{"id":"https://openalex.org/W2910988768","doi":"https://doi.org/10.1109/iros.2018.8594476","title":"Learning and Generalization of Dynamic Movement Primitives by Hierarchical Deep Reinforcement Learning from Demonstration","display_name":"Learning and Generalization of Dynamic Movement Primitives by Hierarchical Deep Reinforcement Learning from Demonstration","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2910988768","doi":"https://doi.org/10.1109/iros.2018.8594476","mag":"2910988768"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8594476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5088068728","display_name":"Wonchul Kim","orcid":"https://orcid.org/0000-0003-2476-1827"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonchul Kim","raw_affiliation_strings":["Faculty of Aerospace and Mechanical Engineering, Seoul National University, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Aerospace and Mechanical Engineering, Seoul National University, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089071024","display_name":"Chungkeun Lee","orcid":"https://orcid.org/0000-0003-1232-0901"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chungkeun Lee","raw_affiliation_strings":["Faculty of Aerospace and Mechanical Engineering, Seoul National University, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Aerospace and Mechanical Engineering, Seoul National University, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044847367","display_name":"Hansom Kim","orcid":"https://orcid.org/0000-0003-1982-3579"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"H. Jin Kim","raw_affiliation_strings":["Faculty of Aerospace and Mechanical Engineering, Seoul National University, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Aerospace and Mechanical Engineering, Seoul National University, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3117","last_page":"3123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9983999729156494,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9769999980926514,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8288031220436096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.712765097618103},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.615140438079834},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6076174378395081},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5975074172019958},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5794668793678284},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5406079292297363},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.4518654942512512},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44589120149612427},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.41984888911247253},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12703275680541992}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8288031220436096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.712765097618103},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.615140438079834},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6076174378395081},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5975074172019958},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5794668793678284},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5406079292297363},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.4518654942512512},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44589120149612427},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41984888911247253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12703275680541992},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2018.8594476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W157454455","https://openalex.org/W1522301498","https://openalex.org/W1592847719","https://openalex.org/W1757796397","https://openalex.org/W1925816294","https://openalex.org/W1952489873","https://openalex.org/W1977655452","https://openalex.org/W2016765487","https://openalex.org/W2071444114","https://openalex.org/W2105546430","https://openalex.org/W2107767097","https://openalex.org/W2109910161","https://openalex.org/W2151975555","https://openalex.org/W2161395589","https://openalex.org/W2167647761","https://openalex.org/W2173248099","https://openalex.org/W2783034017","https://openalex.org/W2919115771","https://openalex.org/W2963262099","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W3005581722","https://openalex.org/W4249441547","https://openalex.org/W4298857966","https://openalex.org/W6606411100","https://openalex.org/W6640290305","https://openalex.org/W6692846177","https://openalex.org/W6703271639"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W3162204513","https://openalex.org/W2045155990","https://openalex.org/W2138720691","https://openalex.org/W4313163053","https://openalex.org/W4362501864","https://openalex.org/W1941703695","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090"],"abstract_inverted_index":{"This":[0,123],"paper":[1],"presents":[2],"an":[3,57],"approach":[4,203,217],"to":[5,41,70,89,93,104,138,150,195],"learn":[6,76],"and":[7,29,75,77,116,177,187,214],"generalize":[8,78],"robotic":[9,63],"skills":[10],"from":[11,34,45,144],"a":[12,25,35,68,109,120,130,145,182,188,191,205,211,219],"demonstration":[13],"using":[14,46],"deep":[15,54,114,155],"reinforcement":[16],"learning":[17,61],"(deep":[18],"RL).":[19],"Dynamic":[20],"Movement":[21],"Primitives":[22],"(DMPs)":[23],"formulate":[24],"nonlinear":[26],"differential":[27,73,158],"equation":[28,159],"produce":[30],"the":[31,62,79,83,90,94,126,134,140,157,197],"observed":[32],"movement":[33,100],"demonstration.":[36],"However,":[37],"it":[38],"is":[39,160,170],"hard":[40],"generate":[42],"new":[43],"behaviors":[44],"DMPs.":[47],"Thus,":[48],"we":[49,66,107,117],"apply":[50,119],"DMPs":[51,86,152],"framework":[52],"into":[53],"RL":[55,115],"as":[56,162],"initial":[58],"setting":[59],"for":[60,113,129],"skills.":[64],"First,":[65],"build":[67],"network":[69],"represent":[71],"this":[72],"equation,":[74],"movements":[80],"by":[81,132],"optimizing":[82],"shape":[84],"of":[85,96,99,165,173],"with":[87,153,210],"respect":[88],"rewards":[91],"up":[92],"end":[95],"each":[97],"sequence":[98],"primitives.":[101],"In":[102,148],"order":[103,149],"do":[105],"this,":[106],"consider":[108],"deterministic":[110],"actor-critic":[111],"algorithm":[112],"also":[118],"hierarchical":[121,154],"strategy.":[122],"drastically":[124],"reduces":[125],"search":[127],"space":[128],"robot":[131],"decomposing":[133],"task,":[135],"which":[136],"allows":[137],"solve":[139],"sparse":[141],"reward":[142],"problem":[143],"complex":[146],"task.":[147,221],"integrate":[151],"RL,":[156],"considered":[161],"temporal":[163],"abstraction":[164],"option.":[166],"The":[167,179],"overall":[168],"structure":[169],"mainly":[171],"composed":[172],"two":[174],"controllers:":[175],"meta-controller":[176,180],"sub-controller.":[178],"learns":[181,190],"policy":[183,192],"over":[184,193],"intrinsic":[185],"goals":[186],"sub-controller":[189],"actions":[194],"accomplish":[196],"given":[198],"goals.":[199],"We":[200],"demonstrate":[201],"our":[202,216],"on":[204],"6":[206],"degree-of-freedom":[207],"(DOF)":[208],"arm":[209],"I-DOF":[212],"gripper":[213],"evaluate":[215],"through":[218],"pick-and-place":[220]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}