{"id":"https://openalex.org/W841120541","doi":null,"title":"Competitive function approximation for reinforcement learning","display_name":"Competitive function approximation for reinforcement learning","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W841120541","mag":"841120541"},"language":"en","primary_location":{"id":"pmh:oai:digital.csic.es:10261/133994","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10261/133994","pdf_url":null,"source":{"id":"https://openalex.org/S4306400616","display_name":"DIGITAL.CSIC (Spanish National Research Council (CSIC))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I134820265","host_organization_name":"Consejo Superior de Investigaciones Cient\u00edficas","host_organization_lineage":["https://openalex.org/I134820265"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Documento de trabajo"},"volume":null,"type":"report","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10261/133994","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051585666","display_name":"Alejandro Agostini","orcid":"https://orcid.org/0000-0002-4894-8752","observed_orcids":["https://orcid.org/0000-0002-4894-8752"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alejandro Agostini","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4894-8752","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084548795","display_name":"Enric Celaya","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Enric Celaya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T10320","display_name":"Neural Networks and Applications","score":0.0,"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":0.0,"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/function-approximation","display_name":"function approximation","score":0.7910000085830688},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.6489999890327454},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8119999766349792},{"id":"https://openalex.org/keywords/continuous-state-spaces","display_name":"continuous state spaces","score":0.8090000152587891},{"id":"https://openalex.org/keywords/nonstationarity","display_name":"non-stationarity","score":0.906000018119812},{"id":"https://openalex.org/keywords/biased-sampling","display_name":"biased sampling","score":0.8579999804496765},{"id":"https://openalex.org/keywords/competitive-learning","display_name":"competitive learning","score":0.7149999737739563},{"id":"https://openalex.org/keywords/bootstrap-method","display_name":"bootstrapping","score":0.8109999895095825},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"dynamic programming","score":0.8009999990463257}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8060429692268372},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.7200571298599243},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6081196069717407},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5873353481292725},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5689213275909424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5642745494842529},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.562190592288971},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5470997095108032},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48364579677581787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3471205234527588},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3037548065185547},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19430795311927795},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.15344011783599854},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:digital.csic.es:10261/133994","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10261/133994","pdf_url":null,"source":{"id":"https://openalex.org/S4306400616","display_name":"DIGITAL.CSIC (Spanish National Research Council (CSIC))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I134820265","host_organization_name":"Consejo Superior de Investigaciones Cient\u00edficas","host_organization_lineage":["https://openalex.org/I134820265"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Documento de trabajo"},{"id":"pmh:oai:upcommons.upc.edu:2117/28454","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/28454","pdf_url":"http://hdl.handle.net/2117/28454","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"External research report"},{"id":"pmh:oai:dnet:upcommonspor::63765e22f922fa98c70321a1aabe997b","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/28454","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/report"},{"id":"pmh:oai:recercat.cat:2072/251499","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/28454","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/report"},{"id":"mag:841120541","doi":null,"is_oa":false,"landing_page_url":"http://digital.csic.es/bitstream/10261/133994/1/Reinforcement-Learning.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:digital.csic.es:10261/133994","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10261/133994","pdf_url":null,"source":{"id":"https://openalex.org/S4306400616","display_name":"DIGITAL.CSIC (Spanish National Research Council (CSIC))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I134820265","host_organization_name":"Consejo Superior de Investigaciones Cient\u00edficas","host_organization_lineage":["https://openalex.org/I134820265"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Documento de trabajo"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W841120541.pdf","grobid_xml":"https://content.openalex.org/works/W841120541.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2099639485","https://openalex.org/W7099815579","https://openalex.org/W2532538840","https://openalex.org/W2154549708","https://openalex.org/W7095341322","https://openalex.org/W7067567345","https://openalex.org/W1547105496","https://openalex.org/W1624593201","https://openalex.org/W2327190923","https://openalex.org/W7100363827"],"abstract_inverted_index":{"The":[0,127,146],"application":[1],"of":[2,17,24,35,46,50,69,90,123,130,148],"reinforcement":[3,25],"learning":[4,26,187],"to":[5,137],"problems":[6,175],"with":[7,81,115,167],"continuous":[8],"domains":[9],"requires":[10],"representing":[11],"the":[12,29,36,44,47,54,70,87,113,131,142,178],"value":[13,55],"function":[14,18,30,38,56,99],"by":[15,121],"means":[16,122],"approximation.":[19,62],"We":[20],"identify":[21],"two":[22],"aspects":[23],"that":[27,177],"make":[28],"approximation":[31,100,118],"process":[32],"hard:":[33],"non-stationarity":[34],"target":[37],"and":[39,112,140,152,184],"biased":[40,143],"sampling.":[41],"Non-stationarity":[42],"is":[43,57,119],"result":[45],"bootstrapping":[48],"nature":[49,129],"dynamic":[51],"programming":[52],"where":[53,101],"estimated":[58],"using":[59],"its":[60],"current":[61],"Biased":[63],"sampling":[64,144],"occurs":[65],"when":[66],"some":[67],"regions":[68],"state":[71],"space":[72],"are":[73,106],"visited":[74],"too":[75],"often,":[76],"causing":[77],"a":[78,95,109,124,158,168,182],"reiterated":[79],"updating":[80],"similar":[82],"values":[83],"which":[84],"fade":[85],"out":[86],"occasional":[88],"updates":[89],"infrequently":[91],"sampled":[92],"regions.\\n\\nWe":[93],"propose":[94],"competitive":[96,179],"approach":[97],"for":[98],"many":[102],"different":[103,173],"local":[104,128],"approximators":[105,132,150],"available":[107],"at":[108],"given":[110],"input":[111],"one":[114],"expectedly":[116],"best":[117],"selected":[120],"relevance":[125],"function.":[126],"allows":[133],"their":[134],"fast":[135],"adaptation":[136],"non-stationary":[138],"changes":[139],"mitigates":[141],"problem.":[145],"coexistence":[147],"multiple":[149],"updated":[151],"tried":[153],"in":[154,172],"parallel":[155],"permits":[156],"obtaining":[157],"good":[159],"estimation":[160],"much":[161],"faster":[162,183],"than":[163,188],"would":[164],"be":[165],"possible":[166],"single":[169],"approximator.":[170],"Experiments":[171],"benchmark":[174],"show":[176],"strategy":[180],"provides":[181],"more":[185],"stable":[186],"non-competitive":[189],"approaches.":[190]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}