{"id":"https://openalex.org/W2771827793","doi":"https://doi.org/10.1109/iros.2017.8206343","title":"Data-efficient control policy search using residual dynamics learning","display_name":"Data-efficient control policy search using residual dynamics learning","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2771827793","doi":"https://doi.org/10.1109/iros.2017.8206343","mag":"2771827793"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2017.8206343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8206343","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/A5031898170","display_name":"Matteo Saveriano","orcid":"https://orcid.org/0000-0002-9784-3973"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Matteo Saveriano","raw_affiliation_strings":["Human-centered Assistive Robotics, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Human-centered Assistive Robotics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032943305","display_name":"Yuchao Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yuchao Yin","raw_affiliation_strings":["Human-centered Assistive Robotics, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Human-centered Assistive Robotics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076700669","display_name":"Pietro Falco","orcid":"https://orcid.org/0000-0003-1133-0884"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pietro Falco","raw_affiliation_strings":["Human-centered Assistive Robotics, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Human-centered Assistive Robotics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088081800","display_name":"Dongheui Lee","orcid":"https://orcid.org/0000-0003-1897-7664"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dongheui Lee","raw_affiliation_strings":["Human-centered Assistive Robotics, Technical University of Munich, Munich, Germany","Institute of Robotics and Mechatronics, German Aerospace Center (DLR), Germany"],"affiliations":[{"raw_affiliation_string":"Human-centered Assistive Robotics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute of Robotics and Mechatronics, German Aerospace Center (DLR), Germany","institution_ids":["https://openalex.org/I2898391981"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031898170"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":5.1911,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.96375503,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4709","last_page":"4715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9980999827384949,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9980999827384949,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996999979019165,"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/T11236","display_name":"Control Systems and Identification","score":0.9914000034332275,"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/computer-science","display_name":"Computer science","score":0.7348144054412842},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7084096074104309},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6898539066314697},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5763189196586609},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.566959798336029},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.46753498911857605},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4609096646308899},{"id":"https://openalex.org/keywords/system-dynamics","display_name":"System dynamics","score":0.4433102011680603},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.42695870995521545},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3859831690788269},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30554717779159546},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2957935929298401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27594029903411865},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15822511911392212}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7348144054412842},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7084096074104309},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6898539066314697},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5763189196586609},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.566959798336029},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.46753498911857605},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4609096646308899},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.4433102011680603},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.42695870995521545},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3859831690788269},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30554717779159546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2957935929298401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27594029903411865},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15822511911392212},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros.2017.8206343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8206343","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"},{"id":"pmh:oai:elib.dlr.de:117916","is_oa":false,"landing_page_url":"https://elib.dlr.de/117916/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196266","display_name":"elib (German Aerospace Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2898391981","host_organization_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","host_organization_lineage":["https://openalex.org/I2898391981"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzbeitrag"},{"id":"pmh:oai:iris.unitn.it:11572/331051","is_oa":false,"landing_page_url":"http://hdl.handle.net/11572/331051","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:www.research.unipd.it:11577/3513841","is_oa":false,"landing_page_url":"https://hdl.handle.net/11577/3513841","pdf_url":null,"source":{"id":"https://openalex.org/S4377196283","display_name":"Research Padua  Archive (University of Padua)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1540685400","https://openalex.org/W1575312501","https://openalex.org/W1583182920","https://openalex.org/W1746819321","https://openalex.org/W1925816294","https://openalex.org/W1973102501","https://openalex.org/W1977655452","https://openalex.org/W2012392077","https://openalex.org/W2018705428","https://openalex.org/W2072752020","https://openalex.org/W2113265921","https://openalex.org/W2117629901","https://openalex.org/W2120630110","https://openalex.org/W2121103318","https://openalex.org/W2126683783","https://openalex.org/W2137488229","https://openalex.org/W2139769245","https://openalex.org/W2167117957","https://openalex.org/W2179284380","https://openalex.org/W3005581722","https://openalex.org/W4211049957","https://openalex.org/W4214717370","https://openalex.org/W6632235069","https://openalex.org/W6640290305","https://openalex.org/W6653435097","https://openalex.org/W6678367057","https://openalex.org/W6678621847","https://openalex.org/W6680880767"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,40,92],"propose":[4],"a":[5,46,62,74,79],"model-based":[6],"and":[7,24,57,99,124,136,144],"data":[8,43],"efficient":[9],"approach":[10,149],"for":[11,139,163],"reinforcement":[12],"learning.":[13],"The":[14,65,83,118],"main":[15],"idea":[16],"of":[17,49,120,154],"our":[18,148],"algorithm":[19],"is":[20,86,102,106,115,128],"to":[21,27,44,78,130,137,157],"combine":[22],"simulated":[23],"real":[25,98,113,133,165],"rollouts":[26,36,155],"efficiently":[28],"find":[29,158],"an":[30,140,159],"optimal":[31,141,160],"control":[32,161],"policy.":[33,142],"While":[34],"performing":[35],"on":[37],"the":[38,50,54,58,95,112,121,125,132,152,164],"robot,":[39],"exploit":[41],"sensory":[42],"learn":[45],"probabilistic":[47],"model":[48,67,101,123],"residual":[51,84],"difference":[52,85,96],"between":[53,97],"measured":[55],"state":[56,59],"predicted":[60],"by":[61],"simplified":[63,66,100],"model.":[64],"can":[68],"be":[69],"any":[70],"dynamical":[71],"system,":[72],"from":[73],"very":[75],"accurate":[76],"system":[77,114,134],"simple,":[80],"linear":[81],"one.":[82],"learned":[87,126],"with":[88],"Gaussian":[89,103,116],"processes.":[90],"Hence,":[91],"assume":[93],"that":[94,111,147],"distributed,":[104],"which":[105],"less":[107],"strict":[108],"than":[109],"assuming":[110],"distributed.":[117],"combination":[119],"partial":[122],"residuals":[127],"exploited":[129],"predict":[131],"behavior":[135],"search":[138],"Simulations":[143],"experiments":[145],"show":[146],"significantly":[150],"reduces":[151],"number":[153],"needed":[156],"policy":[162],"system.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}