{"id":"https://openalex.org/W4405786612","doi":"https://doi.org/10.1109/iros58592.2024.10802000","title":"DecAP : Decaying Action Priors for Accelerated Imitation Learning of Torque-Based Legged Locomotion Policies","display_name":"DecAP : Decaying Action Priors for Accelerated Imitation Learning of Torque-Based Legged Locomotion Policies","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405786612","doi":"https://doi.org/10.1109/iros58592.2024.10802000"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5034933811","display_name":"Shivam Sood","orcid":"https://orcid.org/0000-0001-8188-2065"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shivam Sood","raw_affiliation_strings":["Indian Institute of Technology,Department of Mechanical Engineering,Kharagpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Department of Mechanical Engineering,Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072847443","display_name":"Ge Sun","orcid":"https://orcid.org/0000-0002-0159-1370"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ge Sun","raw_affiliation_strings":["National University of Singapore,Department of Mechanical Engineering,Singapore,117575"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Mechanical Engineering,Singapore,117575","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066556758","display_name":"Peizhuo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Peizhuo Li","raw_affiliation_strings":["National University of Singapore,Department of Mechanical Engineering,Singapore,117575"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Mechanical Engineering,Singapore,117575","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069667034","display_name":"Guillaume Sartoretti","orcid":"https://orcid.org/0000-0002-7579-9916"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Guillaume Sartoretti","raw_affiliation_strings":["National University of Singapore,Department of Mechanical Engineering,Singapore,117575"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Mechanical Engineering,Singapore,117575","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034933811"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":0.5138,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68270873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2809","last_page":"2815"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9965999722480774,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9965999722480774,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.996399998664856,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9912999868392944,"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/torque","display_name":"Torque","score":0.7271775603294373},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.7069680690765381},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.671398401260376},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6075040102005005},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6019774675369263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4742804169654846},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.42820072174072266},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.22037160396575928},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.14716309309005737},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1090826690196991},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.058572202920913696}],"concepts":[{"id":"https://openalex.org/C144171764","wikidata":"https://www.wikidata.org/wiki/Q48103","display_name":"Torque","level":2,"score":0.7271775603294373},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7069680690765381},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.671398401260376},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6075040102005005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6019774675369263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4742804169654846},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.42820072174072266},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.22037160396575928},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.14716309309005737},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1090826690196991},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.058572202920913696},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/iros58592.2024.10802000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":26,"referenced_works":["https://openalex.org/W569084886","https://openalex.org/W2024390895","https://openalex.org/W2157822824","https://openalex.org/W2796290181","https://openalex.org/W2963647792","https://openalex.org/W3164709982","https://openalex.org/W4286423847","https://openalex.org/W4300892751","https://openalex.org/W4383109248","https://openalex.org/W4385756663","https://openalex.org/W4387005676","https://openalex.org/W6680528738","https://openalex.org/W6757380569","https://openalex.org/W6758232801","https://openalex.org/W6787186977","https://openalex.org/W6799860965","https://openalex.org/W6800004206","https://openalex.org/W6801964084","https://openalex.org/W6809847274","https://openalex.org/W6841112233","https://openalex.org/W6845682388","https://openalex.org/W6847063038","https://openalex.org/W6853896040","https://openalex.org/W6854087087","https://openalex.org/W6855724723","https://openalex.org/W7009323136"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2202218907"],"abstract_inverted_index":{"Optimal":[0],"Control":[1],"for":[2,48,106],"legged":[3],"robots":[4],"has":[5,31],"gone":[6],"through":[7],"a":[8,40,85,100,120,168,172,177],"paradigm":[9],"shift":[10],"from":[11,151],"position-based":[12,101,169],"to":[13,17,26,34,43,76,109,123,147,153,171],"torque-based":[14,128,174],"control,":[15],"owing":[16],"the":[18,29,89,104,125,158,165,186],"latter\u2019s":[19],"compliant":[20],"and":[21,71,144],"robust":[22,146],"nature.":[23],"In":[24,88],"parallel":[25],"this":[27],"shift,":[28],"community":[30],"also":[32],"turned":[33],"Deep":[35],"Reinforcement":[36],"Learning":[37],"(DRL)":[38],"as":[39],"promising":[41],"approach":[42,138],"directly":[44],"learn":[45],"locomotion":[46],"policies":[47,129],"complex":[49],"real-life":[50],"tasks.":[51],"However,":[52],"most":[53],"end-to-end":[54],"DRL":[55],"approaches":[56],"still":[57],"operate":[58],"in":[59,65,185],"position":[60],"space,":[61],"mainly":[62],"because":[63],"learning":[64,142],"torque":[66,161],"space":[67],"is":[68,145],"often":[69],"sample-inefficient":[70],"does":[72],"not":[73],"consistently":[74,139],"converge":[75],"natural":[77],"gaits.":[78],"To":[79],"address":[80],"these":[81,149],"challenges,":[82],"we":[83,92],"propose":[84],"two-stage":[86],"framework.":[87],"first":[90],"stage,":[91],"generate":[93],"our":[94,137],"own":[95],"imitation":[96,132,141],"data":[97],"by":[98,131,163],"training":[99],"policy,":[102],"eliminating":[103],"need":[105],"expert":[107],"knowledge":[108],"design":[110],"optimal":[111],"controllers.":[112],"The":[113],"second":[114],"stage":[115],"incorporates":[116],"decaying":[117],"action":[118],"priors,":[119],"novel":[121],"method":[122],"enhance":[124],"exploration":[126],"of":[127,160,167,188],"aided":[130],"rewards.":[133],"We":[134,155],"show":[135],"that":[136],"outperforms":[140],"alone":[143],"scaling":[148],"rewards":[150],"0.1x":[152],"10x.":[154],"further":[156],"validate":[157],"benefits":[159],"control":[162],"comparing":[164],"robustness":[166],"policy":[170,175],"position-assisted":[173],"on":[176],"quadruped":[178],"(Unitree":[179],"Go1)":[180],"without":[181],"any":[182],"domain":[183],"randomization":[184],"form":[187],"external":[189],"disturbances":[190],"during":[191],"training.<sup":[192],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[193],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3</sup>":[194]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}