{"id":"https://openalex.org/W4366149099","doi":"https://doi.org/10.1016/j.procs.2023.03.036","title":"Deep Reinforcement Learning Based Traffic Signal Control: A Comparative Analysis","display_name":"Deep Reinforcement Learning Based Traffic Signal Control: A Comparative Analysis","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4366149099","doi":"https://doi.org/10.1016/j.procs.2023.03.036"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2023.03.036","doi":"https://doi.org/10.1016/j.procs.2023.03.036","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2023.03.036","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.procs.2023.03.036","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","observed_orcids":["https://orcid.org/0000-0003-1663-9581"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chunliang Wu","raw_affiliation_strings":["Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology, Daejeon, 34051, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology, Daejeon, 34051, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Inhi Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Inhi Kim","raw_affiliation_strings":["Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology, Daejeon, 34051, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology, Daejeon, 34051, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072433020","display_name":"Zhenliang Ma","orcid":"https://orcid.org/0000-0002-2141-0389","observed_orcids":["https://orcid.org/0000-0002-2141-0389"]},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Zhenliang Ma","raw_affiliation_strings":["Department of Civil and Architectural Engineering, KTH Royal Institute of Technology, Stockholm, 11428, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Civil and Architectural Engineering, KTH Royal Institute of Technology, Stockholm, 11428, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":13.1413,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.99484936,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":"220","issue":null,"first_page":"275","last_page":"282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9961000084877014,"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":0.9961000084877014,"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":0.0010999999940395355,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0003000000142492354,"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/traffic-signal-control","display_name":"traffic signal control","score":0.9380000233650208},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":1.0},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.8489999771118164},{"id":"https://openalex.org/keywords/state-representation","display_name":"state representation","score":0.7850000262260437},{"id":"https://openalex.org/keywords/isolated-intersections","display_name":"isolated intersections","score":0.9449999928474426},{"id":"https://openalex.org/keywords/learning-stability","display_name":"learning stability","score":0.6909999847412109}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9110012054443359},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8491383194923401},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.7142859697341919},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5523843169212341},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49270084500312805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48504799604415894},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44669434428215027},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44648978114128113},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43364065885543823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39300528168678284},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.12229189276695251},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1067095696926117},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2023.03.036","doi":"https://doi.org/10.1016/j.procs.2023.03.036","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2023.03.036","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.procs.2023.03.036","doi":"https://doi.org/10.1016/j.procs.2023.03.036","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2023.03.036","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.428600013256073}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1116669180","display_name":null,"funder_award_id":"2021R1C1C1006405","funder_id":"https://openalex.org/F4320322030","funder_display_name":"Ministry of Science, ICT and Future Planning"}],"funders":[{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W597872396","https://openalex.org/W1969758122","https://openalex.org/W2124657875","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2794842204","https://openalex.org/W3022861755","https://openalex.org/W3100789280","https://openalex.org/W3123082711","https://openalex.org/W3185625797","https://openalex.org/W4214717370","https://openalex.org/W4252937310","https://openalex.org/W6787597298"],"related_works":["https://openalex.org/W4402896801","https://openalex.org/W4323262648","https://openalex.org/W3216325961","https://openalex.org/W3096632704","https://openalex.org/W4282929921","https://openalex.org/W4200177206","https://openalex.org/W4386236297","https://openalex.org/W3035721219","https://openalex.org/W4213230486","https://openalex.org/W4404739544"],"abstract_inverted_index":{"More":[0],"recently,":[1],"the":[2,31,48,108,112,131,138,172,177],"advancement":[3],"of":[4,50,114,140,187],"deep":[5,60],"learning":[6,10,62,88],"techniques":[7],"enables":[8],"reinforcement":[9,61],"(RL)":[11],"to":[12,29,162,198],"handle":[13],"high-dimensional":[14],"decision-making":[15],"problems.":[16],"It":[17],"brings":[18],"increasing":[19],"attention":[20],"in":[21,205],"transport":[22,196],"areas.":[23],"Some":[24],"work":[25],"has":[26],"applied":[27],"them":[28],"solve":[30],"intractable":[32],"traffic":[33,135,151,208],"signal":[34],"control":[35,91,164,183],"(TSC)":[36],"problem":[37],"and":[38,59,90,118,124,180,193],"achieved":[39],"promising":[40],"results.":[41],"However,":[42,137],"very":[43],"few":[44],"research":[45,71,189],"comprehensively":[46],"investigates":[47],"impacts":[49],"key":[51],"design":[52,79,199],"elements,":[53],"including":[54],"state":[55,110,120],"definitions,":[56],"reward":[57,142],"functions":[58,143],"(DRL)":[63],"methods,":[64],"on":[65,116,130,144],"TSC":[66,182,203],"performance.":[67],"To":[68],"fill":[69],"this":[70,73,188],"gap,":[72],"paper":[74],"first":[75],"selects":[76],"commonly":[77],"used":[78],"elements":[80],"from":[81],"existing":[82],"literature.":[83],"Then,":[84],"we":[85],"compare":[86],"their":[87],"stability":[89],"performance":[92,132,145,165],"at":[93],"an":[94,200],"isolated":[95],"intersection":[96],"under":[97,133,149],"different":[98,134],"scenarios":[99],"via":[100],"simulation":[101],"experiments.":[102],"The":[103,185],"experimental":[104],"results":[105],"show":[106],"that":[107],"quantitative":[109],"(e.g.,":[111,121],"number":[113],"vehicles":[115],"lanes)":[117],"image-like":[119],"vehicle":[122],"position":[123],"speed)":[125],"have":[126],"no":[127],"significant":[128],"impact":[129,139],"demands.":[136],"various":[141],"is":[146],"vivid,":[147],"especially":[148],"high":[150],"demand.":[152],"Also,":[153],"high-resolution":[154],"vehicular":[155],"network":[156],"data":[157],"may":[158],"not":[159],"be":[160],"possible":[161],"improve":[163],"versus":[166],"ordinary":[167],"camera":[168],"data.":[169],"In":[170],"addition,":[171],"value-based":[173],"DRL":[174],"algorithms":[175],"outperform":[176],"policy-based":[178],"algorithm":[179],"traditional":[181],"methods.":[184],"findings":[186],"would":[190],"provide":[191],"insights":[192],"guidance":[194],"for":[195],"engineers":[197],"efficient":[201],"DRL-based":[202],"system":[204],"a":[206],"real":[207],"environment.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-04-19T00:00:00"}