{"id":"https://openalex.org/W2056107746","doi":"https://doi.org/10.1109/humanoids.2014.7041417","title":"Efficient reuse of previous experiences in humanoid motor learning","display_name":"Efficient reuse of previous experiences in humanoid motor learning","publication_year":2014,"publication_date":"2014-11-01","ids":{"openalex":"https://openalex.org/W2056107746","doi":"https://doi.org/10.1109/humanoids.2014.7041417","mag":"2056107746"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2014.7041417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2014.7041417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE-RAS International Conference on Humanoid Robots","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/A5067055140","display_name":"Norikazu Sugimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Norikazu Sugimoto","raw_affiliation_strings":["Department of Center for Information and Neural Networks, National Institute of Information and Communications Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Center for Information and Neural Networks, National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055819776","display_name":"Voot Tangkaratt","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Voot Tangkaratt","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090521498","display_name":"Thijs Wensveen","orcid":null},"institutions":[{"id":"https://openalex.org/I2800939219","display_name":"RIKEN Center for Brain Science","ror":"https://ror.org/04j1n1c04","country_code":"JP","type":"facility","lineage":["https://openalex.org/I2800939219","https://openalex.org/I4210110652"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["JP","NL"],"is_corresponding":false,"raw_author_name":"Thijs Wensveen","raw_affiliation_strings":["Delft University of Technology, Netherlands","Department of Brain Robot Interface, ATR Computational Neuroscience Labs., Japan"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Department of Brain Robot Interface, ATR Computational Neuroscience Labs., Japan","institution_ids":["https://openalex.org/I2800939219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101891226","display_name":"Tingting Zhao","orcid":"https://orcid.org/0000-0001-5915-503X"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Zhao","raw_affiliation_strings":["Tianjin University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University of Science and Technology, China","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072744508","display_name":"Masashi Sugiyama","orcid":"https://orcid.org/0000-0001-6658-6743"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Sugiyama","raw_affiliation_strings":["University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025458882","display_name":"Jun Morimoto","orcid":"https://orcid.org/0000-0002-4115-1919"},"institutions":[{"id":"https://openalex.org/I2800939219","display_name":"RIKEN Center for Brain Science","ror":"https://ror.org/04j1n1c04","country_code":"JP","type":"facility","lineage":["https://openalex.org/I2800939219","https://openalex.org/I4210110652"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Morimoto","raw_affiliation_strings":["Department of Brain Robot Interface, ATR Computational Neuroscience Labs., Japan"],"affiliations":[{"raw_affiliation_string":"Department of Brain Robot Interface, ATR Computational Neuroscience Labs., Japan","institution_ids":["https://openalex.org/I2800939219"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5067055140"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.5562075,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68424283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"554","last_page":"559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9954000115394592,"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/T11685","display_name":"Zebrafish Biomedical Research Applications","score":0.983299970626831,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.8197615146636963},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7995086908340454},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7690322995185852},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.7466475367546082},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6734503507614136},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6491432189941406},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6040636301040649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.521681547164917},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.442035436630249},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3595740795135498},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09781160950660706}],"concepts":[{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.8197615146636963},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7995086908340454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7690322995185852},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.7466475367546082},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6734503507614136},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6491432189941406},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6040636301040649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.521681547164917},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.442035436630249},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3595740795135498},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09781160950660706},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids.2014.7041417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2014.7041417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE-RAS International Conference on Humanoid Robots","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1569296262","https://openalex.org/W1968818868","https://openalex.org/W1969481231","https://openalex.org/W1971492381","https://openalex.org/W1971609423","https://openalex.org/W2045012281","https://openalex.org/W2083456681","https://openalex.org/W2108682071","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2127107099","https://openalex.org/W2130801532","https://openalex.org/W2133224499","https://openalex.org/W2137104525","https://openalex.org/W2138839127","https://openalex.org/W2148053762","https://openalex.org/W2156718681","https://openalex.org/W2165698076","https://openalex.org/W2171277043","https://openalex.org/W2172968643","https://openalex.org/W4214717370","https://openalex.org/W4229739412","https://openalex.org/W6634103402","https://openalex.org/W6676023451","https://openalex.org/W6679257226","https://openalex.org/W6680594301","https://openalex.org/W6682888085"],"related_works":["https://openalex.org/W2745063183","https://openalex.org/W4256317079","https://openalex.org/W2129850190","https://openalex.org/W2295425790","https://openalex.org/W4389009354","https://openalex.org/W1974803039","https://openalex.org/W1991876829","https://openalex.org/W2026275902","https://openalex.org/W2903025760","https://openalex.org/W4289147272"],"abstract_inverted_index":{"In":[0],"this":[1,80],"study,":[2,81],"we":[3,88],"show":[4,131],"that":[5,132],"the":[6,71,75,106,111,155],"motor":[7],"control":[8,50],"performance":[9],"of":[10,74,83,154],"a":[11,23,31,36,90,144],"humanoid":[12,128],"robot":[13,49,107],"can":[14,108,134],"be":[15,64],"improved":[16],"efficiently":[17,109],"using":[18],"its":[19,117],"previous":[20],"experiences":[21],"in":[22,66,79,143],"Reinforcement":[24],"Learning":[25],"(RL)":[26],"framework.":[27],"RL":[28,46,93],"is":[29,51],"becoming":[30],"common":[32],"approach":[33],"to":[34,47,70,115,124],"acquire":[35],"nonlinear":[37],"optimal":[38],"policy":[39,118],"through":[40],"trial":[41],"and":[42,130,139],"error.":[43],"However,":[44],"applying":[45],"real":[48,67,76,127,145],"very":[52],"difficult":[53],"since":[54],"it":[55,133],"usually":[56],"requires":[57],"many":[58,85],"learning":[59,86],"trials.":[60],"Such":[61],"trials":[62],"cannot":[63],"executed":[65],"environments":[68],"due":[69],"limited":[72],"durability":[73],"system.":[77],"Therefore,":[78],"instead":[82],"executing":[84],"trials,":[87],"use":[89],"recently":[91],"developed":[92],"algorithm":[94],"called":[95],"importance-weighted":[96,122],"Policy":[97],"Gradients":[98],"with":[99,104],"Parameter":[100],"based":[101],"Exploration":[102],"(PGPE),":[103],"which":[105],"reuse":[110],"previously":[112],"sampled":[113],"data":[114],"improve":[116],"parameters.":[119],"We":[120],"apply":[121],"PGPE":[123],"CB-i,":[125],"our":[126],"robot,":[129],"learn":[135],"both":[136],"target-reaching":[137],"movement":[138],"cart-pole":[140],"swing-up":[141],"movements":[142],"environment":[146],"within":[147],"10":[148],"minutes":[149],"without":[150],"any":[151,158],"prior":[152],"knowledge":[153],"task":[156],"or":[157],"carefully":[159],"designed":[160],"initial":[161],"trajectory.":[162]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}