{"id":"https://openalex.org/W7151247591","doi":"https://doi.org/10.1109/icmla66185.2025.00159","title":"Offline Reinforcement Learning Benchmark for Variable Speed Limit Control with Real-World Dataset","display_name":"Offline Reinforcement Learning Benchmark for Variable Speed Limit Control with Real-World Dataset","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7151247591","doi":"https://doi.org/10.1109/icmla66185.2025.00159"},"language":null,"primary_location":{"id":"doi:10.1109/icmla66185.2025.00159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","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/A5128894186","display_name":"Yuhang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]},{"id":"https://openalex.org/I4210160740","display_name":"Integrated Software (United States)","ror":"https://ror.org/05dp7m259","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160740"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuhang Zhang","raw_affiliation_strings":["Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212","institution_ids":["https://openalex.org/I4210160740","https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069949235","display_name":"Z. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]},{"id":"https://openalex.org/I4210160740","display_name":"Integrated Software (United States)","ror":"https://ror.org/05dp7m259","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160740"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyao Zhang","raw_affiliation_strings":["Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212","institution_ids":["https://openalex.org/I4210160740","https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128854682","display_name":"Marcos Quinones-Grueiro","orcid":null},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]},{"id":"https://openalex.org/I4210160740","display_name":"Integrated Software (United States)","ror":"https://ror.org/05dp7m259","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160740"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcos Quinones-Grueiro","raw_affiliation_strings":["Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212","institution_ids":["https://openalex.org/I4210160740","https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059421106","display_name":"William Barbour","orcid":"https://orcid.org/0000-0002-1368-3192"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]},{"id":"https://openalex.org/I4210160740","display_name":"Integrated Software (United States)","ror":"https://ror.org/05dp7m259","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160740"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Barbour","raw_affiliation_strings":["Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212","institution_ids":["https://openalex.org/I4210160740","https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051150754","display_name":"Gautam Biswas","orcid":"https://orcid.org/0000-0002-2752-3878"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]},{"id":"https://openalex.org/I4210160740","display_name":"Integrated Software (United States)","ror":"https://ror.org/05dp7m259","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160740"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautam Biswas","raw_affiliation_strings":["Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212","institution_ids":["https://openalex.org/I4210160740","https://openalex.org/I200719446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124520091","display_name":"Daniel B. Work","orcid":null},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]},{"id":"https://openalex.org/I4210160740","display_name":"Integrated Software (United States)","ror":"https://ror.org/05dp7m259","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160740"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Work","raw_affiliation_strings":["Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Institute for Software Integrated Systems,Nashville,TN,USA,37212","institution_ids":["https://openalex.org/I4210160740","https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5128894186"],"corresponding_institution_ids":["https://openalex.org/I200719446","https://openalex.org/I4210160740"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78473516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1046","last_page":"1051"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.5156000256538391,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.5156000256538391,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.13210000097751617,"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"}},{"id":"https://openalex.org/T10805","display_name":"Vehicle Dynamics and Control Systems","score":0.030700000002980232,"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":0.5734999775886536},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5497000217437744},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4837999939918518},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.44830000400543213},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4081999957561493},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.31349998712539673},{"id":"https://openalex.org/keywords/control-limits","display_name":"Control limits","score":0.30149999260902405},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2840000092983246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5979999899864197},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5734999775886536},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5497000217437744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48539999127388},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4837999939918518},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4081999957561493},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3644999861717224},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C166623804","wikidata":"https://www.wikidata.org/wiki/Q5165860","display_name":"Control limits","level":4,"score":0.30149999260902405},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25839999318122864},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmla66185.2025.00159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306108","display_name":"U.S. Department of Transportation","ror":"https://ror.org/02xfw2e90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1857301280","https://openalex.org/W3042354433","https://openalex.org/W4360764815","https://openalex.org/W4392943461","https://openalex.org/W4393968337","https://openalex.org/W4403936869","https://openalex.org/W4413468859","https://openalex.org/W7133210602"],"related_works":[],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,5],"(RL)":[3],"enables":[4],"decision-making":[6],"policies":[7],"directly":[8],"from":[9,61,71],"historical":[10],"data,":[11,33],"which":[12,34],"is":[13],"advantageous":[14],"for":[15,54,121],"safety-critical":[16],"domains":[17],"like":[18],"traffic":[19,102],"control.":[20],"However,":[21],"existing":[22],"offline":[23,51,86,119],"RL":[24,52,87,120],"benchmarks":[25],"in":[26],"transportation":[27,123],"systems":[28],"typically":[29],"rely":[30],"on":[31,78],"simulated":[32],"may":[35],"not":[36],"fully":[37],"capture":[38],"the":[39,49,114],"complexities":[40],"of":[41,66,118],"real-world":[42,67],"environments.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,105],"introduce":[48],"first":[50],"benchmark":[53,128],"variable":[55],"speed":[56],"limit":[57],"(VSL)":[58],"control,":[59],"built":[60],"approximately":[62],"100":[63],"million":[64],"transitions":[65],"interaction":[68],"data":[69],"collected":[70],"a":[72,79],"field-deployed,":[73],"multi-agent":[74],"RL-based":[75],"VSL":[76],"system":[77],"major":[80],"freeway.":[81],"We":[82],"evaluate":[83],"five":[84],"state-of-the-art":[85],"algorithms":[88],"under":[89],"multiple":[90],"dataset":[91,126],"conditions":[92],"defined":[93],"by":[94],"varying":[95],"sizes":[96],"and":[97,109,116,127],"action":[98],"noise":[99],"levels.":[100],"Through":[101],"microsimulation":[103],"experiments,":[104],"analyze":[106],"algorithm":[107],"performance":[108],"generalization,":[110],"providing":[111],"insights":[112],"into":[113],"challenges":[115],"opportunities":[117],"intelligent":[122],"systems.":[124],"The":[125],"are":[129],"released":[130],"at":[131],"https://github.com/Lab-Work/i24-vsl-orl.":[132]},"counts_by_year":[],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2026-04-08T00:00:00"}