{"id":"https://openalex.org/W2100024763","doi":"https://doi.org/10.1007/s00500-010-0581-3","title":"Continuous-action reinforcement learning with fast policy search and adaptive basis function selection","display_name":"Continuous-action reinforcement learning with fast policy search and adaptive basis function selection","publication_year":2010,"publication_date":"2010-03-27","ids":{"openalex":"https://openalex.org/W2100024763","doi":"https://doi.org/10.1007/s00500-010-0581-3","mag":"2100024763"},"language":"en","primary_location":{"id":"doi:10.1007/s00500-010-0581-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00500-010-0581-3","pdf_url":null,"source":{"id":"https://openalex.org/S65753830","display_name":"Soft Computing","issn_l":"1432-7643","issn":["1432-7643","1433-7479"],"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":"Soft Computing","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/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"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Xu","raw_affiliation_strings":["College of Mechatronics and Automation, Institute of Automation, National University of Defense Technology, ChangSha, Hunan, 410073, People\u2019s Republic of China","National University of Defense Technology, College of Mechatronics and Automation, Institute of Automation, 410073, ChangSha, Hunan, People\u2019s Republic of China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, Institute of Automation, National University of Defense Technology, ChangSha, Hunan, 410073, People\u2019s Republic of China","institution_ids":["https://openalex.org/I170215575","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National University of Defense Technology, College of Mechatronics and Automation, Institute of Automation, 410073, ChangSha, Hunan, People\u2019s Republic of China#TAB#","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100623405","display_name":"Chunming Liu","orcid":"https://orcid.org/0000-0002-0564-4476"},"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"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunming Liu","raw_affiliation_strings":["College of Mechatronics and Automation, Institute of Automation, National University of Defense Technology, ChangSha, Hunan, 410073, People\u2019s Republic of China","National University of Defense Technology, College of Mechatronics and Automation, Institute of Automation, 410073, ChangSha, Hunan, People\u2019s Republic of China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, Institute of Automation, National University of Defense Technology, ChangSha, Hunan, 410073, People\u2019s Republic of China","institution_ids":["https://openalex.org/I170215575","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National University of Defense Technology, College of Mechatronics and Automation, Institute of Automation, 410073, ChangSha, Hunan, People\u2019s Republic of China#TAB#","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"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dewen Hu","raw_affiliation_strings":["College of Mechatronics and Automation, Institute of Automation, National University of Defense Technology, ChangSha, Hunan, 410073, People\u2019s Republic of China","National University of Defense Technology, College of Mechatronics and Automation, Institute of Automation, 410073, ChangSha, Hunan, People\u2019s Republic of China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, Institute of Automation, National University of Defense Technology, ChangSha, Hunan, 410073, People\u2019s Republic of China","institution_ids":["https://openalex.org/I170215575","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National University of Defense Technology, College of Mechatronics and Automation, Institute of Automation, 410073, ChangSha, Hunan, People\u2019s Republic of China#TAB#","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053112608"],"corresponding_institution_ids":["https://openalex.org/I170215575","https://openalex.org/I4210112150"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":4.592,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.94689013,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"15","issue":"6","first_page":"1055","last_page":"1070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9954000115394592,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.8739475607872009},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7234833240509033},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.7007702589035034},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6485393643379211},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5660300254821777},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5602366924285889},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5389846563339233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5261803865432739},{"id":"https://openalex.org/keywords/basis-function","display_name":"Basis function","score":0.5254101753234863},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5027999877929688},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4968438446521759},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4941740334033966},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.48015302419662476},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.44000136852264404},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.42029982805252075},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.413520872592926},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38322556018829346},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27792805433273315},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2640068531036377},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19356998801231384}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8739475607872009},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7234833240509033},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.7007702589035034},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6485393643379211},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5660300254821777},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5602366924285889},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5389846563339233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5261803865432739},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.5254101753234863},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4968438446521759},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4941740334033966},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.48015302419662476},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.44000136852264404},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.42029982805252075},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.413520872592926},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38322556018829346},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27792805433273315},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2640068531036377},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19356998801231384},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00500-010-0581-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00500-010-0581-3","pdf_url":null,"source":{"id":"https://openalex.org/S65753830","display_name":"Soft Computing","issn_l":"1432-7643","issn":["1432-7643","1433-7479"],"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":"Soft Computing","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":35,"referenced_works":["https://openalex.org/W1531900088","https://openalex.org/W1557517019","https://openalex.org/W1574700590","https://openalex.org/W1585546214","https://openalex.org/W1965227651","https://openalex.org/W1981276685","https://openalex.org/W2041367235","https://openalex.org/W2091565802","https://openalex.org/W2100677568","https://openalex.org/W2101539915","https://openalex.org/W2107726111","https://openalex.org/W2109102709","https://openalex.org/W2116339921","https://openalex.org/W2118556122","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2124101779","https://openalex.org/W2124175081","https://openalex.org/W2132351269","https://openalex.org/W2136064843","https://openalex.org/W2139418546","https://openalex.org/W2144446635","https://openalex.org/W2147750403","https://openalex.org/W2150339816","https://openalex.org/W2151268438","https://openalex.org/W2153290280","https://openalex.org/W2158091072","https://openalex.org/W2161795906","https://openalex.org/W3103182070","https://openalex.org/W3119651796","https://openalex.org/W4214717370","https://openalex.org/W4242606736","https://openalex.org/W4256052366","https://openalex.org/W4285719527","https://openalex.org/W4307347247"],"related_works":["https://openalex.org/W2955790965","https://openalex.org/W3105579180","https://openalex.org/W4308702637","https://openalex.org/W2138446409","https://openalex.org/W4289355352","https://openalex.org/W2041176007","https://openalex.org/W2808418668","https://openalex.org/W4256087190","https://openalex.org/W4240668504","https://openalex.org/W2011233848"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}