{"id":"https://openalex.org/W4385767691","doi":"https://doi.org/10.24963/ijcai.2023/550","title":"InitLight: Initial Model Generation for Traffic Signal Control Using Adversarial Inverse Reinforcement Learning","display_name":"InitLight: Initial Model Generation for Traffic Signal Control Using Adversarial Inverse Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767691","doi":"https://doi.org/10.24963/ijcai.2023/550"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/550","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/550","pdf_url":"https://www.ijcai.org/proceedings/2023/0550.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0550.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102847794","display_name":"Yutong Ye","orcid":"https://orcid.org/0000-0002-6874-5741"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Ye","raw_affiliation_strings":["MoE Eng. Research Center of SW/HW Co-Design Tech. and App., East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Eng. Research Center of SW/HW Co-Design Tech. and App., East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040821130","display_name":"Yingbo Zhou","orcid":"https://orcid.org/0000-0001-6034-9667"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingbo Zhou","raw_affiliation_strings":["MoE Eng. Research Center of SW/HW Co-Design Tech. and App., East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Eng. Research Center of SW/HW Co-Design Tech. and App., East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025619718","display_name":"Jiepin Ding","orcid":"https://orcid.org/0000-0002-3924-5107"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiepin Ding","raw_affiliation_strings":["MoE Eng. Research Center of SW/HW Co-Design Tech. and App., East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Eng. Research Center of SW/HW Co-Design Tech. and App., East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067164243","display_name":"Ting Wang","orcid":"https://orcid.org/0000-0002-7223-8849"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Wang","raw_affiliation_strings":["MoE Eng. Research Center of SW/HW Co-Design Tech. and App., East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Eng. Research Center of SW/HW Co-Design Tech. and App., East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025413633","display_name":"Mingsong Chen","orcid":"https://orcid.org/0000-0002-3922-0989"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingsong Chen","raw_affiliation_strings":["MoE Eng. Research Center of SW/HW Co-Design Tech. and App., East China Normal University","Shanghai Institute of Intelligent Science and Technology, Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Eng. Research Center of SW/HW Co-Design Tech. and App., East China Normal University","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Institute of Intelligent Science and Technology, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026993561","display_name":"Xiang Lian","orcid":"https://orcid.org/0000-0001-7681-3807"},"institutions":[{"id":"https://openalex.org/I149910238","display_name":"Kent State University","ror":"https://ror.org/049pfb863","country_code":"US","type":"education","lineage":["https://openalex.org/I149910238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Lian","raw_affiliation_strings":["Department of Computer Science, Kent State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Kent State University","institution_ids":["https://openalex.org/I149910238"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7209,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8439726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4949","last_page":"4958"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9994999766349792,"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":0.9994999766349792,"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 Prediction and Management Techniques","score":0.998199999332428,"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","score":0.9948999881744385,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8488532304763794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7548723220825195},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.7120139598846436},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5813608765602112},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.513685405254364},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5122967958450317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48846784234046936},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.44499504566192627},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4315764904022217},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.4195348620414734},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3489176630973816},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11226120591163635},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07832863926887512}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8488532304763794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7548723220825195},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.7120139598846436},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5813608765602112},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.513685405254364},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5122967958450317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48846784234046936},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.44499504566192627},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4315764904022217},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4195348620414734},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3489176630973816},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11226120591163635},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07832863926887512},{"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/550","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/550","pdf_url":"https://www.ijcai.org/proceedings/2023/0550.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/550","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/550","pdf_url":"https://www.ijcai.org/proceedings/2023/0550.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3435841993","display_name":null,"funder_award_id":"2217104","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6766199972","display_name":null,"funder_award_id":"62272170","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7611692203","display_name":null,"funder_award_id":"22510750100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767691.pdf"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W5525483","https://openalex.org/W573924038","https://openalex.org/W1191599655","https://openalex.org/W1516835682","https://openalex.org/W1522301498","https://openalex.org/W1591675293","https://openalex.org/W1999874108","https://openalex.org/W2077757159","https://openalex.org/W2098774185","https://openalex.org/W2133068870","https://openalex.org/W2169498096","https://openalex.org/W2177382477","https://openalex.org/W2210077926","https://openalex.org/W2290104316","https://openalex.org/W2566467060","https://openalex.org/W2736601468","https://openalex.org/W2939228328","https://openalex.org/W2945991855","https://openalex.org/W2950149761","https://openalex.org/W2963277051","https://openalex.org/W2985159211","https://openalex.org/W2997412794","https://openalex.org/W2998187693","https://openalex.org/W2998332605","https://openalex.org/W3086530824","https://openalex.org/W3105017587","https://openalex.org/W3163430304","https://openalex.org/W3188474345","https://openalex.org/W3191742182","https://openalex.org/W3211802628","https://openalex.org/W4206335483","https://openalex.org/W4225463478","https://openalex.org/W4283644556","https://openalex.org/W4285601936","https://openalex.org/W4285603540","https://openalex.org/W4303941905","https://openalex.org/W4312332697","https://openalex.org/W4362203700","https://openalex.org/W4393697730","https://openalex.org/W6650265722","https://openalex.org/W6678511256","https://openalex.org/W6685353786","https://openalex.org/W6688475801","https://openalex.org/W6718092244","https://openalex.org/W6755811877","https://openalex.org/W6791858558","https://openalex.org/W6863071542","https://openalex.org/W6863994431","https://openalex.org/W6868564194"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W2387293848","https://openalex.org/W2250140200","https://openalex.org/W3121791438"],"abstract_inverted_index":{"Due":[0],"to":[1,39,137,172],"repetitive":[2],"trial-and-error":[3],"style":[4],"interactions":[5],"between":[6],"agents":[7,38,81],"and":[8,33],"a":[9,50,77,84],"fixed":[10],"traffic":[11,42,132,178],"environment":[12],"during":[13],"the":[14,106,122,149,160],"policy":[15],"learning,":[16],"existing":[17],"Reinforcement":[18,54],"Learning":[19,55],"(RL)-based":[20],"Traffic":[21],"Signal":[22],"Control":[23],"(TSC)":[24],"methods":[25],"greatly":[26],"suffer":[27],"from":[28],"long":[29],"RL":[30,37,142],"training":[31],"time":[32],"poor":[34],"adaptability":[35],"of":[36,80,130,176],"other":[40],"complex":[41,177],"environments.":[43,179],"To":[44],"address":[45],"these":[46],"problems,":[47],"we":[48],"propose":[49],"novel":[51],"Adversarial":[52],"Inverse":[53],"(AIRL)-based":[56],"pre-training":[57],"method":[58],"named":[59],"InitLight,":[60],"which":[61],"enables":[62],"effective":[63],"initial":[64,93,135,150],"model":[65,94,151],"generation":[66],"for":[67,83,117],"TSC":[68,73,115],"agents.":[69],"Unlike":[70],"traditional":[71],"RL-based":[72],"approaches":[74],"that":[75],"train":[76],"large":[78],"number":[79],"simultaneously":[82],"specific":[85],"multi-intersection":[86],"environment,":[87],"InitLight":[88,111,154],"pre-trains":[89],"only":[90,157],"one":[91],"single":[92],"based":[95],"on":[96],"multiple":[97],"single-intersection":[98],"environments":[99,133],"together":[100],"with":[101,162],"their":[102],"expert":[103],"trajectories.":[104],"Since":[105],"reward":[107],"function":[108],"learned":[109],"by":[110,153],"can":[112,125,155],"recover":[113],"ground-truth":[114],"rewards":[116],"different":[118],"intersections":[119,129],"at":[120,128],"optimality,":[121],"pre-trained":[123],"agent":[124],"be":[126],"deployed":[127],"any":[131],"as":[134],"models":[136],"accelerate":[138,159],"subsequent":[139],"overall":[140],"global":[141],"training.":[143],"Comprehensive":[144],"experimental":[145],"results":[146],"show":[147],"that,":[148],"generated":[152],"not":[156],"significantly":[158],"convergence":[161],"much":[163],"fewer":[164],"episodes,":[165],"but":[166],"also":[167],"own":[168],"superior":[169],"generalization":[170],"ability":[171],"accommodate":[173],"various":[174],"kinds":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}