{"id":"https://openalex.org/W4393241349","doi":"https://doi.org/10.1109/tits.2024.3377106","title":"A General Scenario-Agnostic Reinforcement Learning for Traffic Signal Control","display_name":"A General Scenario-Agnostic Reinforcement Learning for Traffic Signal Control","publication_year":2024,"publication_date":"2024-03-27","ids":{"openalex":"https://openalex.org/W4393241349","doi":"https://doi.org/10.1109/tits.2024.3377106"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2024.3377106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2024.3377106","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.eur.nl/ws/files/184255650/A_General_Scenario-Agnostic_Reinforcement_Learning_for_Traffic_Signal_Control.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101324341","display_name":"Haoyuan Jiang","orcid":"https://orcid.org/0000-0002-3768-865X"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyuan Jiang","raw_affiliation_strings":["Sense-Time Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Sense-Time Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029997962","display_name":"Ziyue Li","orcid":"https://orcid.org/0000-0003-4983-9352"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]},{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Ziyue Li","raw_affiliation_strings":["Department of Information Systems, University of Cologne, K&#x00F6;ln, Germany","Sense-Time Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems, University of Cologne, K&#x00F6;ln, Germany","institution_ids":["https://openalex.org/I180923762"]},{"raw_affiliation_string":"Sense-Time Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030816801","display_name":"Zhishuai Li","orcid":"https://orcid.org/0000-0003-3408-6300"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]},{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Zhishuai Li","raw_affiliation_strings":["Department of Information Systems, University of Cologne, K&#x00F6;ln, Germany","Sense-Time Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems, University of Cologne, K&#x00F6;ln, Germany","institution_ids":["https://openalex.org/I180923762"]},{"raw_affiliation_string":"Sense-Time Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028486493","display_name":"Lei Bai","orcid":"https://orcid.org/0000-0003-3378-7201"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Bai","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076505011","display_name":"Hangyu Mao","orcid":"https://orcid.org/0000-0002-4499-7581"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangyu Mao","raw_affiliation_strings":["Sense-Time Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Sense-Time Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042852488","display_name":"Wolfgang Ketter","orcid":"https://orcid.org/0000-0001-9008-142X"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Ketter","raw_affiliation_strings":["Department of Information Systems, University of Cologne, K&#x00F6;ln, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems, University of Cologne, K&#x00F6;ln, Germany","institution_ids":["https://openalex.org/I180923762"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024522346","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0001-5874-131X"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhao","raw_affiliation_strings":["Sense-Time Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Sense-Time Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101324341"],"corresponding_institution_ids":["https://openalex.org/I4210128910"],"apc_list":null,"apc_paid":null,"fwci":10.078,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.9847375,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"25","issue":"9","first_page":"11330","last_page":"11344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.902999997138977,"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/T10320","display_name":"Neural Networks and Applications","score":0.902999997138977,"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":0.8240346312522888},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6377711296081543},{"id":"https://openalex.org/keywords/traffic-signal","display_name":"Traffic signal","score":0.521547794342041},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.48730742931365967},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4163699448108673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4039376378059387},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.16740119457244873}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8240346312522888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6377711296081543},{"id":"https://openalex.org/C2987419075","wikidata":"https://www.wikidata.org/wiki/Q8004","display_name":"Traffic signal","level":2,"score":0.521547794342041},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.48730742931365967},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4163699448108673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4039376378059387},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.16740119457244873},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tits.2024.3377106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2024.3377106","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-article"},{"id":"pmh:oai:pure.eur.nl:openaire_cris_publications/47ed8446-dc5d-4ea5-943c-b6f22732fcc2","is_oa":true,"landing_page_url":"https://pure.eur.nl/en/publications/47ed8446-dc5d-4ea5-943c-b6f22732fcc2","pdf_url":"https://pure.eur.nl/ws/files/184255650/A_General_Scenario-Agnostic_Reinforcement_Learning_for_Traffic_Signal_Control.pdf","source":{"id":"https://openalex.org/S4306401266","display_name":"EUR Research Repository (Erasmus University Rotterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I913958620","host_organization_name":"Erasmus University Rotterdam","host_organization_lineage":["https://openalex.org/I913958620"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jiang, H, Li, Z, Li, Z, Bai, L, Mao, H, Ketter, W & Zhao, R 2024, 'A General Scenario-Agnostic Reinforcement Learning for Traffic Signal Control', IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 9, pp. 11330-11344. https://doi.org/10.1109/TITS.2024.3377106","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.eur.nl:openaire_cris_publications/47ed8446-dc5d-4ea5-943c-b6f22732fcc2","is_oa":true,"landing_page_url":"https://pure.eur.nl/en/publications/47ed8446-dc5d-4ea5-943c-b6f22732fcc2","pdf_url":"https://pure.eur.nl/ws/files/184255650/A_General_Scenario-Agnostic_Reinforcement_Learning_for_Traffic_Signal_Control.pdf","source":{"id":"https://openalex.org/S4306401266","display_name":"EUR Research Repository (Erasmus University Rotterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I913958620","host_organization_name":"Erasmus University Rotterdam","host_organization_lineage":["https://openalex.org/I913958620"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jiang, H, Li, Z, Li, Z, Bai, L, Mao, H, Ketter, W & Zhao, R 2024, 'A General Scenario-Agnostic Reinforcement Learning for Traffic Signal Control', IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 9, pp. 11330-11344. https://doi.org/10.1109/TITS.2024.3377106","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393241349.pdf","grobid_xml":"https://content.openalex.org/works/W4393241349.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W5525483","https://openalex.org/W573924038","https://openalex.org/W2019974229","https://openalex.org/W2033254849","https://openalex.org/W2053546515","https://openalex.org/W2065748588","https://openalex.org/W2088595989","https://openalex.org/W2162578038","https://openalex.org/W2579346514","https://openalex.org/W2604427121","https://openalex.org/W2613020517","https://openalex.org/W2725582697","https://openalex.org/W2736601468","https://openalex.org/W2809148419","https://openalex.org/W2904065660","https://openalex.org/W2915117209","https://openalex.org/W2964749398","https://openalex.org/W2983178256","https://openalex.org/W2988973041","https://openalex.org/W2998187693","https://openalex.org/W2998332605","https://openalex.org/W3086530824","https://openalex.org/W3096831136","https://openalex.org/W3098136553","https://openalex.org/W3123082711","https://openalex.org/W4220899555","https://openalex.org/W4287590162","https://openalex.org/W4296367480","https://openalex.org/W4307323312","https://openalex.org/W4311474986","https://openalex.org/W4313547795","https://openalex.org/W6600981286","https://openalex.org/W6688485107","https://openalex.org/W6692846177","https://openalex.org/W6695011786","https://openalex.org/W6732080978","https://openalex.org/W6736372492","https://openalex.org/W6737707654","https://openalex.org/W6741002519","https://openalex.org/W6768395096","https://openalex.org/W6775342081","https://openalex.org/W6783867858","https://openalex.org/W6786206678","https://openalex.org/W6798393411","https://openalex.org/W6841140246","https://openalex.org/W6846173864","https://openalex.org/W6862829713"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4367838498","https://openalex.org/W2393348402","https://openalex.org/W4293167677","https://openalex.org/W2242021741","https://openalex.org/W2377015873","https://openalex.org/W2605253768","https://openalex.org/W2392201083"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,154],"(RL)":[2],"can":[3,221,266,293],"automatically":[4,222],"learn":[5],"a":[6,10,42,53,91,103,124,136,149,172,214,236,288],"better":[7],"policy":[8],"through":[9],"trial-and-error":[11],"paradigm":[12],"and":[13,19,62,70,85,134,192,201,233,276,304],"has":[14,52],"been":[15],"adopted":[16],"to":[17,109,166,182,196,213,239],"revolutionize":[18],"optimize":[20],"traditional":[21],"traffic":[22,63,157,216,241],"signal":[23,64,158,217],"control":[24,159,218,240],"systems":[25],"that":[26,129,265],"are":[27,38,306],"usually":[28],"based":[29,40],"on":[30,41],"handcrafted":[31],"methods.":[32],"However,":[33],"most":[34],"existing":[35],"RL-based":[36],"models":[37,67,94],"either":[39],"single":[43],"scenario":[44,51],"or":[45],"multiple":[46,99,210,244],"independent":[47],"scenarios,":[48,100,211,303],"where":[49],"each":[50],"separate":[54],"simulation":[55],"environment":[56],"with":[57,81,209,269,287],"predefined":[58],"road":[59],"network":[60],"topology":[61],"settings.":[65,254],"These":[66],"implement":[68],"training":[69],"testing":[71],"in":[72,252],"the":[73,82,111,115,178,184,198,262],"same":[74],"scenario,":[75,290],"thus":[76],"being":[77],"strictly":[78],"tied":[79],"up":[80],"specific":[83],"setting":[84],"sacrificing":[86],"model":[87,135,199,292],"generalization":[88],"heavily.":[89],"While":[90],"few":[92],"recent":[93],"could":[95,130],"be":[96,267],"trained":[97],"by":[98],"they":[101],"require":[102],"huge":[104],"amount":[105],"of":[106,138,186],"manual":[107,180,274],"labor":[108,181],"label":[110],"intersection":[112],"structure,":[113,174],"hindering":[114],"model\u2019s":[116],"generalization.":[117],"In":[118,255],"this":[119,145],"work,":[120],"we":[121,147,257],"aim":[122],"at":[123],"<italic":[125,140],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[126,141,279,297],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">general</i>":[127],"framework":[128,155],"eliminate":[131],"heavy":[132,179],"labeling":[133],"variety":[137],"scenarios":[139,272],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">simultaneously</i>":[142],".":[143],"To":[144],"end,":[146],"propose":[148],"general":[150,163],"Scenario-Agnostic":[151],"(GESA)":[152],"reinforcement":[153],"for":[156,243],"with:":[160],"(1)":[161],"A":[162,189,206],"plug-in":[164],"module":[165],"map":[167],"all":[168],"different":[169,271],"intersections":[170,226],"into":[171],"unified":[173,190],"freeing":[175],"us":[176],"from":[177,227],"specify":[183],"structure":[185],"intersections;":[187],"(2)":[188],"state":[191],"action":[193],"space":[194],"design":[195],"keep":[197],"input":[200],"output":[202],"consistently":[203],"structured;":[204],"(3)":[205],"large-scale":[207],"co-training":[208],"leading":[212],"generic":[215],"algorithm.":[219],"GESA":[220],"handle":[223],"various":[224,228],"structured":[225],"cities":[229,245],"without":[230,273],"human":[231],"labeling,":[232],"it":[234],"co-trains":[235],"generalist":[237],"agent":[238],"signals":[242],"together,":[246],"which":[247],"also":[248],"demonstrates":[249],"superior":[250],"transferability":[251],"zero-shot":[253],"experiments,":[256],"demonstrate":[258],"our":[259,291],"algorithm":[260],"as":[261],"first":[263],"one":[264],"co-trained":[268],"seven":[270],"annotation":[275],"gets":[277],"<bold":[278,296],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">13.27%</b>":[280],"higher":[281,299],"rewards":[282],"than":[283],"baselines.":[284],"When":[285],"dealing":[286],"new":[289],"still":[294],"achieve":[295],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">9.39%</b>":[298],"rewards.":[300],"The":[301],"code,":[302],"demos":[305],"available":[307],"https://github.com/bonaldli/GESA.":[308]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":7}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}