{"id":"https://openalex.org/W3163612587","doi":"https://doi.org/10.1109/kst51265.2021.9415770","title":"Learning to Drive with Deep Reinforcement Learning","display_name":"Learning to Drive with Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-01-21","ids":{"openalex":"https://openalex.org/W3163612587","doi":"https://doi.org/10.1109/kst51265.2021.9415770","mag":"3163612587"},"language":"en","primary_location":{"id":"doi:10.1109/kst51265.2021.9415770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kst51265.2021.9415770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 13th International Conference on Knowledge and Smart Technology (KST)","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/A5020643479","display_name":"Nut Chukamphaeng","orcid":null},"institutions":[{"id":"https://openalex.org/I91538806","display_name":"King Mongkut's Institute of Technology Ladkrabang","ror":"https://ror.org/055mf0v62","country_code":"TH","type":"education","lineage":["https://openalex.org/I91538806"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Nut Chukamphaeng","raw_affiliation_strings":["Faculty of Information Technology, King Mongkut's Institute of Technology Ladkrabang, Bangkok, Thailand"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, King Mongkut's Institute of Technology Ladkrabang, Bangkok, Thailand","institution_ids":["https://openalex.org/I91538806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066462028","display_name":"Kitsuchart Pasupa","orcid":"https://orcid.org/0000-0001-8359-9888"},"institutions":[{"id":"https://openalex.org/I91538806","display_name":"King Mongkut's Institute of Technology Ladkrabang","ror":"https://ror.org/055mf0v62","country_code":"TH","type":"education","lineage":["https://openalex.org/I91538806"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Kitsuchart Pasupa","raw_affiliation_strings":["Faculty of Information Technology, King Mongkut's Institute of Technology Ladkrabang, Bangkok, Thailand"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, King Mongkut's Institute of Technology Ladkrabang, Bangkok, Thailand","institution_ids":["https://openalex.org/I91538806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033328915","display_name":"Martin Antenreiter","orcid":null},"institutions":[{"id":"https://openalex.org/I182712176","display_name":"Montanuniversit\u00e4t Leoben","ror":"https://ror.org/02fhfw393","country_code":"AT","type":"education","lineage":["https://openalex.org/I182712176"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Martin Antenreiter","raw_affiliation_strings":["Montanuniversit\u00e4t Leoben, Leoben, Austria"],"affiliations":[{"raw_affiliation_string":"Montanuniversit\u00e4t Leoben, Leoben, Austria","institution_ids":["https://openalex.org/I182712176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073954294","display_name":"Peter Auer","orcid":"https://orcid.org/0000-0001-8385-9635"},"institutions":[{"id":"https://openalex.org/I182712176","display_name":"Montanuniversit\u00e4t Leoben","ror":"https://ror.org/02fhfw393","country_code":"AT","type":"education","lineage":["https://openalex.org/I182712176"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Peter Auer","raw_affiliation_strings":["Montanuniversit\u00e4t Leoben, Leoben, Austria"],"affiliations":[{"raw_affiliation_string":"Montanuniversit\u00e4t Leoben, Leoben, Austria","institution_ids":["https://openalex.org/I182712176"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020643479"],"corresponding_institution_ids":["https://openalex.org/I91538806"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61499196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"147","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9923999905586243,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9807999730110168,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.924056887626648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7277522087097168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6638932824134827},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6152474880218506},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.523680567741394},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.472345232963562},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43736135959625244},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.42767471075057983},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.412770539522171},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31622201204299927},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19397181272506714}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.924056887626648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7277522087097168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6638932824134827},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6152474880218506},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.523680567741394},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.472345232963562},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43736135959625244},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.42767471075057983},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.412770539522171},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31622201204299927},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19397181272506714},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":1,"locations":[{"id":"doi:10.1109/kst51265.2021.9415770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kst51265.2021.9415770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 13th International Conference on Knowledge and Smart Technology (KST)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1977992720","https://openalex.org/W1980714852","https://openalex.org/W1983360738","https://openalex.org/W1990609757","https://openalex.org/W2021063678","https://openalex.org/W2040084091","https://openalex.org/W2040661524","https://openalex.org/W2065554167","https://openalex.org/W2112036188","https://openalex.org/W2112796928","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2164637474","https://openalex.org/W2165150801","https://openalex.org/W2257979135","https://openalex.org/W2334782222","https://openalex.org/W2342840547","https://openalex.org/W2553303224","https://openalex.org/W2562337727","https://openalex.org/W2583993537","https://openalex.org/W2605103573","https://openalex.org/W2618530766","https://openalex.org/W2679375846","https://openalex.org/W2740273350","https://openalex.org/W2757226121","https://openalex.org/W2773706593","https://openalex.org/W2786036274","https://openalex.org/W2787938642","https://openalex.org/W2788125442","https://openalex.org/W2908019077","https://openalex.org/W2909676666","https://openalex.org/W2928157547","https://openalex.org/W2963536136","https://openalex.org/W2963881378","https://openalex.org/W2971510799","https://openalex.org/W3003533476","https://openalex.org/W3008897963","https://openalex.org/W3019845454","https://openalex.org/W3047375952","https://openalex.org/W3094191450","https://openalex.org/W3098920376","https://openalex.org/W3100944043","https://openalex.org/W3103752844","https://openalex.org/W3105140685","https://openalex.org/W4285719527","https://openalex.org/W4297797010","https://openalex.org/W4302570325","https://openalex.org/W6684205842","https://openalex.org/W6684470913","https://openalex.org/W6741559791","https://openalex.org/W6758126674"],"related_works":["https://openalex.org/W1966456942","https://openalex.org/W2754028433","https://openalex.org/W3148138296","https://openalex.org/W1882507001","https://openalex.org/W2367922714","https://openalex.org/W1986508893","https://openalex.org/W2352650970","https://openalex.org/W2534140487","https://openalex.org/W4383501708","https://openalex.org/W2130711276"],"abstract_inverted_index":{"Autonomous":[0],"driving":[1],"cars":[2],"are":[3],"important":[4],"due":[5],"to":[6,17,102,115,127],"improved":[7],"safety":[8],"and":[9,27,82,132,141],"fuel":[10],"efficiency.":[11],"Various":[12],"techniques":[13],"have":[14],"been":[15],"described":[16],"consider":[18],"only":[19,96,137],"a":[20,58,97,110],"single":[21,98],"task,":[22],"for":[23,48,90,123,154],"example,":[24],"recognition,":[25],"prediction,":[26],"planning":[28],"with":[29,57,136,149],"supervised":[30],"learning":[31,72,89,100,153],"techniques.":[32],"Some":[33],"limitations":[34],"of":[35,79],"previous":[36],"studies":[37],"are:":[38],"(1)":[39],"human":[40,43],"bias":[41],"from":[42],"demonstration;":[44],"(2)":[45],"the":[46,66,71,77,104,117,128,134,138],"need":[47],"multiple":[49],"components":[50],"such":[51],"as":[52],"localization,":[53],"road":[54],"mapping":[55],"etc.":[56],"complicated":[59],"fusion":[60],"logic;":[61],"(3)":[62],"in":[63],"reinforcement":[64,88,99,152],"learning,":[65],"focus":[67],"was":[68],"mostly":[69],"on":[70,76],"algorithms":[73],"but":[74],"less":[75],"evaluation":[78],"different":[80],"sensors":[81],"reward":[83,113,130],"functions.":[84],"We":[85,143],"describe":[86],"end-to-end":[87],"an":[91],"autonomous":[92,105],"car,":[93],"which":[94],"used":[95],"model":[101],"create":[103],"car.":[106],"Further,":[107],"we":[108],"designed":[109],"new":[111],"efficient":[112],"function":[114],"make":[116],"agent":[118],"learn":[119],"faster":[120],"(18%":[121],"improvement":[122],"all":[124],"settings":[125],"compared":[126],"baseline":[129],"function)":[131],"build":[133],"car":[135],"necessary":[139],"perceptions":[140],"sensors.":[142],"show":[144],"that":[145],"it":[146],"performed":[147],"better":[148],"state-of-the-art":[150],"off-policy":[151],"continuous":[155],"action":[156],"(SAC,":[157],"TD3).":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}