{"id":"https://openalex.org/W2742454413","doi":"https://doi.org/10.1109/tsmc.2017.2712561","title":"Parameterized Batch Reinforcement Learning for Longitudinal Control of Autonomous Land Vehicles","display_name":"Parameterized Batch Reinforcement Learning for Longitudinal Control of Autonomous Land Vehicles","publication_year":2017,"publication_date":"2017-08-04","ids":{"openalex":"https://openalex.org/W2742454413","doi":"https://doi.org/10.1109/tsmc.2017.2712561","mag":"2742454413"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2017.2712561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2017.2712561","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digitalcommons.uri.edu/ele_facpubs/360","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103082016","display_name":"Zhenhua Huang","orcid":"https://orcid.org/0000-0003-3178-9721"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Huang","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-3238-745X","affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112861803","display_name":"Haibo He","orcid":null},"institutions":[{"id":"https://openalex.org/I17626003","display_name":"University of Rhode Island","ror":"https://ror.org/013ckk937","country_code":"US","type":"education","lineage":["https://openalex.org/I17626003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haibo He","raw_affiliation_strings":["Department of Electrical, Computer, and Biomedical Engineering, University of Rhode Island, Kingston, RI, USA"],"raw_orcid":"https://orcid.org/0000-0002-3103-4452","affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer, and Biomedical Engineering, University of Rhode Island, Kingston, RI, USA","institution_ids":["https://openalex.org/I17626003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101714477","display_name":"Jun Tan","orcid":"https://orcid.org/0000-0001-9317-1949"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Tan","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044447816","display_name":"Zhenping Sun","orcid":"https://orcid.org/0009-0009-1491-5280"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenping Sun","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.5276,"has_fulltext":false,"cited_by_count":105,"citation_normalized_percentile":{"value":0.98765191,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"49","issue":"4","first_page":"730","last_page":"741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9904999732971191,"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9488999843597412,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8605782985687256},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.7650954723358154},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.631810188293457},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.5996069312095642},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5937562584877014},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5910071730613708},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.49124830961227417},{"id":"https://openalex.org/keywords/brake","display_name":"Brake","score":0.4785248041152954},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4551238715648651},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4542447030544281},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4459701478481293},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.43342962861061096},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4276863932609558},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4151616394519806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3747346103191376},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25236767530441284},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.2468664050102234},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2269848883152008},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11445999145507812}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8605782985687256},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.7650954723358154},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.631810188293457},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.5996069312095642},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5937562584877014},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5910071730613708},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.49124830961227417},{"id":"https://openalex.org/C2780999251","wikidata":"https://www.wikidata.org/wiki/Q17022503","display_name":"Brake","level":2,"score":0.4785248041152954},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4551238715648651},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4542447030544281},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4459701478481293},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.43342962861061096},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4276863932609558},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4151616394519806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3747346103191376},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25236767530441284},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2468664050102234},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2269848883152008},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11445999145507812},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tsmc.2017.2712561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2017.2712561","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"},{"id":"pmh:oai:digitalcommons.uri.edu:ele_facpubs-1359","is_oa":true,"landing_page_url":"https://digitalcommons.uri.edu/ele_facpubs/360","pdf_url":null,"source":{"id":"https://openalex.org/S2764761010","display_name":"Journal of Media Literacy Education","issn_l":"2167-8715","issn":["2167-8715"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310316378","host_organization_name":"National Association for Media Literacy Education","host_organization_lineage":["https://openalex.org/P4310316378"],"host_organization_lineage_names":["National Association for Media Literacy Education"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical, Computer, and Biomedical Engineering Faculty Publications","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:digitalcommons.uri.edu:ele_facpubs-1359","is_oa":true,"landing_page_url":"https://digitalcommons.uri.edu/ele_facpubs/360","pdf_url":null,"source":{"id":"https://openalex.org/S2764761010","display_name":"Journal of Media Literacy Education","issn_l":"2167-8715","issn":["2167-8715"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310316378","host_organization_name":"National Association for Media Literacy Education","host_organization_lineage":["https://openalex.org/P4310316378"],"host_organization_lineage_names":["National Association for Media Literacy Education"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical, Computer, and Biomedical Engineering Faculty Publications","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5320757814","display_name":null,"funder_award_id":"U1564214","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8136749885","display_name":null,"funder_award_id":"61611540348","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W31956758","https://openalex.org/W560518094","https://openalex.org/W755046805","https://openalex.org/W1556619787","https://openalex.org/W1576992604","https://openalex.org/W1601081659","https://openalex.org/W1626155273","https://openalex.org/W1639525857","https://openalex.org/W1949804828","https://openalex.org/W1970127232","https://openalex.org/W1974883306","https://openalex.org/W1979317847","https://openalex.org/W1997880753","https://openalex.org/W2014729048","https://openalex.org/W2023465281","https://openalex.org/W2027260803","https://openalex.org/W2044330174","https://openalex.org/W2048687352","https://openalex.org/W2089684487","https://openalex.org/W2089904313","https://openalex.org/W2100276679","https://openalex.org/W2101786389","https://openalex.org/W2104641222","https://openalex.org/W2105003586","https://openalex.org/W2113921460","https://openalex.org/W2118556122","https://openalex.org/W2121703796","https://openalex.org/W2121863487","https://openalex.org/W2129660761","https://openalex.org/W2134569556","https://openalex.org/W2137092694","https://openalex.org/W2143124112","https://openalex.org/W2145952809","https://openalex.org/W2152161277","https://openalex.org/W2159998281","https://openalex.org/W2165726932","https://openalex.org/W2188644438","https://openalex.org/W2291041537","https://openalex.org/W2338719424","https://openalex.org/W2343765514","https://openalex.org/W2388591084","https://openalex.org/W2487144912","https://openalex.org/W2489526136","https://openalex.org/W2505763307","https://openalex.org/W2618716815","https://openalex.org/W4214717370","https://openalex.org/W4252227510","https://openalex.org/W6615691484","https://openalex.org/W6636924512","https://openalex.org/W6640712829","https://openalex.org/W6677984395","https://openalex.org/W6681140767","https://openalex.org/W6738384783"],"related_works":["https://openalex.org/W4308702637","https://openalex.org/W2149418961","https://openalex.org/W4256087190","https://openalex.org/W4240668504","https://openalex.org/W2100100236","https://openalex.org/W3038962357","https://openalex.org/W2971484784","https://openalex.org/W4288112126","https://openalex.org/W61119710","https://openalex.org/W2011233848"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,78,113,159],"parameterized":[4,26,48],"batch":[5,49,96],"reinforcement":[6],"learning":[7,56,86,93,111],"algorithm":[8,52],"for":[9,37,81,101,120],"near-optimal":[10,124],"longitudinal":[11,115,185],"control":[12,116,125,132,186,192],"of":[13,84,178],"autonomous":[14],"land":[15],"vehicles":[16],"(ALVs).":[17],"The":[18,172],"proposed":[19],"approach":[20],"uses":[21],"an":[22],"actor-critic":[23,50,55,85],"architecture,":[24],"where":[25],"feature":[27],"vectors":[28],"based":[29],"on":[30,108,158,165],"kernels":[31],"are":[32,99,152],"learned":[33],"from":[34],"collected":[35],"samples":[36],"approximating":[38],"the":[39,47,60,67,82,102,109,130,176,179],"value":[40],"functions":[41],"and":[42,53,62,104,149,169,193],"policies.":[43],"One":[44],"difference":[45],"between":[46],"(PBAC)":[51],"previous":[54],"approaches":[57],"is":[58,118,142],"that":[59,145],"critic":[61,103],"actor":[63],"in":[64],"PBAC":[65,110],"share":[66],"same":[68],"linear":[69],"features,":[70],"which":[71,127],"has":[72],"been":[73],"theoretically":[74],"proved":[75],"to":[76,90,122,134],"be":[77],"beneficial":[79],"property":[80],"convergence":[83],"approaches.":[87],"In":[88],"order":[89],"obtain":[91,123],"better":[92],"efficiency,":[94],"least-squares-based":[95],"updating":[97],"rules":[98],"designed":[100,143],"actor,":[105],"respectively.":[106],"Based":[107],"algorithm,":[112],"data-driven":[114],"method":[117],"presented":[119],"ALVs":[121],"policies":[126],"adaptively":[128],"tune":[129],"fuel/brake":[131],"signals":[133],"track":[135],"different":[136],"speeds.":[137],"A":[138],"multiobjective":[139],"reward":[140],"function":[141],"so":[144],"both":[146],"tracking":[147],"precision":[148],"driving":[150,164],"smoothness":[151],"considered.":[153],"Extensive":[154],"experiments":[155],"were":[156],"conducted":[157],"real":[160],"ALV":[161],"platform":[162],"while":[163],"flat,":[166],"slippery,":[167],"sloping,":[168],"bumpy":[170],"roads.":[171],"experimental":[173],"results":[174],"illustrate":[175],"superiority":[177],"PBAC-based":[180],"self-learning":[181],"controller":[182],"over":[183],"conventional":[184],"methods":[187],"such":[188],"as":[189],"proportional-integral":[190],"(PI)":[191],"learning-based":[194],"PI":[195],"control.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}