{"id":"https://openalex.org/W7137223674","doi":"https://doi.org/10.1109/itsc60802.2025.11423052","title":"InverseLight: Inverse Dynamics Enabling Policy Transfer with Limited Data for Traffic Signal Control","display_name":"InverseLight: Inverse Dynamics Enabling Policy Transfer with Limited Data for Traffic Signal Control","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W7137223674","doi":"https://doi.org/10.1109/itsc60802.2025.11423052"},"language":null,"primary_location":{"id":"doi:10.1109/itsc60802.2025.11423052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc60802.2025.11423052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100354631","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0002-0883-8233"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"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":"Yang Zhang","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University,Shenzhen,China,518000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University,Shenzhen,China,518000","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086154388","display_name":"Ziyu Bian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"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":"Ziyu Bian","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University,Shenzhen,China,518000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University,Shenzhen,China,518000","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100735687","display_name":"Qiyuan Liu","orcid":"https://orcid.org/0000-0001-5605-3409"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"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":"Qiyuan Liu","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University,Shenzhen,China,518000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University,Shenzhen,China,518000","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129621878","display_name":"Zhiheng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"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":"Zhiheng Li","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University,Shenzhen,China,518000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University,Shenzhen,China,518000","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4697","last_page":"4703"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.39430001378059387,"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":0.39430001378059387,"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/T10138","display_name":"Network Traffic and Congestion Control","score":0.11389999836683273,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.07280000299215317,"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/control","display_name":"Control (management)","score":0.40549999475479126},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.39730000495910645},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.38199999928474426},{"id":"https://openalex.org/keywords/data-transmission","display_name":"Data transmission","score":0.3646000027656555},{"id":"https://openalex.org/keywords/transfer-function","display_name":"Transfer function","score":0.36410000920295715},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.36000001430511475},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.33820000290870667},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.3346000015735626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5888000130653381},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.38199999928474426},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2906000018119812},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2653000056743622},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc60802.2025.11423052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc60802.2025.11423052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2091085232","https://openalex.org/W2605102758","https://openalex.org/W2767050701","https://openalex.org/W2903709398","https://openalex.org/W2960571052","https://openalex.org/W2963184939","https://openalex.org/W2963390419","https://openalex.org/W2968116426","https://openalex.org/W2982095652","https://openalex.org/W3034758105","https://openalex.org/W3088310808","https://openalex.org/W3123082711","https://openalex.org/W3206393052","https://openalex.org/W3206481472","https://openalex.org/W4220899555","https://openalex.org/W4231367092","https://openalex.org/W4400353669"],"related_works":[],"abstract_inverted_index":{"Traffic":[0],"signal":[1],"control":[2],"(TSC)":[3],"plays":[4],"a":[5,33,56,79,91,114],"vital":[6],"role":[7],"in":[8,22],"ensuring":[9],"efficient":[10],"and":[11,41,109],"safe":[12],"transportation.":[13],"While":[14],"reinforcement":[15],"learning":[16],"(RL)":[17],"has":[18],"shown":[19],"promising":[20],"performance":[21,129],"simulators":[23],"for":[24],"TSC,":[25],"transferring":[26],"these":[27],"policies":[28],"to":[29,37,85,95],"real-world":[30,48,68,83],"scenarios":[31],"remains":[32],"major":[34],"challenge":[35],"due":[36],"the":[38,42,87],"dynamics":[39,75],"gap":[40],"high":[43],"cost":[44],"of":[45,82],"collecting":[46],"large-scale":[47],"data.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"propose":[54],"InverseLight,":[55],"two-stage":[57],"policy":[58,94,132],"transfer":[59],"framework":[60],"that":[61,124],"enables":[62],"effective":[63],"sim-to-real":[64],"adaptation":[65],"with":[66,104],"limited":[67],"samples.":[69],"Our":[70],"method":[71],"leverages":[72],"an":[73],"inverse":[74],"model":[76],"trained":[77],"on":[78,119],"small":[80],"amount":[81],"data":[84],"reshape":[86],"reward":[88],"function,":[89],"allowing":[90],"pre-trained":[92],"RL":[93],"adapt":[96],"without":[97],"modifying":[98],"its":[99],"architecture.":[100],"InverseLight":[101],"is":[102],"compatible":[103],"existing":[105],"RL-based":[106],"TSC":[107],"methods":[108],"can":[110],"be":[111],"applied":[112],"as":[113],"plug-and-play":[115],"module.":[116],"Experimental":[117],"results":[118],"multiple":[120],"traffic":[121,135],"datasets":[122],"demonstrate":[123],"our":[125],"approach":[126],"significantly":[127],"reduces":[128],"degradation":[130],"during":[131],"transfer,":[133],"improving":[134],"efficiency":[136],"under":[137],"diverse":[138],"conditions.":[139]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-17T00:00:00"}