{"id":"https://openalex.org/W2031692836","doi":"https://doi.org/10.1007/s00521-014-1738-2","title":"A data-based online reinforcement learning algorithm satisfying probably approximately correct principle","display_name":"A data-based online reinforcement learning algorithm satisfying probably approximately correct principle","publication_year":2014,"publication_date":"2014-10-29","ids":{"openalex":"https://openalex.org/W2031692836","doi":"https://doi.org/10.1007/s00521-014-1738-2","mag":"2031692836"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-014-1738-2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00521-014-1738-2","pdf_url":null,"source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"Neural Computing and Applications","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/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["The State Key Laboratory of Management and Control for Complex Systems, Institution of Automation, Chinese Academy of Sciences, Beijing, China","The State Key Laboratory of Management and Control for Complex Systems, Institution of Automation, Chinese Academy of Sciences, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institution of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institution of Automation, Chinese Academy of Sciences, Beijing, China#TAB#","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["The State Key Laboratory of Management and Control for Complex Systems, Institution of Automation, Chinese Academy of Sciences, Beijing, China","The State Key Laboratory of Management and Control for Complex Systems, Institution of Automation, Chinese Academy of Sciences, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institution of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institution of Automation, Chinese Academy of Sciences, Beijing, China#TAB#","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080193690"],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":2.205,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87623366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"26","issue":"4","first_page":"775","last_page":"787"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9829999804496765,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7858281135559082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7623496055603027},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.6856638193130493},{"id":"https://openalex.org/keywords/mathematical-proof","display_name":"Mathematical proof","score":0.6186596155166626},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5878522992134094},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5028561949729919},{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.4945964515209198},{"id":"https://openalex.org/keywords/online-algorithm","display_name":"Online algorithm","score":0.4737178683280945},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4607994854450226},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.45839107036590576},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3829116225242615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2855038642883301},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23400282859802246},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23169350624084473}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7858281135559082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623496055603027},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.6856638193130493},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.6186596155166626},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5878522992134094},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5028561949729919},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.4945964515209198},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.4737178683280945},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4607994854450226},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.45839107036590576},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3829116225242615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2855038642883301},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23400282859802246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23169350624084473},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-014-1738-2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00521-014-1738-2","pdf_url":null,"source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W21891419","https://openalex.org/W65193931","https://openalex.org/W1515851193","https://openalex.org/W1552830313","https://openalex.org/W1626155273","https://openalex.org/W1747856733","https://openalex.org/W1974883306","https://openalex.org/W1990803996","https://openalex.org/W2010193406","https://openalex.org/W2018160758","https://openalex.org/W2018547649","https://openalex.org/W2030038728","https://openalex.org/W2032252420","https://openalex.org/W2035018355","https://openalex.org/W2036729506","https://openalex.org/W2044792947","https://openalex.org/W2056509413","https://openalex.org/W2057447866","https://openalex.org/W2082691056","https://openalex.org/W2093831009","https://openalex.org/W2116488102","https://openalex.org/W2117056304","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2129670787","https://openalex.org/W2159571856","https://openalex.org/W2468519215","https://openalex.org/W2489939061","https://openalex.org/W2911302472","https://openalex.org/W3011120880","https://openalex.org/W3041834803","https://openalex.org/W3139377883","https://openalex.org/W4214717370","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4287073482","https://openalex.org/W2952412049","https://openalex.org/W2572248225","https://openalex.org/W1876956220","https://openalex.org/W3185920324","https://openalex.org/W2195225896","https://openalex.org/W3006977717","https://openalex.org/W4388993829","https://openalex.org/W1993326513","https://openalex.org/W2125573488"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}