{"id":"https://openalex.org/W4388543828","doi":"https://doi.org/10.1109/tnnls.2023.3329513","title":"Relative Entropy Regularized Sample-Efficient Reinforcement Learning With Continuous Actions","display_name":"Relative Entropy Regularized Sample-Efficient Reinforcement Learning With Continuous Actions","publication_year":2023,"publication_date":"2023-11-09","ids":{"openalex":"https://openalex.org/W4388543828","doi":"https://doi.org/10.1109/tnnls.2023.3329513","pmid":"https://pubmed.ncbi.nlm.nih.gov/37943648"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3329513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3329513","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5024730880","display_name":"Zhiwei Shang","orcid":"https://orcid.org/0009-0000-6829-4568"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zhiwei Shang","raw_affiliation_strings":["Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China","Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067872016","display_name":"Renxing Li","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renxing Li","raw_affiliation_strings":["School of Software Engineering, University of Science and Technology of China, Hefei, Anhui, China","School of Software Engineering, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Software Engineering, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020794485","display_name":"Chunhua Zheng","orcid":"https://orcid.org/0000-0002-6973-1827"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhua Zheng","raw_affiliation_strings":["CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems and the Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China","Shenzhen Institute of Advanced Technology, CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems and the Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Chinese Academy of Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems and the Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems and the Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614997","display_name":"Huiyun Li","orcid":"https://orcid.org/0000-0003-0157-1393"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyun Li","raw_affiliation_strings":["CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems and the Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China","Shenzhen Institute of Advanced Technology, CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems and the Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Chinese Academy of Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems and the Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems and the Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011048472","display_name":"Yunduan Cui","orcid":"https://orcid.org/0000-0001-5539-4260"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunduan Cui","raw_affiliation_strings":["CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems and the Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China","Shenzhen Institute of Advanced Technology, CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems and the Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Chinese Academy of Sciences, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems and the Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems and the Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5024730880"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":3.9797,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95023028,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"36","issue":"1","first_page":"475","last_page":"485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9785000085830688,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9656999707221985,"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":0.813207745552063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6272591352462769},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5230917930603027},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.5121002197265625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5039049983024597},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.49814844131469727},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.47624683380126953},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.47517791390419006},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3671189546585083},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2637336254119873},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.14035901427268982}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.813207745552063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6272591352462769},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5230917930603027},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.5121002197265625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5039049983024597},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.49814844131469727},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.47624683380126953},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47517791390419006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3671189546585083},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2637336254119873},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.14035901427268982},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2023.3329513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3329513","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37943648","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37943648","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-133398","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-133398","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3786298023","display_name":null,"funder_award_id":"JCYJ20210324115800002","funder_id":"https://openalex.org/F4320326705","funder_display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality"},{"id":"https://openalex.org/G5861395095","display_name":null,"funder_award_id":"62103403","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7648578132","display_name":null,"funder_award_id":"321GJHZ2022057MI","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320326705","display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2020573190","https://openalex.org/W2145060720","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2575705757","https://openalex.org/W2730929966","https://openalex.org/W2883972132","https://openalex.org/W2900582619","https://openalex.org/W2907217398","https://openalex.org/W2919115771","https://openalex.org/W2966477753","https://openalex.org/W2968095426","https://openalex.org/W3004881034","https://openalex.org/W3015082424","https://openalex.org/W3015979606","https://openalex.org/W3043699236","https://openalex.org/W3108488004","https://openalex.org/W3124201714","https://openalex.org/W3131031071","https://openalex.org/W3169114806","https://openalex.org/W3189480080","https://openalex.org/W4205182066","https://openalex.org/W4214717370","https://openalex.org/W4220774516","https://openalex.org/W4285606945","https://openalex.org/W4307772200","https://openalex.org/W6682330108","https://openalex.org/W6684921986","https://openalex.org/W6728925229","https://openalex.org/W6738568706","https://openalex.org/W6739455066","https://openalex.org/W6741002519","https://openalex.org/W6744991969","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6760625254","https://openalex.org/W6776172991","https://openalex.org/W6780559895","https://openalex.org/W6784712800","https://openalex.org/W6786148139","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W3090555870","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3022820045","https://openalex.org/W2163103544","https://openalex.org/W2551182807","https://openalex.org/W3033899355"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"a":[3],"novel":[4],"reinforcement":[5],"learning":[6,22,63,114,166],"(RL)":[7],"approach,":[8],"continuous":[9,33,66,76,151],"dynamic":[10],"policy":[11,57,97,146],"programming":[12],"(CDPP),":[13],"is":[14,98],"proposed":[15,36,99,129],"to":[16,49,60,100],"tackle":[17],"the":[18,28,40,45,50,62,71,79,87,91,102,107,128,132,136,157],"issues":[19],"of":[20,54,90,104,135],"both":[21,162],"stability":[23],"and":[24,85,118,124,144,154,165],"sample":[25,163],"efficiency":[26,164],"in":[27,65,78,148,161],"current":[29],"RL":[30,149],"methods":[31],"with":[32,150],"actions.":[34],"The":[35],"method":[37,130],"naturally":[38],"extends":[39],"relative":[41,108,137],"entropy":[42,109,138],"regularization":[43,139],"from":[44],"value":[46],"function-based":[47],"framework":[48,53],"actor-critic":[51],"(AC)":[52],"deep":[55],"deterministic":[56],"gradient":[58],"(DDPG)":[59],"stabilize":[61],"process":[64],"action":[67,152],"space.":[68],"It":[69],"tackles":[70],"intractable":[72],"softmax":[73],"operation":[74],"over":[75],"actions":[77],"critic":[80,111],"by":[81,121],"Monte":[82],"Carlo":[83],"estimation":[84],"explores":[86],"practical":[88],"advantages":[89],"Mellowmax":[92],"operator.":[93],"A":[94],"Boltzmann":[95],"sampling":[96],"guide":[101],"exploration":[103,116,142],"actor":[105],"following":[106],"regularized":[110],"for":[112],"superior":[113],"capability,":[115],"efficiency,":[117],"robustness.":[119],"Evaluated":[120],"several":[122],"benchmark":[123],"real-robot-based":[125],"simulation":[126],"tasks,":[127],"illustrates":[131],"positive":[133],"impact":[134],"including":[140],"efficient":[141],"behavior":[143],"stable":[145],"update":[147],"space":[153],"successfully":[155],"outperforms":[156],"related":[158],"baseline":[159],"approaches":[160],"stability.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":10}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}