{"id":"https://openalex.org/W2604883922","doi":"https://doi.org/10.1109/iros.2017.8202137","title":"Black-box data-efficient policy search for robotics","display_name":"Black-box data-efficient policy search for robotics","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2604883922","doi":"https://doi.org/10.1109/iros.2017.8202137","mag":"2604883922"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2017.8202137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8202137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5048630321","display_name":"Konstantinos Chatzilygeroudis","orcid":"https://orcid.org/0000-0003-3585-1027"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Konstantinos Chatzilygeroudis","raw_affiliation_strings":["CNRS, UMR 7503, France","Inria, France","Universit\u00e9 de Lorraine, UMR 7503, France"],"affiliations":[{"raw_affiliation_string":"CNRS, UMR 7503, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838"]},{"raw_affiliation_string":"Inria, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Universit\u00e9 de Lorraine, UMR 7503, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016804536","display_name":"Roberto Rama","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Roberto Rama","raw_affiliation_strings":["CNRS, UMR 7503, France","Inria, France","Universit\u00e9 de Lorraine, UMR 7503, France"],"affiliations":[{"raw_affiliation_string":"CNRS, UMR 7503, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838"]},{"raw_affiliation_string":"Inria, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Universit\u00e9 de Lorraine, UMR 7503, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072492839","display_name":"Rituraj Kaushik","orcid":"https://orcid.org/0000-0003-2598-8804"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Rituraj Kaushik","raw_affiliation_strings":["CNRS, UMR 7503, France","Inria, France","Universit\u00e9 de Lorraine, UMR 7503, France"],"affiliations":[{"raw_affiliation_string":"CNRS, UMR 7503, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838"]},{"raw_affiliation_string":"Inria, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Universit\u00e9 de Lorraine, UMR 7503, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045083917","display_name":"Dorian Goepp","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dorian Goepp","raw_affiliation_strings":["CNRS, UMR 7503, France","Inria, France","Universit\u00e9 de Lorraine, UMR 7503, France"],"affiliations":[{"raw_affiliation_string":"CNRS, UMR 7503, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838"]},{"raw_affiliation_string":"Inria, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Universit\u00e9 de Lorraine, UMR 7503, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021954539","display_name":"Vassilis Vassiliades","orcid":"https://orcid.org/0000-0002-1336-5629"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vassilis Vassiliades","raw_affiliation_strings":["CNRS, UMR 7503, France","Inria, France","Universit\u00e9 de Lorraine, UMR 7503, France"],"affiliations":[{"raw_affiliation_string":"CNRS, UMR 7503, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838"]},{"raw_affiliation_string":"Inria, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Universit\u00e9 de Lorraine, UMR 7503, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032227198","display_name":"Jean-Baptiste Mouret","orcid":"https://orcid.org/0000-0002-2513-027X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Baptiste Mouret","raw_affiliation_strings":["CNRS, UMR 7503, France","Inria, France","Universit\u00e9 de Lorraine, UMR 7503, France"],"affiliations":[{"raw_affiliation_string":"CNRS, UMR 7503, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838"]},{"raw_affiliation_string":"Inria, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Universit\u00e9 de Lorraine, UMR 7503, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048630321"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210121838","https://openalex.org/I90183372"],"apc_list":null,"apc_paid":null,"fwci":9.344,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.98252297,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9945999979972839,"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":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.7283152341842651},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6865069270133972},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6598355770111084},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6488654017448425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6030384302139282},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5841016173362732},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5548292398452759},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.550902783870697},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4867551326751709},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4333757758140564},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4217599630355835},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4105321764945984},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3436490297317505},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3290417194366455},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17228785157203674}],"concepts":[{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.7283152341842651},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6865069270133972},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6598355770111084},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6488654017448425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6030384302139282},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5841016173362732},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5548292398452759},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.550902783870697},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4867551326751709},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4333757758140564},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4217599630355835},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4105321764945984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3436490297317505},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3290417194366455},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17228785157203674},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2017.8202137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8202137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W582134693","https://openalex.org/W770013183","https://openalex.org/W1483202606","https://openalex.org/W1579744901","https://openalex.org/W1601974704","https://openalex.org/W1738827650","https://openalex.org/W1746819321","https://openalex.org/W1911299338","https://openalex.org/W1925816294","https://openalex.org/W1949804828","https://openalex.org/W1950970151","https://openalex.org/W1972063518","https://openalex.org/W1993131108","https://openalex.org/W1997543377","https://openalex.org/W2012392077","https://openalex.org/W2012587148","https://openalex.org/W2018705428","https://openalex.org/W2028678875","https://openalex.org/W2041851440","https://openalex.org/W2085627234","https://openalex.org/W2097263684","https://openalex.org/W2104578628","https://openalex.org/W2108114251","https://openalex.org/W2112036188","https://openalex.org/W2116468180","https://openalex.org/W2119717200","https://openalex.org/W2121103318","https://openalex.org/W2125612430","https://openalex.org/W2130105540","https://openalex.org/W2134911466","https://openalex.org/W2139053308","https://openalex.org/W2145339207","https://openalex.org/W2151965738","https://openalex.org/W2156106639","https://openalex.org/W2162717641","https://openalex.org/W2192203593","https://openalex.org/W2536782980","https://openalex.org/W2552644168","https://openalex.org/W2919115771","https://openalex.org/W2949536823","https://openalex.org/W2963179241","https://openalex.org/W2964059111","https://openalex.org/W3005581722","https://openalex.org/W3007384386","https://openalex.org/W4205513846","https://openalex.org/W4211049957","https://openalex.org/W4232090110","https://openalex.org/W4299604521","https://openalex.org/W6617145748","https://openalex.org/W6622391652","https://openalex.org/W6629021139","https://openalex.org/W6635991215","https://openalex.org/W6640290305","https://openalex.org/W6643267832","https://openalex.org/W6676576766","https://openalex.org/W6678367057","https://openalex.org/W6682262322"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4385437088"],"abstract_inverted_index":{"The":[0,151],"most":[1],"data-efficient":[2,126,132],"algorithms":[3,63,68],"for":[4,131],"reinforcement":[5],"learning":[6],"(RL)":[7],"in":[8,134],"robotics":[9],"are":[10,64,119,149],"based":[11],"on":[12,111,181],"uncertain":[13],"dynamical":[14,23],"models:":[15],"after":[16],"each":[17],"episode,":[18],"they":[19,29],"first":[20],"learn":[21],"a":[22,36,92,162,190,195],"model":[24,45,171],"of":[25,73,83,177],"the":[26,40,44,81,84,112,116,128,157,170,175],"robot,":[27],"then":[28],"use":[30],"an":[31],"optimization":[32,55,159],"algorithm":[33,130,160,165,180],"to":[34,155],"find":[35],"policy":[37,117],"that":[38,53,166],"maximizes":[39],"expected":[41],"return":[42],"given":[43],"and":[46,76,136,189],"its":[47],"uncertainties.":[48,172],"It":[49],"is":[50,124,138,154],"often":[51],"believed":[52],"this":[54,88],"can":[56],"be":[57],"tractable":[58],"only":[59],"if":[60],"analytical,":[61],"gradient-based":[62,158],"used;":[65],"however,":[66],"these":[67],"require":[69],"using":[70],"specific":[71],"families":[72],"reward":[74,113],"functions":[75],"policies,":[77],"which":[78],"greatly":[79],"limits":[80],"flexibility":[82],"overall":[85],"approach.":[86],"In":[87],"paper,":[89],"we":[90],"introduce":[91],"novel":[93],"model-based":[94],"RL":[95,133],"algorithm,":[96],"called":[97],"Black-DROPS":[98],"(Black-box":[99],"Data-efficient":[100],"RObot":[101],"Policy":[102],"Search)":[103],"that:":[104],"(1)":[105],"does":[106],"not":[107],"impose":[108],"any":[109],"constraint":[110],"function":[114],"or":[115],"(they":[118],"treated":[120],"as":[121,125,127,139],"black-boxes),":[122],"(2)":[123],"state-of-the-art":[129],"robotics,":[135],"(3)":[137],"fast":[140],"(or":[141],"faster)":[142],"than":[143],"analytical":[144],"approaches":[145],"when":[146],"several":[147],"cores":[148],"available.":[150],"key":[152],"idea":[153],"replace":[156],"with":[161],"parallel,":[163],"black-box":[164],"takes":[167],"into":[168],"account":[169],"We":[173],"demonstrate":[174],"performance":[176],"our":[178],"new":[179],"two":[182],"standard":[183],"control":[184],"benchmark":[185],"problems":[186],"(in":[187],"simulation)":[188],"low-cost":[191],"robotic":[192],"manipulator":[193],"(with":[194],"real":[196],"robot).":[197]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}