{"id":"https://openalex.org/W2569188472","doi":"https://doi.org/10.1109/humanoids.2016.7803277","title":"Reinforcement learning for improving imitated in-contact skills","display_name":"Reinforcement learning for improving imitated in-contact skills","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W2569188472","doi":"https://doi.org/10.1109/humanoids.2016.7803277","mag":"2569188472"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2016.7803277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2016.7803277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/files/33081455/ELEC_Hazara_etal_Reinforcement_Learning_for_Improving_Humanoids_2016.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047209845","display_name":"Murtaza Hazara","orcid":"https://orcid.org/0000-0003-0477-3767"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Murtaza Hazara","raw_affiliation_strings":["School of Electrical Engineering, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080940147","display_name":"Ville Kyrki","orcid":"https://orcid.org/0000-0002-5230-5549"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Kyrki","raw_affiliation_strings":["School of Electrical Engineering, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047209845"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":1.6194,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.85714964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"194","last_page":"201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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":0.9998999834060669,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.9991000294685364,"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/T10982","display_name":"Motor Control and Adaptation","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7615178823471069},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7482755780220032},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7234560251235962},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6684466600418091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6479424238204956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5284758806228638},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41135239601135254},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15677857398986816}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7615178823471069},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7482755780220032},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7234560251235962},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6684466600418091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6479424238204956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5284758806228638},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41135239601135254},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15677857398986816},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":2,"locations":[{"id":"doi:10.1109/humanoids.2016.7803277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2016.7803277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/23806","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/78f4dae7-7175-4d08-88e1-b8c3feabcbe6","pdf_url":"https://research.aalto.fi/files/33081455/ELEC_Hazara_etal_Reinforcement_Learning_for_Improving_Humanoids_2016.pdf","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/23806","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/78f4dae7-7175-4d08-88e1-b8c3feabcbe6","pdf_url":"https://research.aalto.fi/files/33081455/ELEC_Hazara_etal_Reinforcement_Learning_for_Improving_Humanoids_2016.pdf","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2569188472.pdf","grobid_xml":"https://content.openalex.org/works/W2569188472.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W101508493","https://openalex.org/W1489248927","https://openalex.org/W1555368087","https://openalex.org/W1581870850","https://openalex.org/W1670925118","https://openalex.org/W1851340573","https://openalex.org/W1925816294","https://openalex.org/W1972572518","https://openalex.org/W1984037069","https://openalex.org/W1987516463","https://openalex.org/W1999549166","https://openalex.org/W2016765264","https://openalex.org/W2035813292","https://openalex.org/W2041242313","https://openalex.org/W2064173399","https://openalex.org/W2100235553","https://openalex.org/W2110304639","https://openalex.org/W2120772693","https://openalex.org/W2125079768","https://openalex.org/W2149860990","https://openalex.org/W2156174987","https://openalex.org/W2162000109","https://openalex.org/W2217041877","https://openalex.org/W2219608386","https://openalex.org/W3005581722","https://openalex.org/W4237733001","https://openalex.org/W6604114042","https://openalex.org/W6640290305","https://openalex.org/W6682093400"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4323768008","https://openalex.org/W1941703695","https://openalex.org/W2903025760","https://openalex.org/W4289147272","https://openalex.org/W3213722473","https://openalex.org/W2110944602","https://openalex.org/W3196817267"],"abstract_inverted_index":{"Although":[0],"motor":[1],"primitives":[2],"(MPs)":[3],"for":[4,36,90,144],"trajectory-based":[5,65],"skills":[6],"have":[7,33,81,176],"been":[8,15],"studied":[9],"extensively,":[10],"much":[11],"less":[12],"attention":[13],"has":[14],"devoted":[16],"to":[17,32,55],"studying":[18],"in-contact":[19,39,46,79,93],"tasks.":[20],"With":[21],"robots":[22],"becoming":[23],"more":[24,60],"commonplace,":[25],"it":[26,67],"is":[27,58],"both":[28,73,114],"economical":[29],"and":[30,75,99,119],"convenient":[31],"a":[34,53,56,64,69,88,96,107,163,182],"mechanism":[35],"learning":[37],"an":[38,45,92],"task":[40],"from":[41,52,95],"demonstration.":[42],"However,":[43],"transferring":[44,63],"skill":[47,94],"such":[48],"as":[49],"wood":[50,164],"planing":[51,165],"human":[54,97],"robot":[57],"significantly":[59],"challenging":[61],"than":[62],"skill;":[66],"requires":[68],"simultaneous":[70],"control":[71],"of":[72,155,162,185],"pose":[74],"force.":[76],"Furthermore,":[77],"some":[78],"tasks":[80],"extremely":[82],"complex":[83],"contact":[84,122],"environments.":[85],"We":[86],"present":[87],"framework":[89,112],"imitating":[91],"demonstration":[98],"automatically":[100],"enhancing":[101],"the":[102,115,116,120,146,153,160,173,178],"imitated":[103,147,179],"force":[104,123,148],"profile":[105],"using":[106,124],"policy":[108,180],"search":[109],"method.":[110],"The":[111],"encodes":[113],"demonstrated":[117],"trajectory":[118],"normal":[121],"Dynamic":[125],"Movement":[126],"Primitives":[127],"(DMPs).":[128],"In":[129],"experiments,":[130],"we":[131],"utilize":[132],"Policy":[133],"Improvement":[134],"with":[135],"Path":[136],"Integral":[137],"(PI":[138],"<sup":[139],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[140],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[141],")":[142],"algorithm":[143],"updating":[145],"policy.":[149],"Our":[150],"results":[151],"demonstrate":[152],"effectiveness":[154],"this":[156],"approach":[157],"in":[158],"improving":[159],"performance":[161],"task.":[166],"After":[167],"only":[168],"two":[169],"update":[170],"rounds,":[171],"all":[172],"updated":[174],"policies":[175],"outperformed":[177],"at":[181],"significance":[183],"level":[184],"P":[186],"<;":[187],"0.001.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5}],"updated_date":"2026-05-01T08:36:08.643496","created_date":"2025-10-10T00:00:00"}