{"id":"https://openalex.org/W4385341811","doi":"https://doi.org/10.1007/s10489-023-04816-w","title":"A stable data-augmented reinforcement learning method with ensemble exploration and exploitation","display_name":"A stable data-augmented reinforcement learning method with ensemble exploration and exploitation","publication_year":2023,"publication_date":"2023-07-28","ids":{"openalex":"https://openalex.org/W4385341811","doi":"https://doi.org/10.1007/s10489-023-04816-w"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-023-04816-w","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-023-04816-w","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/A5017790030","display_name":"Guoyu Zuo","orcid":"https://orcid.org/0000-0002-7624-4728"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoyu Zuo","raw_affiliation_strings":["Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, 100124, China","Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, 100124, China","institution_ids":[]},{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100814130","display_name":"Tian Zhipeng","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Tian","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072001884","display_name":"Gao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gao Huang","raw_affiliation_strings":["Beijing Advanced Innovation Center for Intelligent Robots and Systems, Beijing Institute of Technology, Beijing, 100081, China","Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, 100124, China","Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China"],"raw_orcid":"https://orcid.org/0000-0002-0003-0184","affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Intelligent Robots and Systems, Beijing Institute of Technology, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, 100124, China","institution_ids":[]},{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072001884"],"corresponding_institution_ids":["https://openalex.org/I125839683","https://openalex.org/I37796252"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.2619,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63375263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"53","issue":"21","first_page":"24792","last_page":"24803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9921000003814697,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9480999708175659,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8873063325881958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8672705888748169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5957089066505432},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5759406685829163},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5736872553825378},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.5635994076728821},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.46175312995910645},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.44914889335632324},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4462668299674988},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4395032525062561},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4296908676624298},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07890838384628296}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8873063325881958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8672705888748169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5957089066505432},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5759406685829163},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5736872553825378},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.5635994076728821},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.46175312995910645},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.44914889335632324},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4462668299674988},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4395032525062561},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4296908676624298},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07890838384628296},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-023-04816-w","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-023-04816-w","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/G3944791195","display_name":null,"funder_award_id":"62103053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6025883443","display_name":"\u57fa\u4e8e\u9065\u64cd\u4f5c\u793a\u6559\u7684\u4eba\u5f62\u673a\u5668\u4eba\u7c7b\u4eba\u52a8\u4f5c\u751f\u6210\u5bf9\u6297\u5f0f\u6a21\u4eff\u5b66\u4e60\u7814\u7a76","funder_award_id":"61873008","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2087270044","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2162489814","https://openalex.org/W2167917621","https://openalex.org/W2244486986","https://openalex.org/W2887503931","https://openalex.org/W3175558129"],"related_works":["https://openalex.org/W4245395944","https://openalex.org/W2143551613","https://openalex.org/W1979740464","https://openalex.org/W2143345456","https://openalex.org/W2138823233","https://openalex.org/W1789991335","https://openalex.org/W2562731034","https://openalex.org/W4315705795","https://openalex.org/W2101053337","https://openalex.org/W1870651561"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}