{"id":"https://openalex.org/W4386415048","doi":"https://doi.org/10.1016/j.mlwa.2023.100496","title":"Comparing deep reinforcement learning architectures for autonomous racing","display_name":"Comparing deep reinforcement learning architectures for autonomous racing","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4386415048","doi":"https://doi.org/10.1016/j.mlwa.2023.100496"},"language":"en","primary_location":{"id":"doi:10.1016/j.mlwa.2023.100496","doi":"https://doi.org/10.1016/j.mlwa.2023.100496","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.mlwa.2023.100496","pdf_url":null,"source":{"id":"https://openalex.org/S4210201048","display_name":"Machine Learning with Applications","issn_l":"2666-8270","issn":["2666-8270"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","jufo-1","norway-1","oarl","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning with Applications","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.mlwa.2023.100496","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076940088","display_name":"Benjamin Evans","orcid":"https://orcid.org/0000-0001-6312-1203","observed_orcids":["https://orcid.org/0000-0001-6312-1203"]},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Benjamin David Evans","raw_affiliation_strings":["Stellenbosch University, Electrical and Electronic Engineering, Banghoek Road, Stellenbosch, South Africa"],"raw_orcid":"https://orcid.org/0000-0001-6312-1203","affiliations":[{"raw_affiliation_string":"Stellenbosch University, Electrical and Electronic Engineering, Banghoek Road, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065610954","display_name":"Hendrik Willem Jordaan","orcid":"https://orcid.org/0000-0002-6466-6456","observed_orcids":["https://orcid.org/0000-0002-6466-6456"]},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Hendrik Willem Jordaan","raw_affiliation_strings":["Stellenbosch University, Electrical and Electronic Engineering, Banghoek Road, Stellenbosch, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch University, Electrical and Electronic Engineering, Banghoek Road, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091413322","display_name":"Herman A. Engelbrecht","orcid":"https://orcid.org/0000-0001-8753-8994","observed_orcids":["https://orcid.org/0000-0001-8753-8994"]},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Herman Arnold Engelbrecht","raw_affiliation_strings":["Stellenbosch University, Electrical and Electronic Engineering, Banghoek Road, Stellenbosch, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch University, Electrical and Electronic Engineering, Banghoek Road, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5076940088"],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":{"value":2200,"currency":"USD","value_usd":2200},"apc_paid":{"value":2200,"currency":"USD","value_usd":2200},"fwci":1.2622,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.803753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"14","issue":null,"first_page":"100496","last_page":"100496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9940999746322632,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9940999746322632,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.005799999926239252,"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"}},{"id":"https://openalex.org/T10805","display_name":"Vehicle Dynamics and Control Systems","score":0.0,"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/autonomous-racing","display_name":"autonomous racing","score":0.9850000143051147},{"id":"https://openalex.org/keywords/f1tenth","display_name":"F1TENTH","score":0.9259999990463257},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8980000019073486},{"id":"https://openalex.org/keywords/end-to-end-learning","display_name":"end-to-end learning","score":0.6610000133514404},{"id":"https://openalex.org/keywords/trajectory-tracking","display_name":"trajectory tracking","score":0.800000011920929},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.47200000286102295},{"id":"https://openalex.org/keywords/ddpg","display_name":"deep deterministic policy gradient","score":0.8360000252723694},{"id":"https://openalex.org/keywords/twin-delayed-deep-deterministic-policy-gradient","display_name":"TD3","score":0.9990000128746033},{"id":"https://openalex.org/keywords/soft-actor-critic","display_name":"soft actor-critic","score":0.8610000014305115},{"id":"https://openalex.org/keywords/policy-transfer","display_name":"policy transfer","score":0.5299999713897705},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.7250000238418579},{"id":"https://openalex.org/keywords/vehicle-control","display_name":"vehicle control","score":0.4359999895095825}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7498807907104492},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.7002061605453491},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6878734827041626},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6451602578163147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6380969285964966},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.5355892181396484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.512885570526123},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4777073860168457},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.474069744348526},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.43627607822418213},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.4333561062812805},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4299624562263489},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.42235153913497925},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.mlwa.2023.100496","doi":"https://doi.org/10.1016/j.mlwa.2023.100496","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.mlwa.2023.100496","pdf_url":null,"source":{"id":"https://openalex.org/S4210201048","display_name":"Machine Learning with Applications","issn_l":"2666-8270","issn":["2666-8270"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","jufo-1","norway-1","oarl","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning with Applications","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:652589d4a3b14b9d85c89692c8d7253e","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/652589d4a3b14b9d85c89692c8d7253e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning with Applications, Vol 14, Iss , Pp 100496- (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.mlwa.2023.100496","doi":"https://doi.org/10.1016/j.mlwa.2023.100496","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.mlwa.2023.100496","pdf_url":null,"source":{"id":"https://openalex.org/S4210201048","display_name":"Machine Learning with Applications","issn_l":"2666-8270","issn":["2666-8270"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","jufo-1","norway-1","oarl","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning with Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1566405224","https://openalex.org/W2173248099","https://openalex.org/W2787938642","https://openalex.org/W2869375357","https://openalex.org/W2904246096","https://openalex.org/W2904338767","https://openalex.org/W2951357333","https://openalex.org/W2981194798","https://openalex.org/W2994755084","https://openalex.org/W2999762404","https://openalex.org/W3021958118","https://openalex.org/W3068678661","https://openalex.org/W3091512219","https://openalex.org/W3110592977","https://openalex.org/W3155633396","https://openalex.org/W3188004887","https://openalex.org/W3188960348","https://openalex.org/W3193488849","https://openalex.org/W3202635380","https://openalex.org/W4210870706","https://openalex.org/W4221141864","https://openalex.org/W4225642194","https://openalex.org/W4226209822","https://openalex.org/W4281757468","https://openalex.org/W4285102517","https://openalex.org/W4313886669","https://openalex.org/W4366502868","https://openalex.org/W4383109279","https://openalex.org/W4385539610","https://openalex.org/W4404411088","https://openalex.org/W6737060285","https://openalex.org/W7047190309"],"related_works":["https://openalex.org/W3023371578","https://openalex.org/W3036383710","https://openalex.org/W4412445237","https://openalex.org/W3158766211","https://openalex.org/W3068678661","https://openalex.org/W3188004887","https://openalex.org/W4413393756","https://openalex.org/W4385539610","https://openalex.org/W4211094662","https://openalex.org/W4281757468"],"abstract_inverted_index":{"In":[0,22,162],"classical":[1],"autonomous":[2,48],"racing,":[3],"a":[4,16,142,186],"perception,":[5],"planning,":[6,51],"and":[7,56,66,83,86,114,151,179],"control":[8],"pipeline":[9],"is":[10],"employed":[11],"to":[12,30,94,141,175,209],"navigate":[13],"vehicles":[14],"around":[15],"track":[17,184],"as":[18,20],"quickly":[19],"possible.":[21],"contrast,":[23,163],"neural":[24],"network":[25],"controllers":[26],"have":[27],"been":[28],"used":[29],"replace":[31],"either":[32],"part":[33],"of":[34,90,189],"or":[35],"the":[36,54,63,70,80,88,91,99,105,110,126,138,148,164,167,173,176,182],"entire":[37,71],"pipeline.":[38,72],"This":[39],"paper":[40],"compares":[41,79],"three":[42],"deep":[43],"learning":[44],"architectures":[45],"for":[46],"F1Tenth":[47,144],"racing:":[49],"full":[50,106,152],"which":[52,61,68],"replaces":[53,62,69],"global":[55],"local":[57,64],"planner,":[58],"trajectory":[59,118,149],"tracking,":[60],"planner":[65],"end-to-end,":[67],"The":[73,117],"evaluation":[74],"contrasts":[75],"two":[76],"reward":[77],"signals,":[78],"DDPG,":[81],"TD3":[82],"SAC":[84],"algorithms":[85],"investigates":[87],"generality":[89],"learned":[92],"policies":[93],"different":[95,134],"test":[96,135,183],"maps.":[97,136],"Training":[98],"agents":[100,120,140,154],"in":[101,170,201],"simulation":[102,202],"shows":[103],"that":[104,147,195],"planning":[107,153,196],"agent":[108],"has":[109],"most":[111],"robust":[112],"training":[113,127],"testing":[115],"performance.":[116],"tracking":[119,150],"achieve":[121],"fast":[122],"lap":[123],"times":[124],"on":[125,133],"map":[128],"but":[129,204],"low":[130],"completion":[131],"rates":[132],"Transferring":[137],"trained":[139],"physical":[143,177,210],"car":[145],"reveals":[146],"transfer":[155,207],"poorly,":[156],"displaying":[157],"rapid":[158],"side-to-side":[159],"swerving":[160],"(slaloming).":[161],"end-to-end":[165,199,205],"agent,":[166],"worst":[168],"performer":[169],"simulation,":[171],"transfers":[172],"best":[174],"vehicle":[178],"can":[180],"complete":[181],"with":[185],"maximum":[187],"speed":[188],"5":[190],"m/s.":[191],"These":[192],"results":[193],"show":[194],"methods":[197],"outperform":[198],"approaches":[200,206],"performance,":[203],"better":[208],"robots.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":4}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-09-05T00:00:00"}