{"id":"https://openalex.org/W2140556432","doi":"https://doi.org/10.1109/cec.2002.1004434","title":"Evolutionary adaptive-critic methods for reinforcement learning","display_name":"Evolutionary adaptive-critic methods for reinforcement learning","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2140556432","doi":"https://doi.org/10.1109/cec.2002.1004434","mag":"2140556432"},"language":"en","primary_location":{"id":"doi:10.1109/cec.2002.1004434","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2002.1004434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600)","raw_type":"proceedings-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/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Xu","raw_affiliation_strings":["Department of Automatic Control, National University of Defense Technology, Changsha, Hunan, China","Dept. of Autom. Control, National Univ. of Defense Technol., Changsha, China"],"affiliations":[{"raw_affiliation_string":"Department of Automatic Control, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Dept. of Autom. Control, National Univ. of Defense Technol., Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110188567","display_name":"Hangen He","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han-gen He","raw_affiliation_strings":["Department of Automatic Control, National University of Defense Technology, Changsha, Hunan, China","Dept. of Autom. Control, National Univ. of Defense Technol., Changsha, China"],"affiliations":[{"raw_affiliation_string":"Department of Automatic Control, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Dept. of Autom. Control, National Univ. of Defense Technol., Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071074935","display_name":"Dewen Hu","orcid":"https://orcid.org/0000-0001-7357-0053"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dewen Hu","raw_affiliation_strings":["Department of Automatic Control, National University of Defense Technology, Changsha, Hunan, China","Dept. of Autom. Control, National Univ. of Defense Technol., Changsha, China"],"affiliations":[{"raw_affiliation_string":"Department of Automatic Control, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Dept. of Autom. Control, National Univ. of Defense Technol., Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053112608"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.4569,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75297224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"2","issue":null,"first_page":"1320","last_page":"1325"},"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":0.9987000226974487,"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":0.9793999791145325,"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":0.9339815378189087},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6915494203567505},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6874005198478699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6038382649421692},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5366458892822266},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.5257616639137268},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.4577977955341339},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.44677308201789856},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42861756682395935},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3491087555885315},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.34367573261260986},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1738855242729187}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9339815378189087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6915494203567505},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6874005198478699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6038382649421692},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5366458892822266},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.5257616639137268},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.4577977955341339},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.44677308201789856},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42861756682395935},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3491087555885315},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.34367573261260986},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1738855242729187},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cec.2002.1004434","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2002.1004434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1538558539","https://openalex.org/W1553415142","https://openalex.org/W1639032689","https://openalex.org/W1914583973","https://openalex.org/W2057082825","https://openalex.org/W2073258676","https://openalex.org/W2091565802","https://openalex.org/W2107726111","https://openalex.org/W2119717200","https://openalex.org/W2152150600","https://openalex.org/W2155027007","https://openalex.org/W3023540311","https://openalex.org/W3041202696","https://openalex.org/W6683204974"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2101748387","https://openalex.org/W2357975469","https://openalex.org/W4380550992","https://openalex.org/W4322760752","https://openalex.org/W3096874164","https://openalex.org/W2970347269","https://openalex.org/W2146763310","https://openalex.org/W3167472281","https://openalex.org/W2937181779"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3],"novel":[4],"hybrid":[5,33],"learning":[6,12,22,34,61,65,69,75],"method":[7,35,55],"is":[8],"proposed":[9],"for":[10],"reinforcement":[11,21,64,68],"problems":[13,23],"with":[14,39],"continuous":[15],"state":[16],"and":[17,31,62],"action":[18],"spaces.":[19],"The":[20,53],"are":[24],"modeled":[25],"as":[26],"Markov":[27],"decision":[28],"processes":[29],"(MDPs)":[30],"the":[32,48,57,74,81,84],"combines":[36],"evolutionary":[37,60],"algorithms":[38,45],"gradient-based":[40,63],"adaptive":[41],"heuristic":[42],"critic":[43],"(AHC)":[44],"to":[46,66],"approximate":[47],"optimal":[49],"policy":[50],"of":[51,59,77,83],"MDPs.":[52],"suggested":[54],"takes":[56],"advantages":[58],"solve":[67],"problems.":[70],"Simulation":[71],"results":[72],"on":[73],"control":[76],"an":[78],"acrobot":[79],"illustrate":[80],"efficiency":[82],"presented":[85],"method.":[86]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}