{"id":"https://openalex.org/W3129998325","doi":"https://doi.org/10.1109/vtc2020-fall49728.2020.9348821","title":"Fast Bootstrapping for Reinforcement Learning-Based Traffic Signal Control Systems Using Queueing Theory","display_name":"Fast Bootstrapping for Reinforcement Learning-Based Traffic Signal Control Systems Using Queueing Theory","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W3129998325","doi":"https://doi.org/10.1109/vtc2020-fall49728.2020.9348821","mag":"3129998325"},"language":"en","primary_location":{"id":"doi:10.1109/vtc2020-fall49728.2020.9348821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vtc2020-fall49728.2020.9348821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 92nd Vehicular Technology Conference (VTC2020-Fall)","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/A5086710323","display_name":"Maxime Tr\u00e9ca","orcid":"https://orcid.org/0000-0002-1083-0986"},"institutions":[{"id":"https://openalex.org/I4210108314","display_name":"VeDeCoM Institute","ror":"https://ror.org/01ssrp339","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210108314"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Maxime Treca","raw_affiliation_strings":["Universit\u00e9 Versailles SQY,Vedecom Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Versailles SQY,Vedecom Institute","institution_ids":["https://openalex.org/I4210108314"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018537001","display_name":"Juli\u00e1n Garbiso","orcid":"https://orcid.org/0000-0001-7421-6136"},"institutions":[{"id":"https://openalex.org/I4210108314","display_name":"VeDeCoM Institute","ror":"https://ror.org/01ssrp339","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210108314"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Julian Garbiso","raw_affiliation_strings":["Universit\u00e9 Versailles SQY,Vedecom Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Versailles SQY,Vedecom Institute","institution_ids":["https://openalex.org/I4210108314"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019901146","display_name":"Dominique Barth","orcid":null},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4390039268","display_name":"Donn\u00e9es et algorithmes pour une ville intelligente et durable","ror":"https://ror.org/01xta2p78","country_code":"FR","type":"facility","lineage":["https://openalex.org/I195731000","https://openalex.org/I277688954","https://openalex.org/I4390039268"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dominique Barth","raw_affiliation_strings":["Universit\u00e9 Paris Saclay,Laboratoire DAVID"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Saclay,Laboratoire DAVID","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4390039268"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015917791","display_name":"Mahdi Zargayouna","orcid":"https://orcid.org/0000-0002-1221-8977"},"institutions":[{"id":"https://openalex.org/I4210154111","display_name":"Universit\u00e9 Gustave Eiffel","ror":"https://ror.org/03x42jk29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210154111"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mahdi Zargayouna","raw_affiliation_strings":["Universit\u00e9 Gustave Eiffel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Gustave Eiffel","institution_ids":["https://openalex.org/I4210154111"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"135","issue":null,"first_page":"1","last_page":"5"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9965999722480774,"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":0.9947999715805054,"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/bootstrapping","display_name":"Bootstrapping (finance)","score":0.9224668145179749},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8927792310714722},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7846351861953735},{"id":"https://openalex.org/keywords/queueing-theory","display_name":"Queueing theory","score":0.7243829369544983},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.6400659084320068},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.5647101998329163},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.500891923904419},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4391901195049286},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.41644686460494995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4136337339878082},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.41084468364715576},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.38762038946151733},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1706673800945282},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1632973551750183},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11909908056259155}],"concepts":[{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.9224668145179749},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8927792310714722},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7846351861953735},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.7243829369544983},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.6400659084320068},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.5647101998329163},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.500891923904419},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4391901195049286},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41644686460494995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4136337339878082},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41084468364715576},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.38762038946151733},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1706673800945282},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1632973551750183},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11909908056259155},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vtc2020-fall49728.2020.9348821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vtc2020-fall49728.2020.9348821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 92nd Vehicular Technology Conference (VTC2020-Fall)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W33871791","https://openalex.org/W134038551","https://openalex.org/W138497752","https://openalex.org/W562096680","https://openalex.org/W1515851193","https://openalex.org/W1869778509","https://openalex.org/W1971377029","https://openalex.org/W2015840019","https://openalex.org/W2019974229","https://openalex.org/W2021415726","https://openalex.org/W2039472110","https://openalex.org/W2049593940","https://openalex.org/W2088595989","https://openalex.org/W2138834223","https://openalex.org/W2139160917","https://openalex.org/W2480177474","https://openalex.org/W2801573006","https://openalex.org/W2915117209","https://openalex.org/W3023917962","https://openalex.org/W4292167352","https://openalex.org/W6605711098","https://openalex.org/W6639086533","https://openalex.org/W6680185541","https://openalex.org/W6759553562","https://openalex.org/W7011621630"],"related_works":["https://openalex.org/W2385142208","https://openalex.org/W2460732917","https://openalex.org/W4310634103","https://openalex.org/W2092348846","https://openalex.org/W2133228654","https://openalex.org/W2375665878","https://openalex.org/W50176465","https://openalex.org/W3085897220","https://openalex.org/W2014117520","https://openalex.org/W3003926207"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,73],"is":[2,152],"a":[3,23,66,96,156],"commonly":[4],"used":[5],"technique":[6],"in":[7,47,65,139],"the":[8,19,35,48,87,101,120,129,136,143,162,184,191],"field":[9],"of":[10,71,119,133,148,172],"traffic":[11,24,32,36,107],"signal":[12,25],"control.":[13],"By":[14],"iteratively":[15],"testing":[16],"actions":[17,64],"given":[18,34],"current":[20],"network":[21,122],"state,":[22],"agent":[26,185],"gradually":[27],"learns":[28],"to":[29,53,85,90,110,141,155],"optimally":[30],"control":[31,45,108],"lights":[33],"situation":[37],"at":[38,135],"hand.":[39],"While":[40],"they":[41,61],"usually":[42],"outperform":[43],"traditional":[44,158],"systems":[46],"literature,":[49],"these":[50,173],"methods":[51,74,109],"have":[52],"first":[54],"go":[55],"through":[56],"an":[57],"exploration":[58,92],"phase":[59],"where":[60],"test":[62],"different":[63],"trial-and-error":[67],"fashion.":[68],"The":[69,146],"nature":[70],"reinforcement":[72],"hence":[75],"causes":[76],"unstable":[77],"performances":[78],"and":[79,125],"high":[80],"computational":[81],"costs.":[82],"In":[83],"order":[84,140],"limit":[86],"costs":[88],"linked":[89],"this":[91],"phase,":[93],"we":[94],"propose":[95],"bootstrapping":[97,150,169],"method":[98,116,151,160],"that":[99,168],"reduces":[100],"computation":[102],"time":[103,132],"needed":[104],"for":[105],"learning-based":[106],"reach":[111],"acceptable":[112,178],"performance":[113,147,179],"levels.":[114],"Our":[115],"models":[117],"lanes":[118],"road":[121],"as":[123],"queues,":[124],"derives":[126],"results":[127,166],"on":[128],"average":[130],"service":[131],"vehicles":[134],"intersection":[137],"level":[138],"estimate":[142],"agent's":[144],"policy.":[145],"our":[149],"then":[153],"compared":[154],"more":[157],"Q-Learning":[159],"using":[161],"SUMO":[163],"simulator.":[164],"Simulation":[165],"show":[167],"alleviates":[170],"both":[171],"issues":[174],"by":[175,181],"immediately":[176],"reaching":[177],"levels":[180],"quickly":[182],"training":[183],"without":[186],"any":[187],"direct":[188],"interaction":[189],"with":[190],"simulation":[192],"environment.":[193]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}