{"id":"https://openalex.org/W4401863796","doi":"https://doi.org/10.1145/3637528.3671927","title":"CrossLight: Offline-to-Online Reinforcement Learning for Cross-City Traffic Signal Control","display_name":"CrossLight: Offline-to-Online Reinforcement Learning for Cross-City Traffic Signal Control","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863796","doi":"https://doi.org/10.1145/3637528.3671927"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671927","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5048500530","display_name":"Sun Qian","orcid":"https://orcid.org/0000-0002-2205-4566"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Qian Sun","raw_affiliation_strings":["The Division of Emerging Interdisciplinary Areas, Hong Kong University of Science and Technology, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Division of Emerging Interdisciplinary Areas, Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103093616","display_name":"Rui Zha","orcid":"https://orcid.org/0000-0002-6557-123X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zha","raw_affiliation_strings":["School of Computer Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350641","display_name":"Le Zhang","orcid":"https://orcid.org/0000-0003-0894-9651"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Zhang","raw_affiliation_strings":["Baidu Research, Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Research, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101481194","display_name":"Jingbo Zhou","orcid":"https://orcid.org/0000-0003-2677-7021"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbo Zhou","raw_affiliation_strings":["Baidu Research, Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Research, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025158","display_name":"Yu Mei","orcid":"https://orcid.org/0000-0003-2620-3589"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Mei","raw_affiliation_strings":["Department of Intelligent Transportation System, Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Intelligent Transportation System, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031757831","display_name":"Zhiling Li","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiling Li","raw_affiliation_strings":["Department of Intelligent Driving Group Business Management, Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Intelligent Driving Group Business Management, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101862104","display_name":"Hui Xiong","orcid":"https://orcid.org/0000-0001-6016-6465"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hui Xiong","raw_affiliation_strings":["Thrust of Artificial Intelligence, Hong Kong University of Science and Technology (Guangzhou) & Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Thrust of Artificial Intelligence, Hong Kong University of Science and Technology (Guangzhou) & Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Guangzhou, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5048500530"],"corresponding_institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":2.6276,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.9010982,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2765","last_page":"2774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9965999722480774,"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":0.9799000024795532,"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":0.8065498471260071},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6398353576660156},{"id":"https://openalex.org/keywords/traffic-signal","display_name":"Traffic signal","score":0.6134769916534424},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5604655146598816},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43001317977905273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3408932685852051},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.19764631986618042}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8065498471260071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6398353576660156},{"id":"https://openalex.org/C2987419075","wikidata":"https://www.wikidata.org/wiki/Q8004","display_name":"Traffic signal","level":2,"score":0.6134769916534424},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5604655146598816},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43001317977905273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3408932685852051},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.19764631986618042},{"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:10.1145/3637528.3671927","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-143621","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-143621","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.5299999713897705,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2007894170","https://openalex.org/W2760506156","https://openalex.org/W2964749398","https://openalex.org/W2983178256","https://openalex.org/W2985331920","https://openalex.org/W2998187693","https://openalex.org/W2998332605","https://openalex.org/W3096739060","https://openalex.org/W3123082711","https://openalex.org/W3200607907","https://openalex.org/W3210690059","https://openalex.org/W4290877497","https://openalex.org/W4290927794","https://openalex.org/W4290944372","https://openalex.org/W4309954054","https://openalex.org/W4313547795","https://openalex.org/W4385568146","https://openalex.org/W4385568286","https://openalex.org/W4385644834","https://openalex.org/W4387848913","https://openalex.org/W4392518487","https://openalex.org/W4393160268"],"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":{"The":[0],"recent":[1],"advancements":[2],"in":[3,26,77,106,143,149,211,273],"Traffic":[4,85],"Signal":[5,86],"Control":[6,87],"(TSC)":[7,88],"have":[8],"highlighted":[9],"the":[10,47,61,68,107,116,163,167,185,194,199,212,252,257,308],"potential":[11],"of":[12,49,64,118,181,256],"Reinforcement":[13],"Learning":[14],"(RL)":[15],"as":[16,60,295],"a":[17,204,217,228,237,243,296,302],"promising":[18],"solution":[19,306],"to":[20,39,52,114,176,307],"alleviate":[21],"traffic":[22],"congestion.":[23],"Current":[24],"research":[25],"this":[27,75,78],"area":[28],"primarily":[29],"concentrates":[30],"on":[31,162],"either":[32],"online":[33,225,283],"or":[34],"offline":[35,98,168,285],"learning":[36],"strategies,":[37],"aiming":[38],"create":[40],"optimized":[41],"policies":[42,51,121],"for":[43,193,259],"specific":[44],"cities.":[45,145,187],"Nevertheless,":[46],"transferability":[48],"these":[50],"new":[53,274],"cities":[54,102,124,266,275],"is":[55,221],"impeded":[56],"by":[57,132],"constraints":[58],"such":[59],"limited":[62],"availability":[63],"high-quality":[65],"data":[66,99],"and":[67,70,103,230,247,254,284,298,304],"expensive":[69],"risky":[71],"exploration":[72,240],"process.":[73],"To":[74,146,188],"end,":[76],"paper,":[79],"we":[80,130,155,197,215],"present":[81],"an":[82],"innovative":[83],"cross-city":[84],"paradigm":[89],"called":[90],"CrossLight.":[91],"Our":[92],"approach":[93],"involves":[94],"meta":[95],"training":[96],"using":[97,224],"from":[100,184],"source":[101,144,186],"adaptively":[104],"fine-tuning":[105,210,278],"target":[108,213],"city.":[109],"This":[110,233,287],"novel":[111],"methodology":[112],"aims":[113],"address":[115,147],"challenges":[117],"transferring":[119],"TSC":[120],"across":[122,264],"different":[123],"effectively.":[125],"In":[126],"our":[127,291],"proposed":[128],"approach,":[129],"start":[131],"acquiring":[133],"meta-decision":[134],"pattern":[135],"knowledge":[136],"through":[137],"trajectory":[138],"dynamics":[139],"reconstruction":[140],"via":[141],"pre-training":[142],"disparities":[148],"road":[150],"network":[151],"topologies":[152],"between":[153,245],"cities,":[154],"dynamically":[156],"construct":[157],"city":[158],"topological":[159],"structures":[160,172],"based":[161],"extracted":[164],"meta-knowledge":[165],"during":[166],"meta-training":[169],"phase.":[170],"These":[171],"are":[173],"then":[174],"used":[175],"distill":[177],"pattern-structure":[178],"aware":[179],"representations":[180],"decision":[182],"trajectories":[183,258],"identify":[189],"effective":[190,305],"initial":[191],"parameters":[192],"learnable":[195],"components,":[196],"employ":[198],"Model-Agnostic":[200],"Meta-Learning":[201],"(MAML)":[202],"framework,":[203],"popular":[205],"meta-learning":[206],"approach.":[207],"During":[208],"adaptive":[209],"city,":[214],"introduce":[216],"replay":[218],"buffer":[219],"that":[220,268,290],"iteratively":[222],"updated":[223],"interactions":[226],"with":[227,236,276],"rank":[229],"filter":[231],"mechanism.":[232],"mechanism,":[234],"along":[235],"carefully":[238],"designed":[239],"strategy,":[241],"ensures":[242],"balance":[244],"exploitation":[246],"exploration,":[248],"thereby":[249],"fostering":[250],"both":[251,281],"diversity":[253],"quality":[255],"fine-tuning.":[260],"Finally,":[261],"extensive":[262],"experiments":[263],"four":[265],"validate":[267],"CrossLight":[269,292],"achieves":[270],"comparable":[271],"performance":[272],"minimal":[277],"iterations,":[279],"surpassing":[280],"existing":[282],"methods.":[286],"success":[288],"underscores":[289],"framework":[293],"emerges":[294],"groundbreaking":[297],"potent":[299],"paradigm,":[300],"offering":[301],"feasible":[303],"intelligent":[309],"transportation":[310],"community.":[311]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}