{"id":"https://openalex.org/W7225749064","doi":"https://doi.org/10.54254/2755-2721/2026.38754","title":"Federated Reinforcement Learning for Traffic Signal Control: Aggregation Strategies under Intersection-Level Heterogeneity","display_name":"Federated Reinforcement Learning for Traffic Signal Control: Aggregation Strategies under Intersection-Level Heterogeneity","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225749064","doi":"https://doi.org/10.54254/2755-2721/2026.38754"},"language":"en","primary_location":{"id":"doi:10.54254/2755-2721/2026.38754","doi":"https://doi.org/10.54254/2755-2721/2026.38754","is_oa":true,"landing_page_url":"https://doi.org/10.54254/2755-2721/2026.38754","pdf_url":null,"source":{"id":"https://openalex.org/S4387281889","display_name":"Applied and Computational Engineering","issn_l":"2755-2721","issn":["2755-2721","2755-273X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied and Computational Engineering","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.54254/2755-2721/2026.38754","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123804443","display_name":"Jikai Tang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jikai Tang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5123804443"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"280","issue":"1","first_page":"None","last_page":"None"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9804999828338623,"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":0.9804999828338623,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.008100000210106373,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0017000000225380063,"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":[],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8892999887466431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721999883651733},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.6396999955177307},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5202000141143799},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47279998660087585},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3370000123977661},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.32839998602867126},{"id":"https://openalex.org/C82578977","wikidata":"https://www.wikidata.org/wiki/Q16773055","display_name":"Data aggregator","level":3,"score":0.32339999079704285},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.31139999628067017},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3059000074863434},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C47796450","wikidata":"https://www.wikidata.org/wiki/Q508378","display_name":"Intelligent transportation system","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C527821871","wikidata":"https://www.wikidata.org/wiki/Q228502","display_name":"Access control","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C149442271","wikidata":"https://www.wikidata.org/wiki/Q4826616","display_name":"Automatically switched optical network","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C62989814","wikidata":"https://www.wikidata.org/wiki/Q854648","display_name":"Gossip","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C15845906","wikidata":"https://www.wikidata.org/wiki/Q1172338","display_name":"Data exchange","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.54254/2755-2721/2026.38754","doi":"https://doi.org/10.54254/2755-2721/2026.38754","is_oa":true,"landing_page_url":"https://doi.org/10.54254/2755-2721/2026.38754","pdf_url":null,"source":{"id":"https://openalex.org/S4387281889","display_name":"Applied and Computational Engineering","issn_l":"2755-2721","issn":["2755-2721","2755-273X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied and Computational Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.54254/2755-2721/2026.38754","doi":"https://doi.org/10.54254/2755-2721/2026.38754","is_oa":true,"landing_page_url":"https://doi.org/10.54254/2755-2721/2026.38754","pdf_url":null,"source":{"id":"https://openalex.org/S4387281889","display_name":"Applied and Computational Engineering","issn_l":"2755-2721","issn":["2755-2721","2755-273X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied and Computational Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Urban":[0],"traffic":[1,75,238],"signal":[2,76],"control":[3,86,193],"must":[4,27],"adapt":[5],"to":[6,31],"demand":[7],"that":[8,171,235],"varies":[9],"across":[10,58],"intersections,":[11],"time":[12],"of":[13,68,162],"day,":[14],"and":[15,18,46,70,88,112,116,126,143,156,159,164,177,180,210,231],"network":[16],"topology,":[17,105],"centralized":[19],"reinforcement":[20,36,72,101,128],"learning":[21,37,73,99,102],"becomes":[22],"impractical":[23],"when":[24],"every":[25],"intersection":[26,208],"transmit":[28],"raw":[29],"observations":[30],"a":[32,80,92,140,146],"single":[33],"learner.":[34],"Federated":[35],"(FRL)":[38],"relaxes":[39],"this":[40],"constraint":[41],"by":[42,215],"training":[43],"local":[44,136,165],"controllers":[45],"exchanging":[47],"only":[48],"model":[49],"updates,":[50],"but":[51],"the":[52,84,188,237,242],"evidence":[53],"supporting":[54],"it":[55,144],"is":[56,245],"dispersed":[57],"incompatible":[59],"experimental":[60],"settings.":[61],"This":[62],"article":[63],"reviews":[64],"ten":[65],"recent":[66],"studies":[67],"federated":[69,122],"distributed":[71,125],"for":[74,83],"control,":[77],"together":[78],"with":[79,206],"public":[81],"benchmark":[82],"underlying":[85],"task,":[87],"organizes":[89],"them":[90],"through":[91,132],"common":[93],"comparison":[94],"framework":[95],"covering":[96],"traffic-control":[97],"setting,":[98],"paradigm,":[100],"algorithm,":[103],"federation":[104,141,243],"aggregation":[106,151,229],"strategy,":[107],"data":[108],"heterogeneity,":[109],"efficiency,":[110],"privacy":[111,222],"security,":[113],"evaluation":[114,233],"design,":[115],"deployment":[117],"readiness.":[118],"The":[119,167],"review":[120],"separates":[121],"methods":[123],"from":[124,148],"multi-agent":[127],"learning,":[129],"which":[130],"coordinate":[131],"peer":[133],"consensus":[134],"or":[135,198,220],"interaction":[137],"rather":[138],"than":[139],"server,":[142],"traces":[145],"shift":[147],"uniform":[149],"global":[150,163],"toward":[152],"partial-layer":[153],"sharing,":[154],"clustered":[155],"hierarchical":[157],"federation,":[158],"personalized":[160],"combinations":[161],"models.":[166],"synthesized":[168],"results":[169],"indicate":[170],"model-level":[172],"collaboration":[173],"can":[174],"accelerate":[175],"convergence":[176],"reduce":[178],"delay":[179],"queue":[181],"length":[182],"in":[183],"several":[184],"calibrated":[185],"networks,":[186],"yet":[187],"gains":[189],"are":[190,212],"conditional:":[191],"fixed-time":[192],"remains":[194],"competitive":[195],"under":[196],"light":[197],"balanced":[199],"demand,":[200],"shared":[201],"parameters":[202],"weaken":[203],"on":[204,227,232],"networks":[205],"irregular":[207],"geometry,":[209],"improvements":[211],"seldom":[213],"accompanied":[214],"repeated":[216],"trials,":[217],"uncertainty":[218],"estimates,":[219],"adversarial":[221],"evaluation.":[223],"Progress":[224],"therefore":[225],"depends":[226],"task-specific":[228],"design":[230],"protocols":[234],"hold":[236],"scenario":[239],"constant":[240],"while":[241],"configuration":[244],"varied.":[246]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-11T00:00:00"}