{"id":"https://openalex.org/W1967610393","doi":"https://doi.org/10.1155/2013/492852","title":"A Novel Reinforcement Learning Architecture for Continuous State and Action Spaces","display_name":"A Novel Reinforcement Learning Architecture for Continuous State and Action Spaces","publication_year":2013,"publication_date":"2013-04-18","ids":{"openalex":"https://openalex.org/W1967610393","doi":"https://doi.org/10.1155/2013/492852","mag":"1967610393"},"language":"en","primary_location":{"id":"doi:10.1155/2013/492852","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2013/492852","pdf_url":"https://downloads.hindawi.com/archive/2013/492852.pdf","source":{"id":"https://openalex.org/S2788495","display_name":"Advances in Artificial Intelligence","issn_l":"1687-7470","issn":["1687-7470","1687-7489"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://downloads.hindawi.com/archive/2013/492852.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007082510","display_name":"V\u00edctor Uc-Cetina","orcid":"https://orcid.org/0000-0002-4713-3762"},"institutions":[{"id":"https://openalex.org/I23878562","display_name":"Autonomous University of Yucat\u00e1n","ror":"https://ror.org/032p1n739","country_code":"MX","type":"education","lineage":["https://openalex.org/I23878562"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"V\u00edctor Uc-Cetina","raw_affiliation_strings":["Facultad de Matem\u00e1ticas, Universidad Aut\u00f3noma de Yucat\u00e1n, Perif\u00e9rico Norte Tablaje 13615, Apartado Postal 192, C.P. 97119 M\u00e9rida, Yucat\u00e1n, Mexico"],"raw_orcid":"https://orcid.org/0000-0002-4713-3762","affiliations":[{"raw_affiliation_string":"Facultad de Matem\u00e1ticas, Universidad Aut\u00f3noma de Yucat\u00e1n, Perif\u00e9rico Norte Tablaje 13615, Apartado Postal 192, C.P. 97119 M\u00e9rida, Yucat\u00e1n, Mexico","institution_ids":["https://openalex.org/I23878562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007082510"],"corresponding_institution_ids":["https://openalex.org/I23878562"],"apc_list":null,"apc_paid":null,"fwci":0.4868,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74758864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2013","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.993399977684021,"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/T12288","display_name":"Optimization and Search Problems","score":0.9495000243186951,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8968433141708374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8144122362136841},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.7452640533447266},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6430543661117554},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5947130918502808},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5488007664680481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5384582877159119},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49416521191596985},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.44281697273254395},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16337138414382935}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8968433141708374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144122362136841},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.7452640533447266},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6430543661117554},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5947130918502808},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5488007664680481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5384582877159119},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49416521191596985},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.44281697273254395},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16337138414382935},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1155/2013/492852","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2013/492852","pdf_url":"https://downloads.hindawi.com/archive/2013/492852.pdf","source":{"id":"https://openalex.org/S2788495","display_name":"Advances in Artificial Intelligence","issn_l":"1687-7470","issn":["1687-7470","1687-7489"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a352d229e0a549f2995476160ff8189a","is_oa":false,"landing_page_url":"https://doaj.org/article/a352d229e0a549f2995476160ff8189a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Advances in Artificial Intelligence, Vol 2013 (2013)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2013/492852","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2013/492852","pdf_url":"https://downloads.hindawi.com/archive/2013/492852.pdf","source":{"id":"https://openalex.org/S2788495","display_name":"Advances in Artificial Intelligence","issn_l":"1687-7470","issn":["1687-7470","1687-7489"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.7599999904632568,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1967610393.pdf","grobid_xml":"https://content.openalex.org/works/W1967610393.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W171197886","https://openalex.org/W192412155","https://openalex.org/W1515851193","https://openalex.org/W1576452626","https://openalex.org/W1592847719","https://openalex.org/W1985680594","https://openalex.org/W2002978771","https://openalex.org/W2028145673","https://openalex.org/W2035446426","https://openalex.org/W2100677568","https://openalex.org/W2107726111","https://openalex.org/W2108772579","https://openalex.org/W2109790228","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2127038482","https://openalex.org/W2150339816","https://openalex.org/W2169659168","https://openalex.org/W2334782222","https://openalex.org/W3041202696"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"We":[0,85],"introduce":[1],"a":[2,22,29,38,74,100],"reinforcement":[3,136],"learning":[4,137],"architecture":[5,50,88,126],"designed":[6],"for":[7,81],"problems":[8],"with":[9,28,113],"an":[10],"infinite":[11],"number":[12,31],"of":[13,24,32,40,48],"states,":[14],"where":[15,34],"each":[16,35],"state":[17],"can":[18,127],"be":[19,71,128],"seen":[20],"as":[21,43],"vector":[23,39],"real":[25,41],"numbers":[26,42],"and":[27,89,134],"finite":[30],"actions,":[33],"action":[36,69],"requires":[37],"parameters.":[44],"The":[45],"main":[46],"objective":[47],"this":[49],"is":[51],"to":[52,60,121,130],"distribute":[53],"in":[54],"two":[55],"actors":[56],"the":[57,62,78,82,96,107,124],"work":[58,112],"required":[59],"learn":[61],"final":[63],"policy.":[64],"One":[65],"actor":[66,76],"decides":[67],"what":[68],"must":[70],"performed;":[72],"meanwhile,":[73],"second":[75],"determines":[77],"right":[79],"parameters":[80],"selected":[83],"action.":[84],"tested":[86],"our":[87],"one":[90],"algorithm":[91],"based":[92],"on":[93],"it":[94],"solving":[95],"robot":[97,102],"dribbling":[98],"problem,":[99],"challenging":[101],"control":[103],"problem":[104],"taken":[105],"from":[106],"RoboCup":[108],"competitions.":[109],"Our":[110],"experimental":[111],"three":[114],"different":[115],"function":[116],"approximators":[117],"provides":[118],"enough":[119],"evidence":[120],"prove":[122],"that":[123],"proposed":[125],"used":[129],"implement":[131],"fast,":[132],"robust,":[133],"reliable":[135],"algorithms.":[138]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}