{"id":"https://openalex.org/W2908151956","doi":"https://doi.org/10.1109/icosc.2018.8587772","title":"Learning Upper-Level Policy using Importance Sampling-based Policy Search Method","display_name":"Learning Upper-Level Policy using Importance Sampling-based Policy Search Method","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2908151956","doi":"https://doi.org/10.1109/icosc.2018.8587772","mag":"2908151956"},"language":"en","primary_location":{"id":"doi:10.1109/icosc.2018.8587772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icosc.2018.8587772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 7th International Conference on Systems and Control (ICSC)","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/A5068628217","display_name":"J.M. Pastor","orcid":"https://orcid.org/0000-0003-4458-0353"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose Pastor","raw_affiliation_strings":["Universitat Politecnica de Valencia, Valencia, Valenciana, ES"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Politecnica de Valencia, Valencia, Valenciana, ES","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042019617","display_name":"Henry D\u00edaz","orcid":"https://orcid.org/0000-0003-4580-972X"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Henry Diaz","raw_affiliation_strings":["Universitat Politecnica de Valencia, Valencia, Valenciana, ES"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Politecnica de Valencia, Valencia, Valenciana, ES","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011926647","display_name":"Leopoldo Armesto","orcid":"https://orcid.org/0000-0003-0979-4428"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Leopoldo Armesto","raw_affiliation_strings":["Universitat Politecnica de Valencia, Valencia, Valenciana, ES"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Politecnica de Valencia, Valencia, Valenciana, ES","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054878413","display_name":"Alicia Esparza","orcid":"https://orcid.org/0000-0002-7471-8686"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alicia Esparza","raw_affiliation_strings":["Universitat Politecnica de Valencia, Valencia, Valenciana, ES"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Politecnica de Valencia, Valencia, Valenciana, ES","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068150910","display_name":"Antonio Sala","orcid":"https://orcid.org/0000-0002-5691-8772"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Sala","raw_affiliation_strings":["Universitat Politecnica de Valencia, Valencia, Valenciana, ES"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Politecnica de Valencia, Valencia, Valenciana, ES","institution_ids":["https://openalex.org/I60053951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60053951"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16358258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"188","last_page":"193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9961000084877014,"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":0.9961000084877014,"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":0.9948999881744385,"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/T10928","display_name":"Probabilistic and Robust Engineering Design","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.766288161277771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7245293259620667},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6694760322570801},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5702883005142212},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5655562877655029},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.522887647151947},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4670383334159851},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.4579128623008728},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34739983081817627},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3393707871437073},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21756097674369812},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20657092332839966}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.766288161277771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245293259620667},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6694760322570801},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5702883005142212},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5655562877655029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.522887647151947},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4670383334159851},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4579128623008728},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34739983081817627},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3393707871437073},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21756097674369812},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20657092332839966},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icosc.2018.8587772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icosc.2018.8587772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 7th International Conference on Systems and Control (ICSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W49891529","https://openalex.org/W164706946","https://openalex.org/W1504480307","https://openalex.org/W1964357740","https://openalex.org/W1977655452","https://openalex.org/W2012587148","https://openalex.org/W2057487175","https://openalex.org/W2101786389","https://openalex.org/W2119717200","https://openalex.org/W2124776405","https://openalex.org/W2137104525","https://openalex.org/W2137226992","https://openalex.org/W2140135625","https://openalex.org/W2162262334","https://openalex.org/W2165726932","https://openalex.org/W2622604310","https://openalex.org/W4205513846","https://openalex.org/W4211049957","https://openalex.org/W4251232855","https://openalex.org/W6680532697","https://openalex.org/W6680657880","https://openalex.org/W6684017535","https://openalex.org/W6738980247"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2742914308","https://openalex.org/W2330004501","https://openalex.org/W2017089693","https://openalex.org/W2703295919"],"abstract_inverted_index":{"Policy":[0],"search":[1],"methods":[2,43],"are":[3],"a":[4],"successful":[5],"approach":[6],"to":[7,12,35,58,64,92],"reinforcement":[8],"learning.":[9],"These":[10],"allow":[11],"learn":[13],"upper-level":[14],"policies":[15],"whose":[16],"main":[17],"advantage":[18],"is":[19,34],"that":[20,48],"these":[21],"distributions":[22],"explore":[23,93],"directly":[24],"in":[25,52,72],"the":[26,50,69,73,83,87,96,99],"parameter":[27],"space.":[28],"The":[29],"contribution":[30],"of":[31,67,86,98],"this":[32,60],"paper":[33],"propose":[36,63],"an":[37,53],"algorithm":[38],"based":[39],"on":[40],"importance":[41,77],"sampling":[42,78],"and":[44],"local":[45,89],"linear":[46,88],"regression":[47],"uses":[49],"samples":[51,71],"efficient":[54],"way.":[55],"In":[56],"order":[57],"get":[59],"aim,":[61],"we":[62,81],"include":[65],"information":[66],"all":[68],"past":[70],"learning":[74],"process":[75],"using":[76],"methods.":[79],"Additionally,":[80],"use":[82],"gradient":[84],"direction":[85],"model":[90],"reward":[91,100],"regions":[94],"where":[95],"prediction":[97],"could":[101],"be":[102],"better.":[103]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}