{"id":"https://openalex.org/W4385382152","doi":"https://doi.org/10.1007/s10489-023-04867-z","title":"Efficient distributional reinforcement learning with Kullback-Leibler divergence regularization","display_name":"Efficient distributional reinforcement learning with Kullback-Leibler divergence regularization","publication_year":2023,"publication_date":"2023-07-29","ids":{"openalex":"https://openalex.org/W4385382152","doi":"https://doi.org/10.1007/s10489-023-04867-z"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-023-04867-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-023-04867-z","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-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/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, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, University of Science and Technology of China, Suzhou, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024730880","display_name":"Zhiwei Shang","orcid":"https://orcid.org/0009-0000-6829-4568"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Zhiwei Shang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101052243","display_name":"Chunhua Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":["Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":["Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100672857","display_name":"Qing Liang","orcid":"https://orcid.org/0000-0002-8430-0515"},"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":"Qing Liang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":true,"raw_author_name":"Yunduan Cui","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5539-4260","affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5011048472"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":1.4646,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85514191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"53","issue":"21","first_page":"24847","last_page":"24863"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9959999918937683,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9416999816894531,"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/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.851622462272644},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8333916664123535},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.7089412212371826},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7048224210739136},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6782636642456055},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5410230755805969},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4738645553588867},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4319829046726227},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.43099939823150635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42524319887161255},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3422167897224426},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.32970547676086426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24626809358596802},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1926652491092682}],"concepts":[{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.851622462272644},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8333916664123535},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.7089412212371826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7048224210739136},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6782636642456055},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5410230755805969},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4738645553588867},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4319829046726227},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.43099939823150635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42524319887161255},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3422167897224426},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.32970547676086426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24626809358596802},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1926652491092682},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-023-04867-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-023-04867-z","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G372999109","display_name":null,"funder_award_id":"2021A0505030056","funder_id":"https://openalex.org/F4320324202","funder_display_name":"Guangdong Science and Technology Department"},{"id":"https://openalex.org/G506693153","display_name":null,"funder_award_id":"2020YFB2104300","funder_id":"https://openalex.org/F4320335774","funder_display_name":"Key Technologies Research and Development Program"},{"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"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324202","display_name":"Guangdong Science and Technology Department","ror":"https://ror.org/00tjzgn92"},{"id":"https://openalex.org/F4320335774","display_name":"Key Technologies Research and Development Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2145060720","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2575705757","https://openalex.org/W2730929966","https://openalex.org/W2765302304","https://openalex.org/W2772589676","https://openalex.org/W2900582619","https://openalex.org/W2905224739","https://openalex.org/W2947981406","https://openalex.org/W3004881034","https://openalex.org/W3100789280","https://openalex.org/W4205182066"],"related_works":["https://openalex.org/W2105321464","https://openalex.org/W2887774187","https://openalex.org/W2388220555","https://openalex.org/W2033178790","https://openalex.org/W3048739257","https://openalex.org/W1665563134","https://openalex.org/W2963604926","https://openalex.org/W1616881371","https://openalex.org/W1520875569","https://openalex.org/W2199957582"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}