"3114499307"},"language":"en","primary_location":{"id":"doi:10.1109/itsc45102.2020.9294623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc45102.2020.9294623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5051576682","display_name":"Chunliang Wu","orcid":"https://orcid.org/0000-0003-1663-9581"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chunliang Wu","raw_affiliation_strings":["Institute of Transport Studies, Monash University, Clayton, VIC, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Transport Studies, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072433020","display_name":"Zhenliang Ma","orcid":"https://orcid.org/0000-0002-2141-0389"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhenliang Ma","raw_affiliation_strings":["Institute of Transport Studies, Monash University, Clayton, VIC, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Transport Studies, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":null,"display_name":"Inhi Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Inhi Kim","raw_affiliation_strings":["Institute of Transport Studies, Monash University, Clayton, VIC, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Transport Studies, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I56590836"],"apc_list":null,"apc_paid":null,"fwci":1.2354,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78092584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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/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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9997000098228455,"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":0.9933000206947327,"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/robustness","display_name":"Robustness (evolution)","score":0.8596183061599731},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8002309203147888},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7234978079795837},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6416938304901123},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.5450111627578735},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.4044187664985657},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.36089324951171875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2888094186782837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2846931219100952},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.1585180163383484}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8596183061599731},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8002309203147888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7234978079795837},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6416938304901123},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.5450111627578735},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4044187664985657},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.36089324951171875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2888094186782837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2846931219100952},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.1585180163383484},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc45102.2020.9294623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc45102.2020.9294623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W33871791","https://openalex.org/W116194267","https://openalex.org/W138497752","https://openalex.org/W1966071304","https://openalex.org/W1969758122","https://openalex.org/W2019974229","https://openalex.org/W2048041430","https://openalex.org/W2074500080","https://openalex.org/W2101460915","https://openalex.org/W2101786389","https://openalex.org/W2112597014","https://openalex.org/W2173564293","https://openalex.org/W2210077926","https://openalex.org/W2498017881","https://openalex.org/W2562823341","https://openalex.org/W2725582697","https://openalex.org/W2766381093","https://openalex.org/W2770423710","https://openalex.org/W2794842204","https://openalex.org/W2811198925","https://openalex.org/W2895793836","https://openalex.org/W2914656440","https://openalex.org/W2915117209","https://openalex.org/W2951799221","https://openalex.org/W2963027910","https://openalex.org/W2991611854","https://openalex.org/W3100789280","https://openalex.org/W3106357768","https://openalex.org/W3216334156","https://openalex.org/W4232053133","https://openalex.org/W6685444567","https://openalex.org/W6688475801","https://openalex.org/W6730787115","https://openalex.org/W7011621630"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W4381094582","https://openalex.org/W1978893398","https://openalex.org/W2357124094","https://openalex.org/W1977906818","https://openalex.org/W2201908702","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1522139108","https://openalex.org/W2937790267"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,53,75],"(RL),":[2],"given":[3],"its":[4,158],"adaptability":[5],"and":[6,26,59,87,102,122,127,132,156,173],"generality,":[7],"has":[8,176],"great":[9],"potential":[10],"to":[11,67,79],"optimize":[12],"online":[13,155],"traffic":[14,45,56,93,97,100,120,124,165,170],"signal":[15,24,57,70],"control":[16,58,71,89,114],"strategies.":[17],"Although":[18],"studies":[19],"have":[20],"proposed":[21,49,85,112],"various":[22],"RL-based":[23,38,113,150],"controllers":[25,39],"validated":[27],"them":[28],"offline,":[29],"very":[30],"few":[31],"examine":[32],"the":[33,36,81,84,111,130,140,148,163,169,174],"robustness":[34,82],"of":[35,83,142],"trained":[37,149],"when":[40,168],"deployed":[41],"in":[42,139],"a":[43,50,61],"dynamic":[44,164],"environment.":[46],"This":[47],"paper":[48],"multi-agent":[51,63],"reinforcement":[52],"algorithm":[54,86],"for":[55],"developed":[60],"general":[62],"optimization":[64],"simulation":[65],"tool":[66],"evaluate":[68],"different":[69,92],"methods.":[72,134],"A":[73],"transfer":[74],"technique":[76],"is":[77,116,137,171],"applied":[78],"test":[80],"traditional":[88],"approaches":[90],"under":[91,118],"scenarios,":[94],"including":[95],"stochastic":[96,119],"flow,":[98],"varying":[99],"volume,":[101],"uncertain":[103],"sensor":[104,145,175],"data.":[105,146],"The":[106],"experimental":[107],"results":[108],"show":[109],"that":[110],"method":[115],"robust":[117],"flow":[121],"variation":[123],"demand":[125],"patterns,":[126],"it":[128,136],"outperforms":[129],"fixed-time":[131],"vehicle-actuated":[133],"However,":[135],"unstable":[138],"case":[141],"highly":[143],"noisy":[144,177],"Also,":[147],"controller":[151],"can":[152],"continuously":[153],"learn":[154],"improve":[157],"performance":[159],"by":[160],"interacting":[161],"with":[162],"environment,":[166],"especially":[167],"congested,":[172],"observations.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}