{"id":"https://openalex.org/W7011621630","doi":null,"title":"Multi-Agent Reinforcement Learning for Traffic Light control","display_name":"Multi-Agent Reinforcement Learning for Traffic Light control","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W7011621630"},"language":"en","primary_location":{"id":"pmh:uu:oai:dspace.library.uu.nl:1874/20827","doi":null,"is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/20827","pdf_url":"https://dspace.library.uu.nl/handle/1874/20827","source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning: Proceedings of the Seventeenth International Conference (ICML'2000), 1151","raw_type":"info:eu-repo/semantics/bookpart"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.library.uu.nl/handle/1874/20827","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060596453","display_name":"Marco Wiering","orcid":"https://orcid.org/0000-0003-4331-7537","observed_orcids":["https://orcid.org/0000-0003-4331-7537"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wiering, M.A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141428535","display_name":"Intelligente Systemen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Intelligente Systemen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132892735","display_name":"Dep Eng\u00aa Inform\u00e1tica","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dep Informatica","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":195,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9785000085830688,"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":0.9785000085830688,"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":0.007600000128149986,"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":0.004800000227987766,"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/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.8809999823570251},{"id":"https://openalex.org/keywords/traffic-signal-control","display_name":"traffic signal control","score":0.9929999709129333},{"id":"https://openalex.org/keywords/traffic-signal-timing","display_name":"traffic signal timing","score":0.6940000057220459},{"id":"https://openalex.org/keywords/vehicle-waiting-time","display_name":"vehicle waiting time","score":0.9340000152587891},{"id":"https://openalex.org/keywords/value-function","display_name":"value function","score":0.859000027179718},{"id":"https://openalex.org/keywords/agent-communication","display_name":"agent communication","score":0.9070000052452087},{"id":"https://openalex.org/keywords/route-choice","display_name":"route choice","score":0.6990000009536743},{"id":"https://openalex.org/keywords/urban-traffic-management","display_name":"urban traffic management","score":0.5429999828338623}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7980999946594238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6761999726295471},{"id":"https://openalex.org/C2987419075","wikidata":"https://www.wikidata.org/wiki/Q8004","display_name":"Traffic signal","level":2,"score":0.614799976348877},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.39730000495910645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3822000026702881},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.30329999327659607},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C86266404","wikidata":"https://www.wikidata.org/wiki/Q7832512","display_name":"Traffic optimization","level":4,"score":0.2581999897956848},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2526000142097473}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:uu:oai:dspace.library.uu.nl:1874/20827","doi":null,"is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/20827","pdf_url":"https://dspace.library.uu.nl/handle/1874/20827","source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning: Proceedings of the Seventeenth International Conference (ICML'2000), 1151","raw_type":"info:eu-repo/semantics/bookpart"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.32.9887","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.32.9887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uu.nl/people/marco/GROUP/ARTICLES/TRAFFIC_LIGHT.ps.gz","raw_type":"text"},{"id":"pmh:oai:dspace.library.uu.nl:1874/20827","doi":null,"is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/20827","pdf_url":null,"source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Part of book"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/b2bcfa5d-95c3-49b4-b792-72d770ab1a7e","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/11370/b2bcfa5d-95c3-49b4-b792-72d770ab1a7e","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wiering, M 2000, Multi-agent reinforcement learning for traffic light control. in ICML. pp. 1151-1158.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:rug:oai:pure.rug.nl:publications/b2bcfa5d-95c3-49b4-b792-72d770ab1a7e","doi":null,"is_oa":false,"landing_page_url":"https://research.rug.nl/en/publications/b2bcfa5d-95c3-49b4-b792-72d770ab1a7e","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICML, 1151 - 1158","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:uu:oai:dspace.library.uu.nl:1874/20827","doi":null,"is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/20827","pdf_url":"https://dspace.library.uu.nl/handle/1874/20827","source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning: Proceedings of the Seventeenth International Conference (ICML'2000), 1151","raw_type":"info:eu-repo/semantics/bookpart"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/11"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7011621630.pdf","grobid_xml":"https://content.openalex.org/works/W7011621630.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7100852899","https://openalex.org/W2162115371","https://openalex.org/W2953450563","https://openalex.org/W2070310653","https://openalex.org/W1914389580","https://openalex.org/W7104262424","https://openalex.org/W2955226134","https://openalex.org/W2404226462","https://openalex.org/W7021098131","https://openalex.org/W4205998584"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"using":[3,63],"multi-agent":[4],"reinforcement":[5],"learning":[6,10],"(RL)":[7],"algorithms":[8,104],"for":[9,35],"traffic":[11,41,46,71,108],"light":[12,72,109],"controllers":[13],"to":[14,90,94],"minimize":[15],"the":[16,51,78,85,102],"overall":[17],"waiting":[18,33,53],"time":[19],"of":[20,40,45,55,66,88],"cars":[21,36,57,89],"in":[22],"a":[23],"city.":[24],"The":[25,97],"RL":[26,61,103],"systems":[27,62],"learn":[28],"value":[29,79],"functions":[30,80],"estimating":[31],"expected":[32],"times":[34,54],"given":[37],"different":[38,64],"settings":[39,44],"lights.":[42],"Selected":[43],"lights":[47],"result":[48],"from":[49],"combining":[50],"predicted":[52],"all":[56],"involved.":[58],"We":[59,74],"investigate":[60],"kinds":[65],"global":[67],"communicated":[68],"information":[69],"between":[70],"agents.":[73],"also":[75],"show":[76,100],"how":[77],"can":[81,105],"be":[82],"used":[83],"by":[84],"driving":[86,114],"policies":[87,115],"select":[91],"optimal":[92],"routes":[93],"destination":[95],"addresses.":[96],"experimental":[98],"results":[99],"that":[101,112],"outperform":[106],"non-adaptable":[107],"controllers,":[110],"and":[111],"optimizing":[113],"is":[116],"very":[117],"useful.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":8}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2025-10-10T00:00:00"}