{"id":"https://openalex.org/W3203477356","doi":"https://doi.org/10.1109/case49439.2021.9551544","title":"Exploration via Distributional Reinforcement Learning with Epistemic and Aleatoric Uncertainty Estimation","display_name":"Exploration via Distributional Reinforcement Learning with Epistemic and Aleatoric Uncertainty Estimation","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3203477356","doi":"https://doi.org/10.1109/case49439.2021.9551544","mag":"3203477356"},"language":"en","primary_location":{"id":"doi:10.1109/case49439.2021.9551544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case49439.2021.9551544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)","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/A5100453159","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-7485-6344"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Liu","raw_affiliation_strings":["Harbin Institute of Technology,Department of Control Science and Engineering,Shenzhen,China","Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Department of Control Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677178","display_name":"Yanjie Li","orcid":"https://orcid.org/0000-0001-7890-9677"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjie Li","raw_affiliation_strings":["Harbin Institute of Technology,Department of Control Science and Engineering,Shenzhen,China","Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Department of Control Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064580686","display_name":"Yuecheng Liu","orcid":"https://orcid.org/0000-0002-3683-7959"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuecheng Liu","raw_affiliation_strings":["Harbin Institute of Technology,Department of Control Science and Engineering,Shenzhen,China","Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Department of Control Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748367","display_name":"Meiling Chen","orcid":"https://orcid.org/0000-0003-2803-6446"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meiling Chen","raw_affiliation_strings":["Harbin Institute of Technology,Department of Control Science and Engineering,Shenzhen,China","Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Department of Control Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065660401","display_name":"Shaohua Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohua Lv","raw_affiliation_strings":["Harbin Institute of Technology,Department of Control Science and Engineering,Shenzhen,China","Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Department of Control Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014818692","display_name":"Yunhong Xu","orcid":"https://orcid.org/0000-0002-0958-2188"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhong Xu","raw_affiliation_strings":["Harbin Institute of Technology,Department of Control Science and Engineering,Shenzhen,China","Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Department of Control Science and Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100453159"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63703301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2256","last_page":"2261"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9984999895095825,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9689000248908997,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.830491304397583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7386414408683777},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6840603947639465},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.6292932629585266},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6160070896148682},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5567667484283447},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5309946537017822},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5118626952171326}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.830491304397583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7386414408683777},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6840603947639465},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.6292932629585266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6160070896148682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5567667484283447},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5309946537017822},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5118626952171326},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case49439.2021.9551544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case49439.2021.9551544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2636664055","display_name":null,"funder_award_id":"JCYJ20180507183837726","funder_id":"https://openalex.org/F4320329791","funder_display_name":"Shenzhen Fundamental Research Program"},{"id":"https://openalex.org/G6105381427","display_name":null,"funder_award_id":"U1813206,61977019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W779494576","https://openalex.org/W1560021816","https://openalex.org/W1757796397","https://openalex.org/W2025720061","https://openalex.org/W2046033161","https://openalex.org/W2067707835","https://openalex.org/W2121863487","https://openalex.org/W2328111639","https://openalex.org/W2600383743","https://openalex.org/W2885550588","https://openalex.org/W2904688694","https://openalex.org/W2946364835","https://openalex.org/W2962878825","https://openalex.org/W2963126744","https://openalex.org/W2963238274","https://openalex.org/W2963423916","https://openalex.org/W2963757175","https://openalex.org/W2969456553","https://openalex.org/W2970036354","https://openalex.org/W2970961171","https://openalex.org/W2999778183","https://openalex.org/W3101442004"],"related_works":["https://openalex.org/W4312200629","https://openalex.org/W4223943233","https://openalex.org/W4360585206","https://openalex.org/W4364306694","https://openalex.org/W4309045103","https://openalex.org/W4225161397","https://openalex.org/W3014300295","https://openalex.org/W3164822677","https://openalex.org/W4250304930","https://openalex.org/W2922457425"],"abstract_inverted_index":{"The":[0],"problem":[1],"of":[2,6],"exploration":[3,23,64],"remains":[4],"one":[5],"the":[7,22,37,63,79,83],"major":[8],"challenges":[9],"in":[10,85],"deep":[11,46,67],"reinforcement":[12],"learning":[13],"(RL).":[14],"This":[15,56],"paper":[16,30,57],"proposes":[17,31],"an":[18],"approach":[19,81],"to":[20,35,61],"improve":[21,62],"efficiency":[24,65],"for":[25,42,66],"distributional":[26,43,68],"RL.":[27],"First,":[28],"this":[29],"a":[32,59],"novel":[33],"method":[34,60],"estimate":[36],"epistemic":[38,73],"and":[39],"aleatoric":[40],"uncertainty":[41],"RL":[44,69],"using":[45,71],"ensembles,":[47],"which":[48],"is":[49],"inspired":[50],"by":[51,70],"Bayesian":[52],"Deep":[53],"Learning.":[54],"Second,":[55],"presents":[58],"estimated":[72],"uncertainty.":[74],"Experimental":[75],"results":[76],"show":[77],"that":[78],"proposed":[80],"outperforms":[82],"baseline":[84],"Atari":[86],"games.":[87]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}