{"id":"https://openalex.org/W3102066660","doi":"https://doi.org/10.1109/icar53236.2021.9659342","title":"Learning to Drive (L2D) as a Low-Cost Benchmark for Real-World Reinforcement Learning","display_name":"Learning to Drive (L2D) as a Low-Cost Benchmark for Real-World Reinforcement Learning","publication_year":2021,"publication_date":"2021-12-06","ids":{"openalex":"https://openalex.org/W3102066660","doi":"https://doi.org/10.1109/icar53236.2021.9659342","mag":"3102066660"},"language":"en","primary_location":{"id":"doi:10.1109/icar53236.2021.9659342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icar53236.2021.9659342","pdf_url":null,"source":{"id":"https://openalex.org/S4363608199","display_name":"2021 20th International Conference on Advanced Robotics (ICAR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 20th International Conference on Advanced Robotics (ICAR)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.00715","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072972295","display_name":"Ari Viitala","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Ari Viitala","raw_affiliation_strings":["Department of Computer Science, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065850081","display_name":"Rinu Boney","orcid":"https://orcid.org/0000-0002-6968-7109"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Rinu Boney","raw_affiliation_strings":["Department of Computer Science, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103063144","display_name":"Yi Zhao","orcid":"https://orcid.org/0000-0002-3555-9408"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yi Zhao","raw_affiliation_strings":["Department of Computer Science, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103933556","display_name":"Alexander Ilin","orcid":"https://orcid.org/0000-0001-6419-3006"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]},{"id":"https://openalex.org/I4210134318","display_name":"University of Technology","ror":"https://ror.org/03gbw6p94","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210134318"]}],"countries":["FI","RU"],"is_corresponding":false,"raw_author_name":"Alexander Ilin","raw_affiliation_strings":["Department of Computer Science, Aalto University, Finland","(Helsinki University of Technology)"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"(Helsinki University of Technology)","institution_ids":["https://openalex.org/I4210134318"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057931031","display_name":"Juho Kannala","orcid":"https://orcid.org/0000-0001-5088-4041"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Juho Kannala","raw_affiliation_strings":["Department of Computer Science, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072972295"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.24523941,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.45435859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9811999797821045,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9775000214576721,"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":0.8121167421340942},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.757075309753418},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7232065796852112},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5948360562324524},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.52601158618927},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5151485204696655},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5009233951568604},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4935680627822876},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4001128673553467},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13812321424484253}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8121167421340942},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.757075309753418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7232065796852112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5948360562324524},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.52601158618927},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5151485204696655},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5009233951568604},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4935680627822876},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4001128673553467},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13812321424484253},{"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icar53236.2021.9659342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icar53236.2021.9659342","pdf_url":null,"source":{"id":"https://openalex.org/S4363608199","display_name":"2021 20th International Conference on Advanced Robotics (ICAR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 20th International Conference on Advanced Robotics (ICAR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.00715","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.00715","pdf_url":"https://arxiv.org/pdf/2008.00715","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3102066660","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2008.00715","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.00715","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.00715","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.00715","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.00715","pdf_url":"https://arxiv.org/pdf/2008.00715","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3102066660.pdf","grobid_xml":"https://content.openalex.org/works/W3102066660.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2172140247","https://openalex.org/W2342662072","https://openalex.org/W2396672775","https://openalex.org/W2557283755","https://openalex.org/W2563830277","https://openalex.org/W2737347195","https://openalex.org/W2747402019","https://openalex.org/W2754517384","https://openalex.org/W2767621168","https://openalex.org/W2781585732","https://openalex.org/W2789525339","https://openalex.org/W2823112946","https://openalex.org/W2889347284","https://openalex.org/W2902125520","https://openalex.org/W2904246096","https://openalex.org/W2907537824","https://openalex.org/W2938421504","https://openalex.org/W2942608247","https://openalex.org/W2951004968","https://openalex.org/W2963796870","https://openalex.org/W2963864421","https://openalex.org/W2964199361","https://openalex.org/W2968095971","https://openalex.org/W2968585391","https://openalex.org/W2968983352","https://openalex.org/W2976223390","https://openalex.org/W2977481643","https://openalex.org/W2981030070","https://openalex.org/W2985533531","https://openalex.org/W2995298643","https://openalex.org/W3007553593","https://openalex.org/W3010884024","https://openalex.org/W3016042418","https://openalex.org/W3020712699","https://openalex.org/W6640963894","https://openalex.org/W6684921986","https://openalex.org/W6704571135","https://openalex.org/W6711869958","https://openalex.org/W6731293529","https://openalex.org/W6741977017","https://openalex.org/W6742945991","https://openalex.org/W6744123322","https://openalex.org/W6745935785","https://openalex.org/W6747387971","https://openalex.org/W6747473740","https://openalex.org/W6748929038","https://openalex.org/W6753060773","https://openalex.org/W6754162236","https://openalex.org/W6756908582","https://openalex.org/W6757380569","https://openalex.org/W6757592117","https://openalex.org/W6765121789","https://openalex.org/W6767997047","https://openalex.org/W6768511085","https://openalex.org/W6770246895","https://openalex.org/W6771179988","https://openalex.org/W6771217966","https://openalex.org/W6774126978","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2578206533","https://openalex.org/W2981194798","https://openalex.org/W3175932586","https://openalex.org/W2964025922","https://openalex.org/W3170914142","https://openalex.org/W3172360140","https://openalex.org/W2953981431","https://openalex.org/W2097797606","https://openalex.org/W3211941939","https://openalex.org/W3153007185","https://openalex.org/W3157321355","https://openalex.org/W2464601489","https://openalex.org/W55500148","https://openalex.org/W3136265295","https://openalex.org/W3172487372","https://openalex.org/W3089385868","https://openalex.org/W1997816436","https://openalex.org/W3206246732","https://openalex.org/W2756826236","https://openalex.org/W2765628092"],"abstract_inverted_index":{"We":[0,65,92,128],"present":[1,66],"Learning":[2],"to":[3,27,29,51,53,76,82,115,140],"Drive":[4],"(L2D),":[5],"a":[6,16,31,89,148],"low-cost":[7],"benchmark":[8],"for":[9],"real-world":[10],"reinforcement":[11],"learning":[12,146],"(RL).":[13],"L2D":[14,104],"involves":[15],"simple":[17],"and":[18,43,67,98,137,147],"reproducible":[19],"experimental":[20],"setup":[21],"where":[22],"an":[23],"RL":[24,80,111,131],"agent":[25,49],"has":[26,50],"learn":[28,52,114,134],"drive":[30,54,116,141],"Donkey":[32,90],"car":[33,118],"around":[34],"three":[35],"miniature":[36],"tracks,":[37],"given":[38],"only":[39],"monocular":[40],"image":[41],"observations":[42],"speed":[44],"of":[45,85,126],"the":[46,63,83,102,117],"car.":[47,91],"The":[48],"from":[55,119,135],"disengagements,":[56],"which":[57,72],"occurs":[58],"when":[59],"it":[60,74],"drives":[61],"off":[62],"track.":[64],"open-source":[68],"our":[69],"training":[70],"pipeline,":[71],"makes":[73],"straightforward":[75],"apply":[77],"any":[78],"existing":[79,110],"algorithm":[81],"task":[84],"autonomous":[86],"driving":[87],"with":[88],"test":[93],"imitation":[94,145],"learning,":[95],"state-of-the-art":[96],"model-free,":[97],"model-based":[99],"algorithms":[100,112,132],"on":[101],"proposed":[103],"benchmark.":[105],"Our":[106],"results":[107],"show":[108],"that":[109,130],"can":[113,133],"scratch":[120],"in":[121],"less":[122],"than":[123,144],"five":[124],"minutes":[125],"interaction.":[127],"demonstrate":[129],"sparse":[136],"noisy":[138],"disengagement":[139],"even":[142],"faster":[143],"human":[149],"operator.":[150]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}