{"id":"https://openalex.org/W2485902895","doi":"https://doi.org/10.1109/acc.2016.7525014","title":"Large-scale traffic grid signal control with regional Reinforcement Learning","display_name":"Large-scale traffic grid signal control with regional Reinforcement Learning","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2485902895","doi":"https://doi.org/10.1109/acc.2016.7525014","mag":"2485902895"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2016.7525014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2016.7525014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 American Control Conference (ACC)","raw_type":"proceedings-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/A5101737502","display_name":"Tianshu Chu","orcid":"https://orcid.org/0000-0002-9404-3348"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianshu Chu","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Stanford University, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112694715","display_name":"Shuhui Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuhui Qu","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Stanford University, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101422661","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0003-1857-5569"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Stanford University, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101737502"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":2.4335,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.89502885,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"815","last_page":"820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9998000264167786,"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":0.9998000264167786,"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":0.998199999332428,"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":0.9836999773979187,"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":0.8343580961227417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7382310628890991},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.6736056804656982},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.6423640847206116},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6358014345169067},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.539954662322998},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.47429516911506653},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4640364646911621},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4167852997779846},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3649042248725891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33769288659095764},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12862202525138855}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8343580961227417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382310628890991},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.6736056804656982},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6423640847206116},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6358014345169067},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.539954662322998},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.47429516911506653},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4640364646911621},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4167852997779846},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3649042248725891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33769288659095764},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12862202525138855},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acc.2016.7525014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2016.7525014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W33871791","https://openalex.org/W1575592356","https://openalex.org/W1594515725","https://openalex.org/W1678713393","https://openalex.org/W1928215159","https://openalex.org/W1986659999","https://openalex.org/W2027628482","https://openalex.org/W2073384958","https://openalex.org/W2076337359","https://openalex.org/W2121863487","https://openalex.org/W2121947440","https://openalex.org/W2122241715","https://openalex.org/W2125001944","https://openalex.org/W2132603077","https://openalex.org/W2146544184","https://openalex.org/W2153160520","https://openalex.org/W2160085675","https://openalex.org/W2963011350","https://openalex.org/W3103910758","https://openalex.org/W4211221179","https://openalex.org/W4214717370","https://openalex.org/W6634413486","https://openalex.org/W6635618703","https://openalex.org/W7001212498","https://openalex.org/W7011621630"],"related_works":["https://openalex.org/W4256429076","https://openalex.org/W1971174658","https://openalex.org/W2099195351","https://openalex.org/W4296209631","https://openalex.org/W2348092930","https://openalex.org/W2012063272","https://openalex.org/W4306904969","https://openalex.org/W2561617217","https://openalex.org/W2138720691","https://openalex.org/W2138685729"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,94,144],"(RL)":[2],"based":[3],"traffic":[4,9,115,124,147],"signal":[5],"control":[6,81,99,135],"for":[7,22,83],"large-scale":[8,114],"grids":[10],"is":[11,31,158],"challenging":[12],"due":[13],"to":[14,96,131],"the":[15,38,58,79,98,113,122,133,142],"curse":[16],"of":[17,51,93],"dimensionality.":[18],"Most":[19],"particularly,":[20],"searching":[21],"an":[23],"optimal":[24,80],"policy":[25,82,136],"in":[26,101],"a":[27,64,91],"huge":[28],"action":[29],"space":[30],"impractical,":[32],"even":[33],"with":[34],"approximate":[35,129],"Q-functions.":[36],"On":[37],"other":[39],"hand,":[40],"heuristic":[41,168],"self-organizing":[42],"algorithms":[43],"could":[44,70],"achieve":[45],"efficient":[46,160],"decentralized":[47,169],"control,":[48],"but":[49],"most":[50],"them":[52],"have":[53],"few":[54],"effort":[55],"on":[56,121],"optimizing":[57],"real-time":[59,123],"traffic.":[60],"This":[61],"paper":[62],"proposes":[63],"new":[65],"regional":[66,155],"RL":[67,156],"algorithm":[68,157],"that":[69,153],"form":[71],"local":[72],"cooperation":[73],"regions":[74,102],"adaptively,":[75],"and":[76,161,164],"then":[77],"learn":[78,132],"each":[84,107,138],"region":[85],"separately.":[86],"In":[87],"particular,":[88],"we":[89,110,127],"maintain":[90],"set":[92],"parameters":[95,145],"capture":[97],"patterns":[100],"at":[103],"different":[104],"scales.":[105],"At":[106],"time":[108],"step,":[109],"first":[111],"decompose":[112],"grid":[116],"into":[117],"disjoint":[118],"sub-regions,":[119],"depending":[120],"condition.":[125],"Next,":[126],"apply":[128],"Q-learning":[130],"centralized":[134],"within":[137],"sub-region,":[139],"by":[140],"updating":[141],"corresponding":[143],"upon":[146],"observations.":[148],"The":[149],"numerical":[150],"experiments":[151],"demonstrate":[152],"our":[154],"computationally":[159],"functionally":[162],"adaptive,":[163],"it":[165],"outperforms":[166],"typical":[167],"algorithms.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}