{"id":"https://openalex.org/W4411453433","doi":"https://doi.org/10.1007/s10489-025-06693-x","title":"Reducing the value function over-estimation by Kullback-Leibler divergence regularized distributional actor-critic","display_name":"Reducing the value function over-estimation by Kullback-Leibler divergence regularized distributional actor-critic","publication_year":2025,"publication_date":"2025-06-19","ids":{"openalex":"https://openalex.org/W4411453433","doi":"https://doi.org/10.1007/s10489-025-06693-x"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-025-06693-x","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-025-06693-x","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/A5042782318","display_name":"Ming Gong","orcid":"https://orcid.org/0000-0002-5534-2177"},"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":true,"raw_author_name":"Mingrong Gong","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018768566","display_name":"Zhengkun Yi","orcid":"https://orcid.org/0000-0002-8714-1353"},"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":"Zhengkun Yi","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100689058","display_name":"Yidong Chen","orcid":"https://orcid.org/0000-0002-0243-7228"},"institutions":[{"id":"https://openalex.org/I4210086346","display_name":"Guangdong Machinery Research Institute","ror":"https://ror.org/000wc3348","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210086346"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidong Chen","raw_affiliation_strings":["Shenzhen ZHAOWEI Machinery & Electronics Co., Ltd., Shenzhen, 518105, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen ZHAOWEI Machinery & Electronics Co., Ltd., Shenzhen, 518105, Guangdong, China","institution_ids":["https://openalex.org/I4210086346"]}]},{"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/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"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 Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China","Shenzhen University ofAdvanced Technology, Shenzhen, 518107, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Shenzhen University ofAdvanced Technology, Shenzhen, 518107, Guangdong, China","institution_ids":["https://openalex.org/I4210152380"]}]},{"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":["Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, Shenzhen, 518055, Guangdong, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042782318"],"corresponding_institution_ids":["https://openalex.org/I4210145761"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":2.6995,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90797899,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"55","issue":"11","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9959999918937683,"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":0.9959999918937683,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.9397000074386597,"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"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9386000037193298,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.8543937802314758},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.7713895440101624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7616277933120728},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5655199289321899},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5079041123390198},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4914361238479614},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.391933798789978},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38346949219703674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35373425483703613},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2193564474582672},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1664828658103943}],"concepts":[{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.8543937802314758},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.7713895440101624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616277933120728},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5655199289321899},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5079041123390198},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4914361238479614},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.391933798789978},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38346949219703674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35373425483703613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2193564474582672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1664828658103943},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-025-06693-x","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-025-06693-x","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":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1785420969","display_name":null,"funder_award_id":"U22A2056","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2026659355","https://openalex.org/W2145060720","https://openalex.org/W2158782408","https://openalex.org/W2730929966","https://openalex.org/W2765302304","https://openalex.org/W2900582619","https://openalex.org/W2902907165","https://openalex.org/W2919115771","https://openalex.org/W3000642679","https://openalex.org/W3004881034","https://openalex.org/W3011591403","https://openalex.org/W3015082424","https://openalex.org/W3041202696","https://openalex.org/W3160355689","https://openalex.org/W3188220908","https://openalex.org/W4249736682","https://openalex.org/W4308933789","https://openalex.org/W4310895557","https://openalex.org/W4311607213","https://openalex.org/W4313352051","https://openalex.org/W4382239299","https://openalex.org/W4385382152","https://openalex.org/W4391360925","https://openalex.org/W4392499083","https://openalex.org/W4393146620","https://openalex.org/W4396909955","https://openalex.org/W4405109230","https://openalex.org/W6776607772","https://openalex.org/W6814003322"],"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":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}