{"id":"https://openalex.org/W4401871030","doi":"https://doi.org/10.1109/mits.2024.3440069","title":"Boosting the Training of Deep Reinforcement Learning Traffic Control by Using the World Model","display_name":"Boosting the Training of Deep Reinforcement Learning Traffic Control by Using the World Model","publication_year":2024,"publication_date":"2024-08-20","ids":{"openalex":"https://openalex.org/W4401871030","doi":"https://doi.org/10.1109/mits.2024.3440069"},"language":"en","primary_location":{"id":"doi:10.1109/mits.2024.3440069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mits.2024.3440069","pdf_url":null,"source":{"id":"https://openalex.org/S131000621","display_name":"IEEE Intelligent Transportation Systems Magazine","issn_l":"1939-1390","issn":["1939-1390","1941-1197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Intelligent Transportation Systems Magazine","raw_type":"journal-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/A5045147031","display_name":"Pengbo Wang","orcid":"https://orcid.org/0000-0002-8453-3992"},"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":true,"raw_author_name":"Pengbo Wang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076992681","display_name":"Yisheng Lv","orcid":"https://orcid.org/0000-0002-7565-4979"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yisheng Lv","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020672096","display_name":"Jingwei Ge","orcid":"https://orcid.org/0000-0003-2309-9739"},"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":"Jingwei Ge","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114911316","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-9428-1960"},"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":"Li Li","raw_affiliation_strings":["Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045147031"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.6975,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70291846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"17","issue":"3","first_page":"58","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.47749999165534973,"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/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.47749999165534973,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.8436655402183533},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7909965515136719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5958662629127502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5743535161018372},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5192022919654846},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44785481691360474},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4243299961090088},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08041095733642578}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8436655402183533},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7909965515136719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5958662629127502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5743535161018372},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5192022919654846},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44785481691360474},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4243299961090088},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08041095733642578},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mits.2024.3440069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mits.2024.3440069","pdf_url":null,"source":{"id":"https://openalex.org/S131000621","display_name":"IEEE Intelligent Transportation Systems Magazine","issn_l":"1939-1390","issn":["1939-1390","1941-1197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Intelligent Transportation Systems Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2048041430","https://openalex.org/W2088956500","https://openalex.org/W2145339207","https://openalex.org/W2150355110","https://openalex.org/W2533328922","https://openalex.org/W2566768148","https://openalex.org/W2622164924","https://openalex.org/W2809148419","https://openalex.org/W2915117209","https://openalex.org/W2928629935","https://openalex.org/W2964749398","https://openalex.org/W2967474307","https://openalex.org/W2983178256","https://openalex.org/W2990747716","https://openalex.org/W3014350512","https://openalex.org/W3021113705","https://openalex.org/W3096739060","https://openalex.org/W3212930182","https://openalex.org/W4213230486","https://openalex.org/W4226397656","https://openalex.org/W4242049578","https://openalex.org/W4313036208","https://openalex.org/W4382371725","https://openalex.org/W6639086533","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6754184789","https://openalex.org/W6771514159","https://openalex.org/W6783867858","https://openalex.org/W6849730293"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W3082059448","https://openalex.org/W4313640622"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"(DRL)":[3],"traffic":[4,66,75,81,114],"control":[5,82,92,115,125],"attracts":[6],"increasing":[7],"interest":[8],"since":[9],"it":[10],"is":[11],"widely":[12],"viewed":[13],"as":[14],"a":[15,32,56,121,128],"powerful":[16],"tool":[17],"for":[18,59,65],"alleviating":[19],"congestion":[20],"that":[21,38,112],"significantly":[22],"impacts":[23],"people\u2019s":[24],"daily":[25],"lives.":[26],"However,":[27],"traditional":[28],"DRL":[29,63,91,113],"models":[30,64,118],"require":[31],"substantial":[33],"amount":[34],"of":[35,62,80],"interactive":[36],"data":[37,102],"are":[39],"difficult":[40],"to":[41,131],"collect":[42],"in":[43],"both":[44],"field":[45,86],"and":[46,77,87],"simulation":[47,88],"tests.":[48],"To":[49],"overcome":[50],"these":[51],"challenges,":[52],"this":[53],"article":[54],"adopts":[55],"world":[57,70,106,117],"model":[58,71,93,107],"better":[60,123],"training":[61,101],"control.":[67],"The":[68,90],"proposed":[69],"can":[72,94,119],"quickly":[73],"learn":[74],"dynamics":[76],"the":[78,100,105],"influence":[79],"based":[83,98],"on":[84,99],"limited":[85],"data.":[89],"then":[95],"be":[96],"established":[97],"generated":[103],"by":[104],"instead.":[108],"Experimental":[109],"results":[110],"demonstrate":[111],"using":[116],"achieve":[120],"noticeably":[122],"signal":[124],"strategy,":[126],"providing":[127],"promising":[129],"solution":[130],"optimize":[132],"urban":[133],"traffic.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}