{"id":"https://openalex.org/W3215437569","doi":"https://doi.org/10.1007/978-3-030-91702-9_3","title":"Gradient Estimation in Model-Based Reinforcement Learning: A Study on Linear Quadratic Environments","display_name":"Gradient Estimation in Model-Based Reinforcement Learning: A Study on Linear Quadratic Environments","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3215437569","doi":"https://doi.org/10.1007/978-3-030-91702-9_3","mag":"3215437569"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-91702-9_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-91702-9_3","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5011476049","display_name":"\u00c2ngelo Greg\u00f3rio Lovatto","orcid":"https://orcid.org/0000-0002-0586-5412"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"\u00c2ngelo Greg\u00f3rio Lovatto","raw_affiliation_strings":["Instituto de Matem\u00e1tica e Estat\u00edstica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"affiliations":[{"raw_affiliation_string":"Instituto de Matem\u00e1tica e Estat\u00edstica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079849725","display_name":"Thiago Pereira Bueno","orcid":"https://orcid.org/0000-0003-1999-9697"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Thiago Pereira Bueno","raw_affiliation_strings":["Instituto de Matem\u00e1tica e Estat\u00edstica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"affiliations":[{"raw_affiliation_string":"Instituto de Matem\u00e1tica e Estat\u00edstica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070668357","display_name":"Leliane Nunes de Barros","orcid":"https://orcid.org/0000-0002-9128-0188"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leliane Nunes de Barros","raw_affiliation_strings":["Instituto de Matem\u00e1tica e Estat\u00edstica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"affiliations":[{"raw_affiliation_string":"Instituto de Matem\u00e1tica e Estat\u00edstica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011476049"],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.3585,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62591926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"47"},"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.991100013256073,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9879999756813049,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6153441071510315},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.5594863295555115},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5334285497665405},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.487806111574173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4095659852027893},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3832508325576782},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.36022308468818665},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3335969150066376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3213112950325012},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16556188464164734},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05302327871322632},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.03860411047935486}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6153441071510315},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.5594863295555115},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5334285497665405},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.487806111574173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4095659852027893},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3832508325576782},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.36022308468818665},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3335969150066376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3213112950325012},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16556188464164734},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05302327871322632},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.03860411047935486},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-91702-9_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-91702-9_3","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W391985582","https://openalex.org/W1906772730","https://openalex.org/W2073384958","https://openalex.org/W2101234009","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2160272666","https://openalex.org/W2523246573","https://openalex.org/W2580909119","https://openalex.org/W2747402019","https://openalex.org/W2754517384","https://openalex.org/W2822752092","https://openalex.org/W2952726221","https://openalex.org/W2970971581","https://openalex.org/W2980016056","https://openalex.org/W2995298643","https://openalex.org/W2995617888","https://openalex.org/W2995894173","https://openalex.org/W2996449210","https://openalex.org/W2996680501","https://openalex.org/W3003257820","https://openalex.org/W3082278101","https://openalex.org/W3082349339","https://openalex.org/W3103145119","https://openalex.org/W4211221179","https://openalex.org/W4241749978","https://openalex.org/W6675354045","https://openalex.org/W6771730547"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2089013912","https://openalex.org/W2145821588"],"abstract_inverted_index":null,"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
