{"id":"https://openalex.org/W4205089755","doi":"https://doi.org/10.1109/smc52423.2021.9658875","title":"A Model-Based Method for Learning Locomotion Skills from Demonstration","display_name":"A Model-Based Method for Learning Locomotion Skills from Demonstration","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W4205089755","doi":"https://doi.org/10.1109/smc52423.2021.9658875"},"language":"en","primary_location":{"id":"doi:10.1109/smc52423.2021.9658875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc52423.2021.9658875","pdf_url":null,"source":{"id":"https://openalex.org/S4363607761","display_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5073334638","display_name":"Hyunseong Park","orcid":null},"institutions":[{"id":"https://openalex.org/I2801036362","display_name":"Agency for Defense Development","ror":"https://ror.org/05fhe0r85","country_code":"KR","type":"government","lineage":["https://openalex.org/I1327899338","https://openalex.org/I1344042128","https://openalex.org/I2801036362","https://openalex.org/I2801339556"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunseong Park","raw_affiliation_strings":["Agency for Defense Development, Dajeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Agency for Defense Development, Dajeon, South Korea","institution_ids":["https://openalex.org/I2801036362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101535288","display_name":"Suk-Min Yoon","orcid":"https://orcid.org/0000-0002-3523-3221"},"institutions":[{"id":"https://openalex.org/I2801036362","display_name":"Agency for Defense Development","ror":"https://ror.org/05fhe0r85","country_code":"KR","type":"government","lineage":["https://openalex.org/I1327899338","https://openalex.org/I1344042128","https://openalex.org/I2801036362","https://openalex.org/I2801339556"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sukmin Yoon","raw_affiliation_strings":["Agency for Defense Development, Dajeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Agency for Defense Development, Dajeon, South Korea","institution_ids":["https://openalex.org/I2801036362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084700021","display_name":"Yong-Duk Kim","orcid":"https://orcid.org/0009-0005-3017-6095"},"institutions":[{"id":"https://openalex.org/I2801036362","display_name":"Agency for Defense Development","ror":"https://ror.org/05fhe0r85","country_code":"KR","type":"government","lineage":["https://openalex.org/I1327899338","https://openalex.org/I1344042128","https://openalex.org/I2801036362","https://openalex.org/I2801339556"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong-Duk Kim","raw_affiliation_strings":["Agency for Defense Development, Dajeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Agency for Defense Development, Dajeon, South Korea","institution_ids":["https://openalex.org/I2801036362"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2801036362"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19442613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"327","last_page":"332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.7918192148208618},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7492150068283081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7323409914970398},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5820314884185791},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5419801473617554},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4748257100582123},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4507572054862976},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4361991286277771},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4223652780056},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41012144088745117},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.321219801902771},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14083176851272583}],"concepts":[{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.7918192148208618},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7492150068283081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7323409914970398},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5820314884185791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5419801473617554},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4748257100582123},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4507572054862976},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4361991286277771},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4223652780056},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41012144088745117},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.321219801902771},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14083176851272583},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc52423.2021.9658875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc52423.2021.9658875","pdf_url":null,"source":{"id":"https://openalex.org/S4363607761","display_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W2057450058","https://openalex.org/W2095705004","https://openalex.org/W2098774185","https://openalex.org/W2140135625","https://openalex.org/W2144513243","https://openalex.org/W2145339207","https://openalex.org/W2147544021","https://openalex.org/W2268617045","https://openalex.org/W2618017917","https://openalex.org/W2736601468","https://openalex.org/W2738669288","https://openalex.org/W2740210681","https://openalex.org/W2787938642","https://openalex.org/W2890822044","https://openalex.org/W2906643110","https://openalex.org/W2911383979","https://openalex.org/W2952854274","https://openalex.org/W2963277051","https://openalex.org/W2963301010","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2964006217","https://openalex.org/W2964067469","https://openalex.org/W2989988749","https://openalex.org/W2999385649","https://openalex.org/W3022782115","https://openalex.org/W3109547540","https://openalex.org/W3113374047","https://openalex.org/W4287996125","https://openalex.org/W4293396018","https://openalex.org/W4294336468","https://openalex.org/W4295521014","https://openalex.org/W6638018090","https://openalex.org/W6639949747","https://openalex.org/W6674330103","https://openalex.org/W6674884181","https://openalex.org/W6680657880","https://openalex.org/W6681151457","https://openalex.org/W6681478256","https://openalex.org/W6684921986","https://openalex.org/W6718092244","https://openalex.org/W6735913928","https://openalex.org/W6741832191","https://openalex.org/W6748839928","https://openalex.org/W6751087324","https://openalex.org/W6754484421","https://openalex.org/W6756303580","https://openalex.org/W6758568160","https://openalex.org/W6771249860","https://openalex.org/W6771378615"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"While":[0],"Generative":[1],"Adversarial":[2],"Imitation":[3],"Learning":[4],"(GAIL)":[5],"shows":[6],"remarkable":[7],"performance":[8,100],"in":[9,40,61],"many":[10,19],"high":[11],"dimensional":[12],"imitation":[13,119],"learning":[14,120],"tasks,":[15],"it":[16,95],"requires":[17,106],"too":[18],"sampled":[20],"transitions,":[21],"which":[22,109],"are":[23],"infeasible":[24],"for":[25,133],"some":[26],"real":[27],"world":[28],"problems.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,126],"demonstrate":[34],"how":[35],"exploiting":[36],"the":[37,54,75,81,99,102],"reward":[38,56,83],"function":[39,57],"GAIL":[41,152],"can":[42,58,66],"improve":[43],"sample":[44],"efficiency.":[45],"We":[46,140],"design":[47],"our":[48,142],"algorithm":[49,121],"end-to-end":[50,116],"differentiable":[51,117],"so":[52],"that":[53,94],"learned":[55],"directly":[59],"participate":[60],"policy":[62],"updates.":[63],"End-to-end":[64],"differentiability":[65],"be":[67],"achieved":[68],"by":[69],"introducing":[70],"a":[71,87,137],"forward":[72,88,103,138],"model":[73,89,104],"of":[74,80,101,136],"environment,":[76],"enabling":[77],"direct":[78],"calculation":[79],"cumulative":[82],"function.":[84],"However,":[85],"using":[86],"has":[90],"two":[91],"significant":[92],"limitations":[93],"heavily":[96],"relies":[97],"on":[98,157],"and":[105,154],"multi-step":[107],"prediction,":[108],"causes":[110],"severe":[111],"error":[112],"accumulation.":[113],"The":[114],"proposed":[115],"adversarial":[118],"alleviates":[122],"these":[123,146],"limitations.":[124],"Also,":[125],"suggest":[127],"applying":[128],"several":[129],"existing":[130],"regularization":[131,147],"techniques":[132],"robust":[134],"training":[135],"model.":[139],"call":[141],"algorithm,":[143],"integrated":[144],"with":[145],"methods,":[148],"fully":[149],"Differentiable":[150],"Regularized":[151],"(DRGAIL),":[153],"test":[155],"DRGAIL":[156],"continuous":[158],"control":[159],"tasks.":[160]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}