{"id":"https://openalex.org/W4390492454","doi":"https://doi.org/10.1109/tits.2023.3344585","title":"Reinforcement Learning for Traffic Signal Control in Hybrid Action Space","display_name":"Reinforcement Learning for Traffic Signal Control in Hybrid Action Space","publication_year":2024,"publication_date":"2024-01-02","ids":{"openalex":"https://openalex.org/W4390492454","doi":"https://doi.org/10.1109/tits.2023.3344585"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2023.3344585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2023.3344585","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051236447","display_name":"Haoqing Luo","orcid":"https://orcid.org/0009-0009-2828-1979"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoqing Luo","raw_affiliation_strings":["Institute of Intelligent Transportation Systems, College of Civil Engineering and Architecture, and the Center for Balance Architecture, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-2828-1979","affiliations":[{"raw_affiliation_string":"Institute of Intelligent Transportation Systems, College of Civil Engineering and Architecture, and the Center for Balance Architecture, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108563315","display_name":"Yiming Bie","orcid":"https://orcid.org/0000-0003-4651-1570"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Bie","raw_affiliation_strings":["School of Transportation, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0003-4651-1570","affiliations":[{"raw_affiliation_string":"School of Transportation, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101960327","display_name":"Sheng Jin","orcid":"https://orcid.org/0000-0001-6110-0783"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Jin","raw_affiliation_strings":["Institute of Intelligent Transportation Systems, College of Civil Engineering and Architecture, and the Center for Balance Architecture, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6110-0783","affiliations":[{"raw_affiliation_string":"Institute of Intelligent Transportation Systems, College of Civil Engineering and Architecture, and the Center for Balance Architecture, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051236447"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":7.888,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.97948521,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"25","issue":"6","first_page":"5225","last_page":"5241"},"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9944999814033508,"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":0.9538000226020813,"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":0.8164812922477722},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.6705574989318848},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.6037700772285461},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5610337257385254},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5284770727157593},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5261487364768982},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5175813436508179},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5084375739097595},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4984476566314697},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.48291918635368347},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4481097459793091},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42198604345321655},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4201757311820984},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4153531491756439},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2766338586807251},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26306217908859253},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2215568721294403},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1300535798072815},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12220820784568787}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8164812922477722},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.6705574989318848},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.6037700772285461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5610337257385254},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5284770727157593},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5261487364768982},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5175813436508179},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5084375739097595},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4984476566314697},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48291918635368347},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4481097459793091},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42198604345321655},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4201757311820984},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4153531491756439},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2766338586807251},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26306217908859253},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2215568721294403},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1300535798072815},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12220820784568787},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2023.3344585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2023.3344585","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G419958781","display_name":null,"funder_award_id":"LR23E080002","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G6510882642","display_name":null,"funder_award_id":"72361137006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W116194267","https://openalex.org/W138497752","https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W1549969567","https://openalex.org/W1971918058","https://openalex.org/W2007894170","https://openalex.org/W2015817066","https://openalex.org/W2033254849","https://openalex.org/W2076337359","https://openalex.org/W2088595989","https://openalex.org/W2089361241","https://openalex.org/W2109690032","https://openalex.org/W2124657875","https://openalex.org/W2144488633","https://openalex.org/W2145339207","https://openalex.org/W2210077926","https://openalex.org/W2256420211","https://openalex.org/W2480177474","https://openalex.org/W2498017881","https://openalex.org/W2604427121","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2747213132","https://openalex.org/W2766381093","https://openalex.org/W2786928559","https://openalex.org/W2794842204","https://openalex.org/W2809148419","https://openalex.org/W2895793836","https://openalex.org/W2897417898","https://openalex.org/W2903709398","https://openalex.org/W2915117209","https://openalex.org/W2924816077","https://openalex.org/W2944306386","https://openalex.org/W2963027910","https://openalex.org/W2964749398","https://openalex.org/W2965757358","https://openalex.org/W2983178256","https://openalex.org/W2985159211","https://openalex.org/W2988973041","https://openalex.org/W3011120880","https://openalex.org/W3014845548","https://openalex.org/W3023394361","https://openalex.org/W3099689767","https://openalex.org/W3106357768","https://openalex.org/W3138688069","https://openalex.org/W3148476902","https://openalex.org/W3164005523","https://openalex.org/W4206335483","https://openalex.org/W4206867326","https://openalex.org/W4212774754","https://openalex.org/W4213439995","https://openalex.org/W4214717370","https://openalex.org/W4220805666","https://openalex.org/W4221141531","https://openalex.org/W4281385358","https://openalex.org/W4287112662","https://openalex.org/W4288425262","https://openalex.org/W6605423657","https://openalex.org/W6605711098","https://openalex.org/W6621395797","https://openalex.org/W6627932998","https://openalex.org/W6631190155","https://openalex.org/W6632837212","https://openalex.org/W6684205842","https://openalex.org/W6685444567","https://openalex.org/W6688475801","https://openalex.org/W6692846177","https://openalex.org/W6736372492","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748554570","https://openalex.org/W6755326576","https://openalex.org/W6762592680","https://openalex.org/W6775686901","https://openalex.org/W6783867858","https://openalex.org/W6840380725","https://openalex.org/W6840548035","https://openalex.org/W6843241716","https://openalex.org/W6849140488"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W4225571923","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908"],"abstract_inverted_index":{"The":[0],"prevailing":[1],"reinforcement-learning-based":[2],"traffic":[3,38],"signal":[4],"control":[5],"methods":[6],"are":[7,52,89],"typically":[8],"staging-optimizable":[9],"or":[10,48],"duration-optimizable,":[11],"depending":[12],"on":[13],"the":[14,29,40,74,94,111,118,126],"action":[15,50,57],"spaces.":[16],"In":[17],"this":[18],"paper,":[19],"we":[20,123],"use":[21],"hybrid":[22,56],"proximal":[23],"policy":[24],"optimization":[25,45],"to":[26,71,91,110],"synchronously":[27],"optimize":[28],"stage":[30],"specification":[31],"and":[32,79,86,100,107],"green":[33],"interval":[34],"duration.":[35],"Under":[36],"reformulated":[37],"demands,":[39],"intrinsic":[41],"imperfections":[42],"of":[43,105,121],"(implementing":[44],"in)":[46],"discrete":[47],"continuous":[49],"spaces":[51],"revealed.":[53],"By":[54],"comparison,":[55],"space":[58],"offers":[59],"a":[60],"unified":[61],"search":[62],"space,":[63],"in":[64,83],"which":[65],"our":[66],"proposed":[67,95,127],"method":[68,96,128],"is":[69],"able":[70],"better":[72],"balance":[73],"trade-off":[75],"between":[76],"frequent":[77],"switching":[78],"unsaturated":[80],"release.":[81],"Experiments":[82],"both":[84],"single-agent":[85],"multi-agent":[87],"scenarios":[88],"given":[90],"demonstrate":[92],"that":[93,125],"reduces":[97],"queue":[98],"length":[99],"delay":[101],"by":[102,116],"an":[103],"average":[104],"12.72%":[106],"11.89%,":[108],"compared":[109],"state-of-the-art":[112],"RL":[113],"methods.":[114],"Furthermore,":[115],"calculating":[117],"Gini":[119],"coefficients":[120],"right-of-way,":[122],"reveal":[124],"does":[129],"not":[130],"harm":[131],"fairness":[132],"while":[133],"improving":[134],"efficiency.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}