{"id":"https://openalex.org/W3168793406","doi":"https://doi.org/10.1080/15472450.2021.1934679","title":"A cold-start-free reinforcement learning approach for traffic signal control","display_name":"A cold-start-free reinforcement learning approach for traffic signal control","publication_year":2021,"publication_date":"2021-06-06","ids":{"openalex":"https://openalex.org/W3168793406","doi":"https://doi.org/10.1080/15472450.2021.1934679","mag":"3168793406"},"language":"en","primary_location":{"id":"doi:10.1080/15472450.2021.1934679","is_oa":false,"landing_page_url":"https://doi.org/10.1080/15472450.2021.1934679","pdf_url":null,"source":{"id":"https://openalex.org/S172631016","display_name":"Journal of Intelligent Transportation Systems","issn_l":"1547-2442","issn":["1547-2442","1547-2450"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Transportation Systems","raw_type":"journal-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/A5070429242","display_name":"Nan Xiao","orcid":"https://orcid.org/0000-0002-3540-6209"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nan Xiao","raw_affiliation_strings":["Alibaba Cloud Intelligence, Alibaba Group, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Intelligence, Alibaba Group, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101999141","display_name":"Liang Yu","orcid":"https://orcid.org/0000-0003-2580-6345"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Yu","raw_affiliation_strings":["Alibaba Cloud Intelligence, Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Intelligence, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036140953","display_name":"Jinqiang Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinqiang Yu","raw_affiliation_strings":["Alibaba Cloud Intelligence, Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Intelligence, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338429","display_name":"Peng Chen","orcid":"https://orcid.org/0000-0001-5221-3655"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Chen","raw_affiliation_strings":["Alibaba Cloud Intelligence, Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Intelligence, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101438777","display_name":"Yuehu Liu","orcid":"https://orcid.org/0000-0002-1048-5115"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuehu Liu","raw_affiliation_strings":["Alibaba Cloud Intelligence, Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Intelligence, Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070429242"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0986,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.76745697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"26","issue":"4","first_page":"476","last_page":"485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9995999932289124,"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":0.9995999932289124,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.9909999966621399,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8946413993835449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7466538548469543},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.5752995610237122},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.543808102607727},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49537742137908936},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4799928367137909},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4519774615764618},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.41219693422317505},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14070722460746765}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8946413993835449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7466538548469543},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.5752995610237122},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.543808102607727},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49537742137908936},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4799928367137909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4519774615764618},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.41219693422317505},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14070722460746765},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/15472450.2021.1934679","is_oa":false,"landing_page_url":"https://doi.org/10.1080/15472450.2021.1934679","pdf_url":null,"source":{"id":"https://openalex.org/S172631016","display_name":"Journal of Intelligent Transportation Systems","issn_l":"1547-2442","issn":["1547-2442","1547-2450"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W138497752","https://openalex.org/W630810838","https://openalex.org/W842642076","https://openalex.org/W1217193980","https://openalex.org/W1516835682","https://openalex.org/W1598140581","https://openalex.org/W1602136775","https://openalex.org/W1757796397","https://openalex.org/W1972711079","https://openalex.org/W2019974229","https://openalex.org/W2061928772","https://openalex.org/W2074500080","https://openalex.org/W2139728973","https://openalex.org/W2173248099","https://openalex.org/W2179488730","https://openalex.org/W2257979135","https://openalex.org/W2291776898","https://openalex.org/W2480177474","https://openalex.org/W2516321972","https://openalex.org/W2564243486","https://openalex.org/W2575705757","https://openalex.org/W2604738573","https://openalex.org/W2612690371","https://openalex.org/W2725582697","https://openalex.org/W2741122588","https://openalex.org/W2792545614","https://openalex.org/W2809148419","https://openalex.org/W2894849109","https://openalex.org/W2907400790","https://openalex.org/W2951886768","https://openalex.org/W2963027910","https://openalex.org/W6605711098"],"related_works":["https://openalex.org/W2264067234","https://openalex.org/W3124243301","https://openalex.org/W1571502335","https://openalex.org/W1589409554","https://openalex.org/W2759038785","https://openalex.org/W2172232600","https://openalex.org/W3123876860","https://openalex.org/W3124172198","https://openalex.org/W2142633247","https://openalex.org/W2148394657"],"abstract_inverted_index":{"Typical":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"requires":[4],"a":[5,37,52,76,122,157],"huge":[6],"amount":[7,54],"of":[8,31,39,55,85,91,97,100,186,194,197],"data":[9,56],"before":[10],"achieving":[11],"an":[12],"acceptable":[13],"result,":[14],"and":[15,28,102,108,145,174],"its":[16,34],"performance":[17,161,179],"can":[18,59,81,155],"be":[19,60],"rather":[20],"poor":[21],"during":[22],"initial":[23,160],"interacting":[24],"process.":[25],"Sample":[26],"inefficiency":[27],"cold-start":[29],"phenomenon":[30],"RL":[32,78,101,198],"limits":[33],"feasibility":[35],"in":[36,68,133,142,159,199],"range":[38],"real-world":[40],"applications":[41],"such":[42],"as":[43,162],"traffic":[44,69],"signal":[45],"control":[46,172],"(TSC).":[47],"On":[48],"the":[49,83,115,118,181,187,192],"other":[50,119],"hand,":[51],"large":[53],"on":[57],"TSC":[58],"accumulated":[61],"by":[62,88],"various":[63],"model-based":[64],"controllers":[65],"(MBCs)":[66],"rooted":[67],"engineering.":[70],"In":[71],"this":[72],"context,":[73],"we":[74],"propose":[75],"new":[77],"approach":[79],"which":[80],"avoid":[82],"appearance":[84],"cold":[86],"starts":[87],"taking":[89],"advantage":[90],"MBC":[92,103,138],"experiences.":[93],"First,":[94],"three":[95],"frameworks":[96],"joint":[98],"utilization":[99],"are":[104,140],"summarized":[105],"for":[106,135],"TSC,":[107,136],"staged":[109,123,153],"framework":[110],"is":[111,131],"considered":[112],"to":[113,164,176],"have":[114],"edge":[116],"over":[117],"two.":[120],"Then,":[121],"noisy-net":[124],"prioritized":[125],"dueling":[126],"double":[127],"deep":[128],"Q-network":[129],"(NPDD-DQN)":[130],"described":[132],"detail":[134],"where":[137],"experiences":[139],"used":[141],"both":[143],"pre-training":[144],"online":[146],"training":[147],"processes.":[148],"Experimental":[149],"evaluation":[150],"demonstrates":[151],"that":[152,167],"NPDD-DQN":[154,166],"achieve":[156],"boost":[158],"compared":[163],"pure":[165],"does":[168],"not":[169],"utilize":[170],"any":[171],"experiences,":[173],"learn":[175],"improve":[177],"final":[178],"beyond":[180],"underlying":[182],"MBC.":[183],"The":[184],"effectiveness":[185],"proposed":[188],"method":[189],"opens":[190],"up":[191],"possibility":[193],"real":[195],"implementation":[196],"TSC.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}