{"id":"https://openalex.org/W4414590260","doi":"https://doi.org/10.1145/3774904.3792352","title":"HALO: Hierarchical Reinforcement Learning for Large-Scale Adaptive Traffic Signal Control","display_name":"HALO: Hierarchical Reinforcement Learning for Large-Scale Adaptive Traffic Signal Control","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W4414590260","doi":"https://doi.org/10.1145/3774904.3792352"},"language":"en","primary_location":{"id":"doi:10.1145/3774904.3792352","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792352","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792352","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102421308","display_name":"Yaqiao Zhu","orcid":"https://orcid.org/0009-0004-1482-3240"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yaqiao Zhu","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0004-1482-3240","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, United Kingdom","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053684989","display_name":"Hongkai Wen","orcid":"https://orcid.org/0000-0003-1159-090X"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hongkai Wen","raw_affiliation_strings":["Department of Computer Science, University of Warwick, Coventry, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-1159-090X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Warwick, Coventry, United Kingdom","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770003","display_name":"Geyong Min","orcid":"https://orcid.org/0000-0003-1395-7314"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Geyong Min","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-1395-7314","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, United Kingdom","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"last","author":{"id":null,"display_name":"Man Luo","orcid":"https://orcid.org/0000-0002-7346-9024"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Man Luo","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-7346-9024","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, United Kingdom","institution_ids":["https://openalex.org/I23923803"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00503468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5368","last_page":"5379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9297000169754028,"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":0.9297000169754028,"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/T12495","display_name":"Electrostatic Discharge in Electronics","score":0.9228000044822693,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9126999974250793,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8398000001907349},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.714900016784668},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6054999828338623},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4984999895095825},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4932999908924103},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4535999894142151},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.388700008392334}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8398000001907349},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.714900016784668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7139000296592712},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5012000203132629},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4932999908924103},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3580000102519989},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C123138037","wikidata":"https://www.wikidata.org/wiki/Q5570871","display_name":"Global network","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C2987015589","wikidata":"https://www.wikidata.org/wiki/Q1040098","display_name":"Learning network","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3774904.3792352","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792352","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.14391","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.14391","pdf_url":"https://arxiv.org/pdf/2506.14391","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.14391","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.14391","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792352","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792352","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Adaptive":[0],"traffic":[1,16,176],"signal":[2],"control":[3,116],"(ATSC)":[4],"is":[5,18],"essential":[6],"for":[7,79],"mitigating":[8],"urban":[9],"congestion":[10],"in":[11,61,208],"modern":[12],"smart":[13],"cities,":[14],"where":[15,138],"infrastructure":[17],"evolving":[19],"into":[20,85],"interconnected":[21],"Web-of-Things":[22],"(WoT)":[23],"environments":[24],"with":[25,171],"thousands":[26],"of":[27,129],"sensing-and-control":[28],"nodes.":[29],"However,":[30],"existing":[31],"methods":[32,53],"face":[33],"a":[34,70,88,165],"critical":[35],"scalability-coordination":[36],"tradeoff:":[37],"centralized":[38],"approaches":[39],"optimize":[40],"global":[41,90,123,140],"objectives":[42],"but":[43],"become":[44],"computationally":[45],"intractable":[46],"at":[47],"city":[48],"scale,":[49],"while":[50,109,203],"decentralized":[51,115],"multi-agent":[52],"scale":[54],"efficiently":[55],"yet":[56],"lack":[57],"network-level":[58,144],"coherence,":[59],"resulting":[60],"suboptimal":[62],"performance.":[63],"In":[64],"this":[65,77],"paper,":[66],"we":[67,132],"present":[68],"HALO,":[69],"hierarchical":[71],"reinforcement":[72],"learning":[73],"framework":[74],"that":[75,146],"addresses":[76],"tradeoff":[78],"large-scale":[80,168,210],"ATSC.":[81],"HALO":[82,158,188],"decouples":[83],"decision-making":[84],"two":[86],"levels:":[87],"high-level":[89],"guidance":[91,107],"policy":[92,141],"employs":[93],"Transformer-LSTM":[94],"encoders":[95],"to":[96,151,214],"model":[97],"spatio-temporal":[98],"dependencies":[99],"across":[100,200],"the":[101,139,205,226],"entire":[102],"network":[103,170,197],"and":[104,122,164,183,192,220],"broadcast":[105],"compact":[106],"signals,":[108],"low-level":[110],"local":[111,120,147],"intersection":[112],"policies":[113,148],"execute":[114],"conditioned":[117],"on":[118,160],"both":[119],"observations":[121],"context.":[124],"To":[125],"ensure":[126],"better":[127],"alignment":[128],"global-local":[130],"objectives,":[131],"introduce":[133],"an":[134],"adversarial":[135],"goal-setting":[136],"mechanism":[137],"proposes":[142],"challenging-yet-feasible":[143],"targets":[145],"are":[149],"trained":[150],"surpass,":[152],"fostering":[153],"robust":[154],"coordination.":[155],"We":[156],"evaluate":[157],"extensively":[159],"multiple":[161],"standard":[162],"benchmarks,":[163,202],"newly":[166],"constructed":[167],"Manhattan-like":[169],"2,668":[172],"intersections":[173],"under":[174],"real-world":[175],"patterns,":[177],"including":[178],"peak":[179],"transitions,":[180],"adverse":[181],"weather":[182],"holiday":[184],"surges.":[185],"Results":[186],"demonstrate":[187],"shows":[189],"competitive":[190],"performance":[191,207],"becomes":[193],"increasingly":[194],"dominant":[195],"as":[196],"complexity":[198],"grows":[199],"small-scale":[201],"delivering":[204],"strongest":[206],"all":[209],"regimes,":[211],"offering":[212],"up":[213],"6.8%":[215],"lower":[216,222],"average":[217,223],"travel":[218],"time":[219],"5.0%":[221],"delay":[224],"than":[225],"best":[227],"state-of-the-art.":[228]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}