{"id":"https://openalex.org/W2077907932","doi":"https://doi.org/10.1142/s0218001414600076","title":"TRANSFER LEARNING FOR CONTINUOUS STATE AND ACTION SPACES","display_name":"TRANSFER LEARNING FOR CONTINUOUS STATE AND ACTION SPACES","publication_year":2014,"publication_date":"2014-08-03","ids":{"openalex":"https://openalex.org/W2077907932","doi":"https://doi.org/10.1142/s0218001414600076","mag":"2077907932"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001414600076","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001414600076","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","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/A5053042092","display_name":"Esteban Garcia","orcid":null},"institutions":[{"id":"https://openalex.org/I39824353","display_name":"National Institute of Astrophysics, Optics and Electronics","ror":"https://ror.org/00bpmmc63","country_code":"MX","type":"facility","lineage":["https://openalex.org/I39824353"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"ESTEBAN O. GARC\u00cdA","raw_affiliation_strings":["Computer Science, Instituto Nacional de Astrofisica, Optica y Electronica, Tonantzintla, Puebla 72840, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, Instituto Nacional de Astrofisica, Optica y Electronica, Tonantzintla, Puebla 72840, Mexico","institution_ids":["https://openalex.org/I39824353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064277708","display_name":"Enrique Mu\u00f1oz de Cote","orcid":"https://orcid.org/0000-0002-3249-096X"},"institutions":[{"id":"https://openalex.org/I39824353","display_name":"National Institute of Astrophysics, Optics and Electronics","ror":"https://ror.org/00bpmmc63","country_code":"MX","type":"facility","lineage":["https://openalex.org/I39824353"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"ENRIQUE MUNOZ DE COTE","raw_affiliation_strings":["Computer Science, Instituto Nacional de Astrofisica, Optica y Electronica, Tonantzintla, Puebla 72840, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, Instituto Nacional de Astrofisica, Optica y Electronica, Tonantzintla, Puebla 72840, Mexico","institution_ids":["https://openalex.org/I39824353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035687300","display_name":"Eduardo F. Morales","orcid":"https://orcid.org/0000-0002-7618-8762"},"institutions":[{"id":"https://openalex.org/I39824353","display_name":"National Institute of Astrophysics, Optics and Electronics","ror":"https://ror.org/00bpmmc63","country_code":"MX","type":"facility","lineage":["https://openalex.org/I39824353"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"EDUARDO F. MORALES","raw_affiliation_strings":["Computer Science, Instituto Nacional de Astrofisica, Optica y Electronica, Tonantzintla, Puebla 72840, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, Instituto Nacional de Astrofisica, Optica y Electronica, Tonantzintla, Puebla 72840, Mexico","institution_ids":["https://openalex.org/I39824353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4229,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75510235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"28","issue":"07","first_page":"1460007","last_page":"1460007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9966999888420105,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9905999898910522,"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":0.8291042447090149},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.746066689491272},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.7294430136680603},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.7045331001281738},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6101089119911194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6095198392868042},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5853939652442932},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5114377737045288},{"id":"https://openalex.org/keywords/inductive-transfer","display_name":"Inductive transfer","score":0.46565940976142883},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4637262225151062},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45899561047554016},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4332839846611023},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42833125591278076},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.41718292236328125},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4103041887283325},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.28921031951904297},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11601290106773376},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10173740983009338},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.08397513628005981}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8291042447090149},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.746066689491272},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.7294430136680603},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7045331001281738},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6101089119911194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6095198392868042},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5853939652442932},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5114377737045288},{"id":"https://openalex.org/C77075516","wikidata":"https://www.wikidata.org/wiki/Q6027324","display_name":"Inductive transfer","level":5,"score":0.46565940976142883},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4637262225151062},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45899561047554016},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4332839846611023},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42833125591278076},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.41718292236328125},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4103041887283325},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.28921031951904297},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11601290106773376},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10173740983009338},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.08397513628005981},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"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/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0218001414600076","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001414600076","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.723.5985","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.723.5985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ccc.inaoep.mx/%7Ejemc/bib/bib2html/e-documents/ijprai14.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W36691172","https://openalex.org/W109727711","https://openalex.org/W110451278","https://openalex.org/W197857547","https://openalex.org/W755046805","https://openalex.org/W1480877541","https://openalex.org/W1515851193","https://openalex.org/W1520597402","https://openalex.org/W1746819321","https://openalex.org/W1799762961","https://openalex.org/W1986935961","https://openalex.org/W1994005439","https://openalex.org/W2004030284","https://openalex.org/W2097381042","https://openalex.org/W2098946742","https://openalex.org/W2108734173","https://openalex.org/W2109102709","https://openalex.org/W2110292307","https://openalex.org/W2117629901","https://openalex.org/W2123246446","https://openalex.org/W2126025075","https://openalex.org/W2128786740","https://openalex.org/W2132849848","https://openalex.org/W2134491302","https://openalex.org/W2140135625","https://openalex.org/W2151268438","https://openalex.org/W2153353285","https://openalex.org/W2156974606","https://openalex.org/W2760506156","https://openalex.org/W3103256699","https://openalex.org/W3103503690","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W3016888008","https://openalex.org/W4387770285","https://openalex.org/W3022215768","https://openalex.org/W2165698076","https://openalex.org/W4387183713","https://openalex.org/W2821676139","https://openalex.org/W3043695725","https://openalex.org/W4382138864","https://openalex.org/W3135975972","https://openalex.org/W4287255623"],"abstract_inverted_index":{"Transfer":[0],"learning":[1,19,41,108,132,135],"focuses":[2],"on":[3,113],"developing":[4],"methods":[5],"to":[6,16,33,129],"reuse":[7],"information":[8,72],"gathered":[9],"from":[10,81],"a":[11,22,30,39,120],"source":[12,83],"task":[13,98],"in":[14,21,38,62,67,123],"order":[15],"improve":[17],"the":[18,50,63,68,74,77,82,90,96,102,107,124],"performance":[20,126],"related":[23],"task.":[24],"In":[25],"this":[26],"work,":[27],"we":[28],"present":[29],"novel":[31],"approach":[32,65],"transfer":[34,134],"knowledge":[35,88],"between":[36],"tasks":[37,115],"reinforcement":[40,131],"(RL)":[42],"framework":[43],"with":[44],"continuous":[45,138],"states":[46],"and":[47,52,105,133,140],"actions,":[48],"where":[49],"transition":[51,79,93],"policy":[53],"functions":[54],"are":[55],"approximated":[56],"by":[57],"Gaussian":[58],"processes.":[59],"The":[60],"novelty":[61],"proposed":[64],"lies":[66],"idea":[69],"of":[70,76,92],"transferring":[71],"about":[73,89],"hyper-parameters":[75],"state":[78,139],"function":[80,94],"task,":[84],"which":[85,118],"represents":[86],"qualitative":[87],"type":[91],"that":[95],"target":[97],"might":[99],"have,":[100],"constraining":[101],"search":[103],"space":[104],"accelerating":[106],"process.":[109],"We":[110],"performed":[111],"experiments":[112],"relevant":[114],"for":[116,137],"RL,":[117],"show":[119],"clear":[121],"improvement":[122],"overall":[125],"when":[127],"compared":[128],"state-of-the-art":[130],"algorithms":[136],"action":[141],"spaces.":[142]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
