{"id":"https://openalex.org/W4416749476","doi":"https://doi.org/10.1109/iros60139.2025.11246186","title":"SAC(\u03bb): Efficient Reinforcement Learning for Sparse-Reward Autonomous Car Racing using Imperfect Demonstrations","display_name":"SAC(\u03bb): Efficient Reinforcement Learning for Sparse-Reward Autonomous Car Racing using Imperfect Demonstrations","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749476","doi":"https://doi.org/10.1109/iros60139.2025.11246186"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5039121949","display_name":"H. Y. Lee","orcid":"https://orcid.org/0000-0001-6970-6042"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heeseong Lee","raw_affiliation_strings":["Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114285959","display_name":"Sungpyo Sagong","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungpyo Sagong","raw_affiliation_strings":["Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100607969","display_name":"Minhyeong Lee","orcid":"https://orcid.org/0000-0002-6853-6528"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minhyeong Lee","raw_affiliation_strings":["Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118704590","display_name":"Jeongmin Lee","orcid":"https://orcid.org/0000-0002-6953-4129"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongmin Lee","raw_affiliation_strings":["Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100626026","display_name":"Dongjun Lee","orcid":"https://orcid.org/0000-0003-2108-3960"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongjun Lee","raw_affiliation_strings":["Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Institute of Advanced Machines and Design (IAMD) and Institute of Engineering Research (IOER),Department of Mechanical Engineering,Seoul,South Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34278529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13460","last_page":"13467"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7904000282287598,"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":0.7904000282287598,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.09700000286102295,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0210999995470047,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8641999959945679},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7820000052452087},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5715000033378601},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.5625},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4377000033855438},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.34150001406669617}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8641999959945679},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7820000052452087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541000247001648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.611299991607666},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5715000033378601},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.5625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.482699990272522},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34150001406669617},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324625","display_name":"Korea Agency for Infrastructure Technology Advancement","ror":"https://ror.org/00rxf7n07"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2102847492","https://openalex.org/W2410617946","https://openalex.org/W2615547864","https://openalex.org/W2806163172","https://openalex.org/W2869375357","https://openalex.org/W2954115742","https://openalex.org/W2979863294","https://openalex.org/W2999762404","https://openalex.org/W3030656010","https://openalex.org/W3047366950","https://openalex.org/W3068678661","https://openalex.org/W3132760324","https://openalex.org/W3188004887","https://openalex.org/W3204990527","https://openalex.org/W3205950063","https://openalex.org/W4206098878","https://openalex.org/W4210870706","https://openalex.org/W4285102517","https://openalex.org/W4382203560","https://openalex.org/W4385539610","https://openalex.org/W4386285856","https://openalex.org/W4390494915","https://openalex.org/W4415795934"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,10,115],"Reinforcement":[3],"Learning":[4],"(RL)":[5],"have":[6],"demonstrated":[7],"promising":[8],"results":[9],"autonomous":[11],"car":[12],"racing.":[13],"However,":[14],"two":[15,63],"fundamental":[16],"challenges":[17],"remain:":[18],"sparse":[19],"rewards,":[20],"which":[21,31,70,95],"hinder":[22],"efficient":[23],"learning":[24,82,89],"process,":[25],"and":[26,84,131,139,143],"the":[27,34,97,109,116,128],"quality":[28],"of":[29,36,104],"demonstrations,":[30,130],"directly":[32],"affects":[33],"effectiveness":[35],"RL":[37,138],"from":[38,74],"Demonstration":[39],"(RLfD)":[40],"approaches.":[41,141],"To":[42],"address":[43],"these":[44],"issues,":[45],"we":[46,120],"propose":[47],"SAC(\u03bb),":[48],"a":[49,67,86],"novel":[50],"RLfD":[51,140],"algorithm":[52],"tailored":[53],"for":[54],"sparse-reward":[55],"racing":[56],"tasks":[57],"with":[58,91],"imperfect":[59],"demonstrations.":[60],"SAC(\u03bb)":[61,123],"introduces":[62],"key":[64],"components:":[65],"(1)":[66],"discriminator-augmented":[68],"Q-function,":[69],"integrates":[71],"prior":[72,93],"knowledge":[73],"demonstrations":[75],"into":[76],"value":[77],"estimation":[78],"while":[79,107],"maintaining":[80],"off-policy":[81],"benefits,":[83],"(2)":[85],"Positive-Unlabeled":[87],"(PU)":[88],"framework":[90],"adaptive":[92],"adjustment,":[94],"enables":[96],"agent":[98],"to":[99],"progressively":[100],"refine":[101],"its":[102],"understanding":[103],"positive":[105],"behaviors,":[106],"mitigating":[108],"overfitting":[110],"problem.":[111],"Through":[112],"extensive":[113],"experiments":[114],"Assetto":[117],"Corsa":[118],"simulator,":[119],"demonstrate":[121],"that":[122],"significantly":[124],"accelerates":[125],"training,":[126],"surpasses":[127],"provided":[129],"achieves":[132],"superior":[133],"lap":[134],"times":[135],"over":[136],"existing":[137],"Code":[142],"videos":[144],"are":[145],"available":[146],"at":[147],"https://heesungsung.github.":[148],"io/AC-RLRacer/.":[149]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}