{"id":"https://openalex.org/W2772449134","doi":"https://doi.org/10.1177/0278364917743795","title":"Learning manipulation skills from a single demonstration","display_name":"Learning manipulation skills from a single demonstration","publication_year":2017,"publication_date":"2017-12-05","ids":{"openalex":"https://openalex.org/W2772449134","doi":"https://doi.org/10.1177/0278364917743795","mag":"2772449134"},"language":"en","primary_location":{"id":"doi:10.1177/0278364917743795","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364917743795","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","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/A5110458164","display_name":"P\u00e9ter Englert","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Peter Englert","raw_affiliation_strings":["Machine Learning & Robotics Lab, University of Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Machine Learning & Robotics Lab, University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065672819","display_name":"Marc Toussaint","orcid":"https://orcid.org/0000-0002-5487-6767"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marc Toussaint","raw_affiliation_strings":["Machine Learning & Robotics Lab, University of Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Machine Learning & Robotics Lab, University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110458164"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":3.822,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.9375718,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"37","issue":"1","first_page":"137","last_page":"154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9976000189781189,"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/leverage","display_name":"Leverage (statistics)","score":0.7439737319946289},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.7399052381515503},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6704772114753723},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6512866020202637},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.63312828540802},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5741254687309265},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.530673086643219},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.5101702213287354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4810074269771576},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.4745795726776123},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4389127194881439},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4334111213684082},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4326733350753784},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1510191261768341}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7439737319946289},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.7399052381515503},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6704772114753723},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6512866020202637},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.63312828540802},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5741254687309265},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.530673086643219},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.5101702213287354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4810074269771576},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.4745795726776123},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4389127194881439},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4334111213684082},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4326733350753784},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1510191261768341},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0278364917743795","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364917743795","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W202805564","https://openalex.org/W770013183","https://openalex.org/W1483202606","https://openalex.org/W1491420040","https://openalex.org/W1499669280","https://openalex.org/W1517508454","https://openalex.org/W1518336263","https://openalex.org/W1588959569","https://openalex.org/W1701825639","https://openalex.org/W1746819321","https://openalex.org/W1824348304","https://openalex.org/W1925816294","https://openalex.org/W1977655452","https://openalex.org/W1986014385","https://openalex.org/W1994648061","https://openalex.org/W1999874108","https://openalex.org/W2012204020","https://openalex.org/W2012392077","https://openalex.org/W2041242313","https://openalex.org/W2053936014","https://openalex.org/W2061144551","https://openalex.org/W2061562262","https://openalex.org/W2062525454","https://openalex.org/W2063741856","https://openalex.org/W2063987138","https://openalex.org/W2085627234","https://openalex.org/W2098774185","https://openalex.org/W2099201756","https://openalex.org/W2100235553","https://openalex.org/W2100484286","https://openalex.org/W2104733512","https://openalex.org/W2105947986","https://openalex.org/W2112036188","https://openalex.org/W2117675763","https://openalex.org/W2120034667","https://openalex.org/W2121863487","https://openalex.org/W2134491302","https://openalex.org/W2143346970","https://openalex.org/W2156734147","https://openalex.org/W2157826563","https://openalex.org/W2169209873","https://openalex.org/W2317988884","https://openalex.org/W2474696542","https://openalex.org/W2529601334","https://openalex.org/W2610753682","https://openalex.org/W2743603832","https://openalex.org/W2783425358","https://openalex.org/W2950465931","https://openalex.org/W2962803570","https://openalex.org/W2963280855","https://openalex.org/W2964161785","https://openalex.org/W2983690517","https://openalex.org/W2990138404","https://openalex.org/W3029645440","https://openalex.org/W3104073816","https://openalex.org/W4211049957","https://openalex.org/W4214717370","https://openalex.org/W4251727044","https://openalex.org/W4256361765","https://openalex.org/W4293775970"],"related_works":["https://openalex.org/W2393022482","https://openalex.org/W2377346130","https://openalex.org/W2361092061","https://openalex.org/W3106461837","https://openalex.org/W2319775965","https://openalex.org/W2357314690","https://openalex.org/W4306904969","https://openalex.org/W2191886813","https://openalex.org/W2768698792","https://openalex.org/W4387225845"],"abstract_inverted_index":{"We":[0,143],"consider":[1],"the":[2,44,52,65,86,89,146],"scenario":[3],"where":[4],"a":[5,9,18,39,124,133,152],"robot":[6],"is":[7,37,130],"demonstrated":[8],"manipulation":[10,35],"skill":[11,36,126],"once":[12],"and":[13,29,75,97,115,137],"should":[14],"then":[15],"use":[16],"only":[17],"few":[19],"trials":[20],"on":[21,85,132,148],"its":[22],"own":[23],"to":[24,26,50,63,95,103,111,121],"learn":[25],"reproduce,":[27],"optimize,":[28],"generalize":[30],"that":[31],"same":[32],"skill.":[33],"A":[34],"generally":[38],"high-dimensional":[40],"policy.":[41],"To":[42],"achieve":[43],"desired":[45],"sample":[46],"efficiency,":[47],"we":[48,61],"need":[49],"exploit":[51],"inherent":[53],"structure":[54],"in":[55],"this":[56],"problem.":[57],"With":[58],"our":[59],"approach,":[60],"propose":[62],"decompose":[64],"problem":[66],"into":[67],"analytically":[68],"known":[69],"objectives,":[70,77,106,114],"such":[71,78],"as":[72,79],"motion":[73],"smoothness,":[74],"black-box":[76,113],"trial":[80],"success":[81],"or":[82],"reward,":[83],"depending":[84],"interaction":[87],"with":[88,139,151],"environment.":[90],"The":[91,128],"decomposition":[92],"allows":[93],"us":[94],"leverage":[96],"combine":[98],"(i)":[99],"constrained":[100,108],"optimization":[101,110],"methods":[102,120],"address":[104],"analytic":[105],"(ii)":[107],"Bayesian":[109],"explore":[112],"(iii)":[116],"inverse":[117],"optimal":[118],"control":[119],"eventually":[122],"extract":[123],"generalizable":[125],"representation.":[127],"algorithm":[129],"evaluated":[131],"synthetic":[134],"benchmark":[135],"experiment":[136],"compared":[138],"state-of-the-art":[140],"learning":[141],"methods.":[142],"also":[144],"demonstrate":[145],"performance":[147],"real-robot":[149],"experiments":[150],"PR2.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}