乐胖代购免代理版

{"id":"https://openalex.org/W4387123596","doi":"https://doi.org/10.1109/case56687.2023.10260400","title":"Efficient Policy Transfer in Large-Scale Traffic Light Control via Multi-Agent Hierarchical Reinforcement Learning","display_name":"Efficient Policy Transfer in Large-Scale Traffic Light Control via Multi-Agent Hierarchical Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-26","ids":{"openalex":"https://openalex.org/W4387123596","doi":"https://doi.org/10.1109/case56687.2023.10260400"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/case56687.2023.10260400","pdf_url":null,"source":{"id":"https://openalex.org/S4363607892","display_name":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5100756590","display_name":"Chenghao Li","orcid":"https://orcid.org/0000-0001-5667-7430"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenghao Li","raw_affiliation_strings":["Tsinghua University,Center for Intelligent and Networked System,Dept Automation,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Intelligent and Networked System,Dept Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105309533","display_name":"Yan Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu Yan","raw_affiliation_strings":["Tsinghua University,Center for Intelligent and Networked System,Dept Automation,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Intelligent and Networked System,Dept Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014109600","display_name":"Qianchuan Zhao","orcid":"https://orcid.org/0000-0002-7952-5621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianchuan Zhao","raw_affiliation_strings":["Tsinghua University,Center for Intelligent and Networked System,Dept Automation,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Intelligent and Networked System,Dept Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":{"min":0,"max":68},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Modeling and Control of Traffic Flow Systems","score":0.9996,"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":"Modeling and Control of Traffic Flow Systems","score":0.9996,"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 Flow Prediction and Forecasting","score":0.9964,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety Systems","score":0.9959,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.6837722},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.63175803},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement Learning","score":0.581725},{"id":"https://openalex.org/keywords/traffic-signal-control","display_name":"Traffic Signal Control","score":0.571014},{"id":"https://openalex.org/keywords/urban-driving","display_name":"Urban Driving","score":0.526984},{"id":"https://openalex.org/keywords/lane-detection","display_name":"Lane Detection","score":0.523673},{"id":"https://openalex.org/keywords/traffic-flow","display_name":"Traffic Flow","score":0.509071}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7949239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.746155},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.6837722},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.63175803},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5531491},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5502234},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46877566},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43644753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41045672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40373722},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1514897},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/case56687.2023.10260400","pdf_url":null,"source":{"id":"https://openalex.org/S4363607892","display_name":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.45,"display_name":"Decent work and economic growth"}],"grants":[{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"62192751"}],"datasets":[],"versions":[],"referenced_works_count":16,"referenced_works":["https://openalex.org/W1516835682","https://openalex.org/W1998622835","https://openalex.org/W2033254849","https://openalex.org/W2078895652","https://openalex.org/W2498017881","https://openalex.org/W2736601468","https://openalex.org/W2809148419","https://openalex.org/W2915117209","https://openalex.org/W2950149761","https://openalex.org/W2954360742","https://openalex.org/W2963027910","https://openalex.org/W2964749398","https://openalex.org/W2988973041","https://openalex.org/W2998187693","https://openalex.org/W3092643721","https://openalex.org/W4286748781"],"related_works":["https://openalex.org/W4399895933","https://openalex.org/W4234629551","https://openalex.org/W4229699405","https://openalex.org/W2366903352","https://openalex.org/W2355491300","https://openalex.org/W2216382288","https://openalex.org/W2161221533","https://openalex.org/W2028856635","https://openalex.org/W2011110943","https://openalex.org/W1666484574"],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1],"learning":[2,33],"(MARL)":[3],"is":[4],"increasingly":[5],"being":[6],"used":[7],"for":[8,118],"traffic":[9,13,20,56,97],"light":[10,21,57],"control":[11,22,54],"in":[12,34,49,94],"networks.":[14],"However,":[15],"applying":[16],"MARL":[17],"to":[18,26,52],"large-scale":[19,55],"faces":[23],"challenges":[24],"due":[25],"the":[27,61,88,108],"time-consuming":[28],"and":[29,71,101],"resource-intensive":[30],"nature":[31],"of":[32,64,91,110],"such":[35],"environments.":[36],"This":[37],"paper":[38],"addresses":[39],"this":[40],"challenge":[41],"by":[42,77],"leveraging":[43],"transfer":[44],"learning,":[45],"utilizing":[46],"policies":[47,92],"trained":[48,65,93],"small-scale":[50,96],"environments":[51],"effectively":[53],"systems.":[58],"To":[59],"enhance":[60],"zero-shot":[62,89,119],"transferability":[63,76,90],"policies,":[66],"we":[67,86],"introduce":[68],"communication":[69],"channels":[70],"sub-task":[72,103,116],"decomposition,":[73],"while":[74],"ensuring":[75],"sharing":[78],"all":[79],"neural":[80],"network":[81],"parameters.":[82],"In":[83],"our":[84],"experiments,":[85],"assess":[87],"different":[95],"networks,":[98],"both":[99],"with":[100],"without":[102],"decomposition.":[104],"The":[105],"results":[106],"demonstrate":[107],"significance":[109],"establishing":[111],"a":[112],"hierarchical":[113],"structure":[114],"through":[115],"decomposition":[117],"transfer.":[120]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4387123596","counts_by_year":[],"updated_date":"2024-12-03T11:52:01.195944","created_date":"2023-09-29"}