{"id":"https://openalex.org/W4391770058","doi":"https://doi.org/10.1109/itsc57777.2023.10421987","title":"Bridging the Reality Gap of Reinforcement Learning based Traffic Signal Control using Domain Randomization and Meta Learning","display_name":"Bridging the Reality Gap of Reinforcement Learning based Traffic Signal Control using Domain Randomization and Meta Learning","publication_year":2023,"publication_date":"2023-09-24","ids":{"openalex":"https://openalex.org/W4391770058","doi":"https://doi.org/10.1109/itsc57777.2023.10421987"},"language":"en","primary_location":{"id":"doi:10.1109/itsc57777.2023.10421987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc57777.2023.10421987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)","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/A5102487989","display_name":"Arthur M\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111500","display_name":"Fraunhofer Institute of Optronics, System Technologies and Image Exploitation","ror":"https://ror.org/01zx97922","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210111500","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Arthur M\u00fcller","raw_affiliation_strings":["Fraunhofer IOSB-INA,Lemgo,Germany,32657"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IOSB-INA,Lemgo,Germany,32657","institution_ids":["https://openalex.org/I4210111500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074266137","display_name":"Matthia Sabatelli","orcid":"https://orcid.org/0009-0007-7540-8616"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Matthia Sabatelli","raw_affiliation_strings":["University of Groningen,Department of Artificial Intelligence and Cognitive Engineering,Groningen,CP,The Netherlands,9712"],"affiliations":[{"raw_affiliation_string":"University of Groningen,Department of Artificial Intelligence and Cognitive Engineering,Groningen,CP,The Netherlands,9712","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102487989"],"corresponding_institution_ids":["https://openalex.org/I4210111500"],"apc_list":null,"apc_paid":null,"fwci":0.7899,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71332595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5271","last_page":"5278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.8988000154495239,"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"}},"topics":[{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.8988000154495239,"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/T14011","display_name":"Elevator Systems and Control","score":0.7785000205039978,"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/T10320","display_name":"Neural Networks and Applications","score":0.7749999761581421,"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":0.8181228637695312},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.8003138303756714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6585255861282349},{"id":"https://openalex.org/keywords/randomization","display_name":"Randomization","score":0.46958890557289124},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.45946595072746277},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42750081419944763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41432899236679077},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4136834740638733},{"id":"https://openalex.org/keywords/control-signal","display_name":"Control signal","score":0.41104114055633545},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.14535284042358398},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14089331030845642},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12844324111938477},{"id":"https://openalex.org/keywords/randomized-controlled-trial","display_name":"Randomized controlled trial","score":0.0858965516090393}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8181228637695312},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8003138303756714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6585255861282349},{"id":"https://openalex.org/C204243189","wikidata":"https://www.wikidata.org/wiki/Q1363085","display_name":"Randomization","level":3,"score":0.46958890557289124},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.45946595072746277},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42750081419944763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41432899236679077},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4136834740638733},{"id":"https://openalex.org/C3018134525","wikidata":"https://www.wikidata.org/wiki/Q2501541","display_name":"Control signal","level":3,"score":0.41104114055633545},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.14535284042358398},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14089331030845642},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12844324111938477},{"id":"https://openalex.org/C168563851","wikidata":"https://www.wikidata.org/wiki/Q1436668","display_name":"Randomized controlled trial","level":2,"score":0.0858965516090393},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C141071460","wikidata":"https://www.wikidata.org/wiki/Q40821","display_name":"Surgery","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/itsc57777.2023.10421987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc57777.2023.10421987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/462206","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/462206","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W146964248","https://openalex.org/W565101274","https://openalex.org/W1522301498","https://openalex.org/W1965455100","https://openalex.org/W2583080009","https://openalex.org/W2736601468","https://openalex.org/W2767050701","https://openalex.org/W2792609710","https://openalex.org/W2903709398","https://openalex.org/W2960705509","https://openalex.org/W2971017539","https://openalex.org/W2978409868","https://openalex.org/W2990747716","https://openalex.org/W2996355317","https://openalex.org/W2998332605","https://openalex.org/W3037450713","https://openalex.org/W3044015199","https://openalex.org/W3088310808","https://openalex.org/W3090612618","https://openalex.org/W3101442004","https://openalex.org/W3107421563","https://openalex.org/W3120778962","https://openalex.org/W3121342653","https://openalex.org/W3123082711","https://openalex.org/W3160581959","https://openalex.org/W4210562249","https://openalex.org/W4214717370","https://openalex.org/W4220899555","https://openalex.org/W4226372424","https://openalex.org/W4283644556","https://openalex.org/W4298101404","https://openalex.org/W4308080467","https://openalex.org/W4317670814","https://openalex.org/W6631190155","https://openalex.org/W6736057607","https://openalex.org/W6741002519","https://openalex.org/W6748103735","https://openalex.org/W6752963931","https://openalex.org/W6767410255","https://openalex.org/W6769066991","https://openalex.org/W6779874285","https://openalex.org/W6797636097","https://openalex.org/W6839324983","https://openalex.org/W6849169497","https://openalex.org/W7002173608","https://openalex.org/W7028793324"],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W4235186151","https://openalex.org/W2056057048","https://openalex.org/W2054685365","https://openalex.org/W2272354214","https://openalex.org/W2120383820","https://openalex.org/W2043010663","https://openalex.org/W2667588871","https://openalex.org/W4248308508","https://openalex.org/W118554674"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3,18],"been":[4,19],"widely":[5],"explored":[6],"in":[7,21,28,108,177],"Traffic":[8],"Signal":[9],"Control":[10],"(TSC)":[11],"applications,":[12],"however,":[13],"still":[14],"no":[15],"such":[16],"system":[17],"deployed":[20],"practice.":[22],"A":[23],"key":[24],"barrier":[25],"to":[26,67,172],"progress":[27],"this":[29,49,53,68,81,147],"area":[30],"is":[31],"the":[32,35,104,118,124,127,135,151,174],"reality":[33,69,152,175],"gap,":[34],"discrepancy":[36],"that":[37,65,78,112,138,158],"results":[38,156],"from":[39],"differences":[40],"between":[41],"simulation":[42,63,97],"models":[43],"and":[44,86,161],"their":[45,170],"real-world":[46],"equivalents.":[47],"In":[48,102,146],"paper,":[50],"we":[51,122,149],"address":[52],"challenge":[54],"by":[55],"first":[56],"presenting":[57],"a":[58,95,110,131,142,164],"comprehensive":[59],"analysis":[60],"of":[61,99,126,134],"potential":[62,171],"parameters":[64],"contribute":[66],"gap.":[70,153],"We":[71],"then":[72],"also":[73],"examine":[74],"two":[75,128],"promising":[76],"strategies":[77,91],"can":[79],"bridge":[80],"gap:":[82],"Domain":[83],"Randomization":[84],"(DR)":[85],"Model-Agnostic":[87],"Meta-Learning":[88],"(MAML).":[89],"Both":[90],"were":[92],"trained":[93],"with":[94,141],"traffic":[96,144],"model":[98,105,133],"an":[100],"intersection.":[101],"addition,":[103],"was":[106,139],"embedded":[107],"LemgoRL,":[109],"framework":[111],"integrates":[113],"realistic,":[114],"safety-critical":[115],"requirements":[116],"into":[117],"control":[119],"system.":[120],"Subsequently,":[121],"evaluated":[123],"performance":[125],"methods":[129],"on":[130],"separate":[132],"same":[136],"intersection":[137],"developed":[140],"different":[143],"simulator.":[145],"way,":[148],"mimic":[150],"Our":[154],"experimental":[155],"show":[157],"both":[159],"DR":[160],"MAML":[162],"outperform":[163],"state-of-the-art":[165],"RL":[166],"algorithm,":[167],"therefore":[168],"highlighting":[169],"mitigate":[173],"gap":[176],"RL-based":[178],"TSC":[179],"systems.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}