{"id":"https://openalex.org/W4413393408","doi":"https://doi.org/10.23919/acc63710.2025.11107911","title":"Boosting Exploration in Reinforcement Learning for Sparse Reward Tasks","display_name":"Boosting Exploration in Reinforcement Learning for Sparse Reward Tasks","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413393408","doi":"https://doi.org/10.23919/acc63710.2025.11107911"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107911","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","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/A5091896736","display_name":"Yuhang Zhang","orcid":"https://orcid.org/0000-0002-6866-3447"},"institutions":[{"id":"https://openalex.org/I4210145005","display_name":"State Key Laboratory of Vehicle NVH and Safety Technology","ror":"https://ror.org/04e6h1p91","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145005"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhang Zhang","raw_affiliation_strings":["Tsinghua University,State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility,Beijing,China","institution_ids":["https://openalex.org/I4210145005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083537762","display_name":"Yao Lyu","orcid":"https://orcid.org/0000-0003-1539-472X"},"institutions":[{"id":"https://openalex.org/I4210145005","display_name":"State Key Laboratory of Vehicle NVH and Safety Technology","ror":"https://ror.org/04e6h1p91","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145005"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Lyu","raw_affiliation_strings":["Tsinghua University,State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility,Beijing,China","institution_ids":["https://openalex.org/I4210145005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029301375","display_name":"Guojian Zhan","orcid":"https://orcid.org/0000-0002-1246-4860"},"institutions":[{"id":"https://openalex.org/I4210145005","display_name":"State Key Laboratory of Vehicle NVH and Safety Technology","ror":"https://ror.org/04e6h1p91","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145005"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojian Zhan","raw_affiliation_strings":["Tsinghua University,State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility,Beijing,China","institution_ids":["https://openalex.org/I4210145005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009217428","display_name":"Wenjun Zou","orcid":"https://orcid.org/0009-0009-5331-0938"},"institutions":[{"id":"https://openalex.org/I4210145005","display_name":"State Key Laboratory of Vehicle NVH and Safety Technology","ror":"https://ror.org/04e6h1p91","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145005"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Zou","raw_affiliation_strings":["Tsinghua University,State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility,Beijing,China","institution_ids":["https://openalex.org/I4210145005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100747108","display_name":"Shengbo Eben Li","orcid":"https://orcid.org/0000-0003-4923-3633"},"institutions":[{"id":"https://openalex.org/I4210145005","display_name":"State Key Laboratory of Vehicle NVH and Safety Technology","ror":"https://ror.org/04e6h1p91","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145005"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["Tsinghua University,State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility,Beijing,China","institution_ids":["https://openalex.org/I4210145005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5091896736"],"corresponding_institution_ids":["https://openalex.org/I4210145005"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26270367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3492","last_page":"3499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.8306999802589417,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.8306999802589417,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7764000296592712,"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.691100001335144,"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/boosting","display_name":"Boosting (machine learning)","score":0.8455756902694702},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7954500913619995},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7275198698043823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5684356689453125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4907704293727875}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8455756902694702},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7954500913619995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275198698043823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5684356689453125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4907704293727875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc63710.2025.11107911","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1941445455","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2788862220","https://openalex.org/W2963781688","https://openalex.org/W2997289589","https://openalex.org/W3015082424","https://openalex.org/W3018036994","https://openalex.org/W3088218629","https://openalex.org/W4220747123","https://openalex.org/W4362650413","https://openalex.org/W4366158867","https://openalex.org/W4388878609","https://openalex.org/W4406983280"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3082059448","https://openalex.org/W4313640622","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694"],"abstract_inverted_index":{"Effective":[0],"exploration":[1,30,62,187],"is":[2,33,106],"critical":[3],"for":[4,29,142],"reinforcement":[5],"learning":[6],"(RL)":[7],"to":[8,44,49,70,98,117,195],"understand":[9],"the":[10,72,88,95,99,110,131,190],"environment":[11],"and":[12,121,157,173],"achieve":[13],"high":[14],"performance,":[15],"especially":[16],"in":[17,35,75,164],"sparse":[18,166],"reward":[19,144,167],"tasks.":[20],"Existing":[21],"methods":[22],"often":[23],"depend":[24],"on":[25,40],"task-specific":[26],"prior":[27],"knowledge":[28],"guidance,":[31],"which":[32,47,65,93,115,147],"unavailable":[34],"complex":[36],"tasks,":[37,168],"or":[38,199],"rely":[39],"additional":[41],"policy":[42,69,105],"objectives":[43],"encourage":[45],"exploration,":[46,153],"leads":[48],"sub-optimal":[50],"solutions.":[51],"This":[52],"paper":[53],"addresses":[54],"these":[55,182,197],"limitations":[56],"by":[57,108],"introducing":[58],"a":[59,84,102,137],"dual-policy":[60,151],"guided":[61,152],"(DPE)":[63],"mechanism,":[64,81],"learns":[66],"an":[67],"extra":[68],"promote":[71],"sample":[73],"collection":[74],"unfamiliar":[76,119],"state":[77,96],"areas.":[78],"In":[79],"this":[80,128],"we":[82,135],"define":[83],"curiosity":[85,113,154],"signal":[86,155],"using":[87],"random":[89],"network":[90],"distillation":[91],"technique,":[92],"evaluates":[94],"familiarity":[97],"agent.":[100],"Then,":[101],"separate":[103],"courage":[104],"trained":[107],"maximizing":[109],"accumulated":[111],"discounted":[112],"signal,":[114],"aims":[116],"explore":[118],"areas":[120],"discover":[122],"potential":[123],"high-value":[124],"behaviors.":[125],"By":[126],"incorporating":[127],"mechanism":[129],"into":[130],"distributional":[132],"RL":[133],"framework,":[134],"propose":[136],"Distributional":[138],"Soft":[139],"Actor-Critic":[140],"algorithm":[141],"Sparse":[143,171],"tasks":[145,183],"(DSAC-S),":[146],"comprises":[148],"three":[149],"modules:":[150],"learning,":[156],"actor-critic":[158],"training.":[159],"We":[160],"validate":[161],"its":[162,185],"effectiveness":[163],"several":[165],"including":[169],"MountainCar,":[170],"HalfCheetah,":[172],"IDSim.":[174],"The":[175],"results":[176],"demonstrate":[177],"that":[178],"DSAC-S":[179],"successfully":[180],"conquers":[181],"with":[184],"enhanced":[186],"ability,":[188],"while":[189],"two":[191],"baselines":[192],"either":[193],"fail":[194],"solve":[196],"problems":[198],"exhibit":[200],"poor":[201],"performance.":[202]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}