{"id":"https://openalex.org/W2147828974","doi":"https://doi.org/10.1109/ichr.2010.5686320","title":"Reinforcement learning of full-body humanoid motor skills","display_name":"Reinforcement learning of full-body humanoid motor skills","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2147828974","doi":"https://doi.org/10.1109/ichr.2010.5686320","mag":"2147828974"},"language":"en","primary_location":{"id":"doi:10.1109/ichr.2010.5686320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichr.2010.5686320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 10th IEEE-RAS International Conference on Humanoid Robots","raw_type":"proceedings-article"},"type":"conference-paper","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/A5017689065","display_name":"Freek Stulp","orcid":"https://orcid.org/0000-0001-9555-9517"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Freek Stulp","raw_affiliation_strings":["Computational Learning and Motor Control Lab, University of Southern California, Los Angeles, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Learning and Motor Control Lab, University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077279214","display_name":"Jonas Buchli","orcid":"https://orcid.org/0000-0001-7494-8492"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonas Buchli","raw_affiliation_strings":["Computational Learning and Motor Control Lab, University of Southern California, Los Angeles, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Learning and Motor Control Lab, University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044505993","display_name":"Evangelos A. Theodorou","orcid":"https://orcid.org/0000-0002-0834-5738"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evangelos Theodorou","raw_affiliation_strings":["Computational Learning and Motor Control Lab, University of Southern California, Los Angeles, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Learning and Motor Control Lab, University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029642293","display_name":"Stefan Schaal","orcid":"https://orcid.org/0000-0001-5660-1874"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Schaal","raw_affiliation_strings":["Computational Learning and Motor Control Lab, University of Southern California, Los Angeles, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Learning and Motor Control Lab, University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"405","last_page":"410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10879","display_name":"Robotic Locomotion and Control","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.9980000257492065,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9926999807357788,"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":0.8321582078933716},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.7159104943275452},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5832576155662537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5602862238883972},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5077832341194153},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3929932117462158}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8321582078933716},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.7159104943275452},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5832576155662537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5602862238883972},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5077832341194153},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3929932117462158},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ichr.2010.5686320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichr.2010.5686320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 10th IEEE-RAS International Conference on Humanoid Robots","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.395.9508","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.395.9508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ensta-paristech.fr/~stulp/publications/pdfs/stulp10reinforcement.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"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":18,"referenced_works":["https://openalex.org/W1586251222","https://openalex.org/W1925816294","https://openalex.org/W1967377907","https://openalex.org/W1971609423","https://openalex.org/W1978023077","https://openalex.org/W2107464055","https://openalex.org/W2110304639","https://openalex.org/W2114171536","https://openalex.org/W2121863487","https://openalex.org/W2137808289","https://openalex.org/W2161872510","https://openalex.org/W2167117957","https://openalex.org/W2250331966","https://openalex.org/W2295809278","https://openalex.org/W2323447981","https://openalex.org/W4205362845","https://openalex.org/W4214717370","https://openalex.org/W6697583374"],"related_works":["https://openalex.org/W2745063183","https://openalex.org/W2129850190","https://openalex.org/W4256317079","https://openalex.org/W2295425790","https://openalex.org/W1991876829","https://openalex.org/W4389009354","https://openalex.org/W1974803039","https://openalex.org/W2088677124","https://openalex.org/W1589423663","https://openalex.org/W2143454724"],"abstract_inverted_index":{"Applying":[0],"reinforcement":[1,27,53],"learning":[2,28,54,105],"to":[3,41,116],"humanoid":[4,124],"robots":[5],"is":[6,57,96,114],"challenging":[7],"because":[8],"humanoids":[9],"have":[10],"a":[11,36,51,83,122],"large":[12],"number":[13],"of":[14,16,39,62,130,143],"degrees":[15],"freedom":[17],"and":[18,20,34,66,98,151],"state":[19],"action":[21],"spaces":[22],"are":[23,157],"continuous.":[24],"Thus,":[25],"most":[26],"algorithms":[29],"would":[30],"become":[31],"computationally":[32],"infeasible":[33],"require":[35],"prohibitive":[37],"amount":[38],"trials":[40],"explore":[42],"such":[43],"high-dimensional":[44],"spaces.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,133],"present":[50],"probabilistic":[52],"approach,":[55,132],"which":[56],"derived":[58],"from":[59],"the":[60,93,128,141],"framework":[61],"stochastic":[63],"optimal":[64],"control":[65],"path":[67],"integrals.":[68],"The":[69],"algorithm,":[70],"called":[71],"Policy":[72],"Improvement":[73],"with":[74],"Path":[75],"Integrals":[76],"(PI":[77],"<sup":[78,111,137],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[79,112,138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[80,113,139],"),":[81],"has":[82,87],"surprisingly":[84],"simple":[85],"form,":[86],"no":[88],"open":[89],"tuning":[90],"parameters":[91],"besides":[92],"exploration":[94],"noise,":[95],"model-free,":[97],"performs":[99],"numerically":[100],"robustly":[101],"in":[102,140],"high":[103],"dimensional":[104],"problems.":[106],"We":[107],"demonstrate":[108,127],"how":[109],"PI":[110,136],"able":[115],"learn":[117],"full-body":[118],"motor":[119],"skills":[120],"on":[121],"34-DOF":[123],"robot.":[125],"To":[126],"generality":[129],"our":[131],"also":[134],"apply":[135],"context":[142],"variable":[144],"impedance":[145],"control,":[146],"where":[147],"both":[148],"planned":[149],"trajectories":[150],"gain":[152],"schedules":[153],"for":[154],"each":[155],"joint":[156],"optimized":[158],"simultaneously.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}