{"id":"https://openalex.org/W7163201409","doi":"https://doi.org/10.3390/math14111942","title":"Fuzzy-Guided Exploration for Multi-Agent Reinforcement Learning in Traffic Signal Control","display_name":"Fuzzy-Guided Exploration for Multi-Agent Reinforcement Learning in Traffic Signal Control","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163201409","doi":"https://doi.org/10.3390/math14111942"},"language":"en","primary_location":{"id":"doi:10.3390/math14111942","doi":"https://doi.org/10.3390/math14111942","is_oa":true,"landing_page_url":"https://doi.org/10.3390/math14111942","pdf_url":null,"source":{"id":"https://openalex.org/S4210192031","display_name":"Mathematics","issn_l":"2227-7390","issn":["2227-7390"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/math14111942","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114569820","display_name":"Dejan \u0106iprovski","orcid":"https://orcid.org/0000-0002-6153-9574","observed_orcids":["https://orcid.org/0000-0002-6153-9574"]},"institutions":[{"id":"https://openalex.org/I170253739","display_name":"Singidunum University","ror":"https://ror.org/017v7rz39","country_code":"RS","type":"education","lineage":["https://openalex.org/I170253739"]},{"id":"https://openalex.org/I4405257720","display_name":"Vlatacom Institute (Serbia)","ror":"https://ror.org/05kbhwa49","country_code":"RS","type":"company","lineage":["https://openalex.org/I4405257720"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Dejan \u0106iprovski","raw_affiliation_strings":["Artificial Intelligence Department, Vlatacom Institute, 11070 Belgrade, Serbia","Faculty of Informatics and Computing, Singidunum University, 11000 Belgrade, Serbia"],"raw_orcid":"https://orcid.org/0000-0002-6153-9574","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Department, Vlatacom Institute, 11070 Belgrade, Serbia","institution_ids":["https://openalex.org/I4405257720"]},{"raw_affiliation_string":"Faculty of Informatics and Computing, Singidunum University, 11000 Belgrade, Serbia","institution_ids":["https://openalex.org/I170253739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101518778","display_name":"Nemanja Ili\u0107","orcid":"https://orcid.org/0000-0002-2763-2564","observed_orcids":["https://orcid.org/0000-0002-2763-2564"]},"institutions":[{"id":"https://openalex.org/I4210105304","display_name":"Union University","ror":"https://ror.org/01p8d4t94","country_code":"RS","type":"education","lineage":["https://openalex.org/I4210105304"]},{"id":"https://openalex.org/I4405257720","display_name":"Vlatacom Institute (Serbia)","ror":"https://ror.org/05kbhwa49","country_code":"RS","type":"company","lineage":["https://openalex.org/I4405257720"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Nemanja Ili\u0107","raw_affiliation_strings":["Artificial Intelligence Department, Vlatacom Institute, 11070 Belgrade, Serbia","Department of Information Technologies, College of Applied Technical Sciences, 37000 Kru\u0161evac, Serbia","School of Computing, Union University, 11000 Belgrade, Serbia"],"raw_orcid":"https://orcid.org/0000-0002-2763-2564","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Department, Vlatacom Institute, 11070 Belgrade, Serbia","institution_ids":["https://openalex.org/I4405257720"]},{"raw_affiliation_string":"Department of Information Technologies, College of Applied Technical Sciences, 37000 Kru\u0161evac, Serbia","institution_ids":[]},{"raw_affiliation_string":"School of Computing, Union University, 11000 Belgrade, Serbia","institution_ids":["https://openalex.org/I4210105304"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086554527","display_name":"Bo\u0161ko Bo\u017eilovi\u0107","orcid":"https://orcid.org/0000-0001-6775-8543","observed_orcids":["https://orcid.org/0000-0001-6775-8543"]},"institutions":[{"id":"https://openalex.org/I4405257720","display_name":"Vlatacom Institute (Serbia)","ror":"https://ror.org/05kbhwa49","country_code":"RS","type":"company","lineage":["https://openalex.org/I4405257720"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Bo\u0161ko Bo\u017eilovi\u0107","raw_affiliation_strings":["Artificial Intelligence Department, Vlatacom Institute, 11070 Belgrade, Serbia"],"raw_orcid":"https://orcid.org/0000-0001-6775-8543","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Department, Vlatacom Institute, 11070 Belgrade, Serbia","institution_ids":["https://openalex.org/I4405257720"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075103590","display_name":"Miljan Vu\u010deti\u0107","orcid":"https://orcid.org/0000-0002-4362-6201","observed_orcids":["https://orcid.org/0000-0002-4362-6201"]},"institutions":[{"id":"https://openalex.org/I142208455","display_name":"VSB - Technical University of Ostrava","ror":"https://ror.org/05x8mcb75","country_code":"CZ","type":"education","lineage":["https://openalex.org/I142208455"]},{"id":"https://openalex.org/I170253739","display_name":"Singidunum University","ror":"https://ror.org/017v7rz39","country_code":"RS","type":"education","lineage":["https://openalex.org/I170253739"]},{"id":"https://openalex.org/I4405257720","display_name":"Vlatacom Institute (Serbia)","ror":"https://ror.org/05kbhwa49","country_code":"RS","type":"company","lineage":["https://openalex.org/I4405257720"]}],"countries":["CZ","RS"],"is_corresponding":false,"raw_author_name":"Miljan Vu\u010deti\u0107","raw_affiliation_strings":["Artificial Intelligence Department, Vlatacom Institute, 11070 Belgrade, Serbia","Department of Systems Engineering and Informatics, V\u0160B\u2014Technical University of Ostrava, 708 00 Ostrava, Czech Republic","Faculty of Informatics and Computing, Singidunum University, 11000 Belgrade, Serbia"],"raw_orcid":"https://orcid.org/0000-0002-4362-6201","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Department, Vlatacom Institute, 11070 Belgrade, Serbia","institution_ids":["https://openalex.org/I4405257720"]},{"raw_affiliation_string":"Department of Systems Engineering and Informatics, V\u0160B\u2014Technical University of Ostrava, 708 00 Ostrava, Czech Republic","institution_ids":["https://openalex.org/I142208455"]},{"raw_affiliation_string":"Faculty of Informatics and Computing, Singidunum University, 11000 Belgrade, Serbia","institution_ids":["https://openalex.org/I170253739"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2600,"currency":"CHF","value_usd":3137},"apc_paid":{"value":2600,"currency":"CHF","value_usd":3137},"fwci":3.2328,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89345815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"14","issue":"11","first_page":"1942","last_page":"1942"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9794999957084656,"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":0.9794999957084656,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.011500000022351742,"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"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.0027000000700354576,"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/traffic-signal-control","display_name":"traffic signal control","score":0.8389999866485596},{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.996999979019165},{"id":"https://openalex.org/keywords/epsilon-greedy-exploration","display_name":"epsilon-greedy exploration","score":0.8650000095367432},{"id":"https://openalex.org/keywords/phase-pressure","display_name":"phase pressure","score":0.7559999823570251},{"id":"https://openalex.org/keywords/domain-knowledge-integration","display_name":"domain knowledge integration","score":0.6819999814033508},{"id":"https://openalex.org/keywords/traffic-congestion","display_name":"traffic congestion","score":0.5889999866485596},{"id":"https://openalex.org/keywords/signalized-intersections","display_name":"signalized intersections","score":0.4909999966621399},{"id":"https://openalex.org/keywords/centralized-training-with-decentralized-execution","display_name":"centralized training decentralized execution","score":0.6880000233650208},{"id":"https://openalex.org/keywords/qmix","display_name":"QMIX","score":0.7490000128746033},{"id":"https://openalex.org/keywords/urban-road-networks","display_name":"urban road networks","score":0.5090000033378601}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7059999704360962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6261000037193298},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.570900022983551},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4609000086784363},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40950000286102295},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3959999978542328},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C195975749","wikidata":"https://www.wikidata.org/wiki/Q1475705","display_name":"Fuzzy control system","level":3,"score":0.36800000071525574},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3310999870300293},{"id":"https://openalex.org/C2987419075","wikidata":"https://www.wikidata.org/wiki/Q8004","display_name":"Traffic signal","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C2778391309","wikidata":"https://www.wikidata.org/wiki/Q7832527","display_name":"Traffic simulation","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2939999997615814},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C2775905063","wikidata":"https://www.wikidata.org/wiki/Q6132995","display_name":"Road traffic control","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/math14111942","doi":"https://doi.org/10.3390/math14111942","is_oa":true,"landing_page_url":"https://doi.org/10.3390/math14111942","pdf_url":null,"source":{"id":"https://openalex.org/S4210192031","display_name":"Mathematics","issn_l":"2227-7390","issn":["2227-7390"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:056a796364f041adae3e00c0aa71471d","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/056a796364f041adae3e00c0aa71471d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mathematics, Vol 14, Iss 11, p 1942 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/math14111942","doi":"https://doi.org/10.3390/math14111942","is_oa":true,"landing_page_url":"https://doi.org/10.3390/math14111942","pdf_url":null,"source":{"id":"https://openalex.org/S4210192031","display_name":"Mathematics","issn_l":"2227-7390","issn":["2227-7390"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G535059049","display_name":null,"funder_award_id":"CZ.10.03.01/00/22_0 03/0000048","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320329307","display_name":"Science Fund of the Republic of Serbia","ror":"https://ror.org/02r531a15"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W2007894170","https://openalex.org/W2019207321","https://openalex.org/W2040810017","https://openalex.org/W2097072771","https://openalex.org/W2139728973","https://openalex.org/W2145339207","https://openalex.org/W2166533447","https://openalex.org/W2168405694","https://openalex.org/W2168930969","https://openalex.org/W2292533394","https://openalex.org/W2747213132","https://openalex.org/W2807741983","https://openalex.org/W2903709398","https://openalex.org/W2913662073","https://openalex.org/W2915117209","https://openalex.org/W2964749398","https://openalex.org/W2967474307","https://openalex.org/W2998187693","https://openalex.org/W3034311880","https://openalex.org/W4211007335","https://openalex.org/W4376480457","https://openalex.org/W4385767260","https://openalex.org/W4404645986","https://openalex.org/W4407767292","https://openalex.org/W4408178282","https://openalex.org/W4409217692","https://openalex.org/W4410121475","https://openalex.org/W7117741076","https://openalex.org/W7124239827","https://openalex.org/W7124263640"],"related_works":["https://openalex.org/W4282021251","https://openalex.org/W7131135250","https://openalex.org/W1999371911","https://openalex.org/W4205998584","https://openalex.org/W7021098131","https://openalex.org/W7213538992","https://openalex.org/W7222400601","https://openalex.org/W2781537693","https://openalex.org/W4281652995","https://openalex.org/W7124297724"],"abstract_inverted_index":{"Traffic":[0],"signal":[1,47,187,194],"control":[2],"over":[3],"urban":[4],"networks":[5],"requires":[6],"coordinating":[7],"the":[8,54,103,108,119,144,153,161],"controllers":[9],"of":[10,18,41,102],"multiple":[11],"signalized":[12],"intersections":[13],"toward":[14],"a":[15,70,91,96,132,136,185],"shared":[16],"goal":[17],"minimizing":[19],"network-wide":[20],"congestion.":[21],"Multi-agent":[22],"reinforcement":[23],"learning":[24,116],"(MARL)":[25],"methods":[26,43],"have":[27],"shown":[28],"considerable":[29],"promise":[30],"in":[31,68,100,146,177,192],"this":[32],"setting.":[33],"The":[34],"epsilon\u2013greedy":[35],"exploration":[36,140,168],"strategy":[37],"adopted":[38],"by":[39],"many":[40],"these":[42],"treats":[44],"every":[45],"candidate":[46,89],"phase":[48,80,90],"as":[49,82],"equally":[50],"worth":[51],"trying,":[52],"discarding":[53],"rich":[55],"domain":[56],"knowledge":[57],"that":[58,167,181,190],"traffic":[59,77,193],"theory":[60],"already":[61],"provides.":[62],"This":[63],"paper":[64],"proposes":[65],"fuzzy-guided":[66],"exploration,":[67],"which":[69],"multi-criteria":[71],"fuzzy":[72],"inference":[73],"system":[74],"uses":[75],"local":[76],"conditions,":[78],"with":[79,122,149],"pressure":[81],"its":[83],"primary":[84],"input,":[85],"to":[86,188],"assign":[87],"each":[88],"priority.":[92],"These":[93,164],"priorities":[94],"define":[95],"sampling":[97],"distribution":[98],"used":[99],"place":[101],"uniform":[104],"draw.":[105],"We":[106],"evaluate":[107],"method":[109],"across":[110],"four":[111],"MARL":[112],"algorithms":[113],"covering":[114],"independent":[115],"(IQL)":[117],"and":[118,128,135,156,180],"centralized":[120],"training":[121],"decentralized":[123],"execution":[124],"paradigm":[125],"(VDN,":[126],"QMIX,":[127],"QPLEX)":[129],"on":[130,152,160],"both":[131],"synthetic":[133,154],"grid":[134,155],"real-world":[137,162],"network.":[138,163],"Fuzzy-guided":[139],"consistently":[141],"improves":[142],"upon":[143],"baseline":[145],"all":[147],"combinations,":[148],"tangible":[150],"gains":[151],"substantially":[157],"larger":[158],"improvements":[159],"findings":[165],"demonstrate":[166],"is":[169],"an":[170],"effective":[171],"intervention":[172],"point":[173],"for":[174],"domain-knowledge":[175],"integration":[176],"cooperative":[178],"MARL,":[179],"pressure-based":[182],"scoring":[183],"provides":[184],"well-suited":[186],"serve":[189],"role":[191],"control.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-06-03T00:00:00"}
