{"id":"https://openalex.org/W4390591052","doi":"https://doi.org/10.1109/lra.2024.3349934","title":"Learning Locomotion for Quadruped Robots via Distributional Ensemble Actor-Critic","display_name":"Learning Locomotion for Quadruped Robots via Distributional Ensemble Actor-Critic","publication_year":2024,"publication_date":"2024-01-04","ids":{"openalex":"https://openalex.org/W4390591052","doi":"https://doi.org/10.1109/lra.2024.3349934"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3349934","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2024.3349934","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/7339444/10380686.pdf","source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/7083369/7339444/10380686.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061527315","display_name":"Sicen Li","orcid":"https://orcid.org/0000-0002-2049-8921"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sicen Li","raw_affiliation_strings":["College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-2049-8921","affiliations":[{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106426681","display_name":"Yiming Pang","orcid":"https://orcid.org/0000-0003-1307-2700"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Pang","raw_affiliation_strings":["College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-1307-2700","affiliations":[{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101956364","display_name":"Panju Bai","orcid":"https://orcid.org/0009-0008-0316-7590"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Panju Bai","raw_affiliation_strings":["College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0008-0316-7590","affiliations":[{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106428144","display_name":"Jiawei Li","orcid":"https://orcid.org/0009-0007-0695-0196"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Li","raw_affiliation_strings":["College of Shipbuilding Engineering, Harbin Engineering University, Harbin, China","College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0007-0695-0196","affiliations":[{"raw_affiliation_string":"College of Shipbuilding Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077903464","display_name":"Zhaojin Liu","orcid":"https://orcid.org/0009-0006-0313-1868"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaojin Liu","raw_affiliation_strings":["College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0006-0313-1868","affiliations":[{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082401388","display_name":"Shihao Hu","orcid":"https://orcid.org/0009-0003-8287-0279"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihao Hu","raw_affiliation_strings":["College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0003-8287-0279","affiliations":[{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101910810","display_name":"Liquan Wang","orcid":"https://orcid.org/0000-0002-6470-4889"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liquan Wang","raw_affiliation_strings":["College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-6470-4889","affiliations":[{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100367342","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0002-0741-9838"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["College of Shipbuilding Engineering, Harbin Engineering University, Harbin, China","College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-0741-9838","affiliations":[{"raw_affiliation_string":"College of Shipbuilding Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"College of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5061527315"],"corresponding_institution_ids":["https://openalex.org/I151727225"],"apc_list":null,"apc_paid":null,"fwci":4.6359,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.95089786,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"9","issue":"2","first_page":"1811","last_page":"1818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9933000206947327,"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":0.9933000206947327,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9886999726295471,"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"}},{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9692000150680542,"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/robot","display_name":"Robot","score":0.6381491422653198},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6372986435890198},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.6026376485824585},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5886942148208618},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5680496096611023},{"id":"https://openalex.org/keywords/terrain","display_name":"Terrain","score":0.4870636761188507},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43900784850120544},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.42858976125717163},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.41953253746032715},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4144189953804016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40014055371284485},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3985653221607208},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3396851420402527},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22677645087242126},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2233113944530487},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0821588933467865}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6381491422653198},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6372986435890198},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.6026376485824585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5886942148208618},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5680496096611023},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.4870636761188507},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43900784850120544},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.42858976125717163},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.41953253746032715},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4144189953804016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40014055371284485},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3985653221607208},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3396851420402527},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22677645087242126},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2233113944530487},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0821588933467865},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3349934","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2024.3349934","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/7339444/10380686.pdf","source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lra.2024.3349934","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2024.3349934","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/7339444/10380686.pdf","source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1949792850","display_name":null,"funder_award_id":"YQ2020E028","funder_id":"https://openalex.org/F4320323085","funder_display_name":"Natural Science Foundation of Heilongjiang Province"}],"funders":[{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390591052.pdf","grobid_xml":"https://content.openalex.org/works/W4390591052.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2411824964","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2765302304","https://openalex.org/W2889693550","https://openalex.org/W2963184939","https://openalex.org/W2972810470","https://openalex.org/W3088310808","https://openalex.org/W3093922502","https://openalex.org/W3100366369","https://openalex.org/W3104876774","https://openalex.org/W3120778962","https://openalex.org/W3175254947","https://openalex.org/W4205430897","https://openalex.org/W4226143977","https://openalex.org/W4283787029","https://openalex.org/W4377825225","https://openalex.org/W4382365373","https://openalex.org/W4389665940","https://openalex.org/W4401416328","https://openalex.org/W6616173779","https://openalex.org/W6640174482","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6751629939","https://openalex.org/W6767112054","https://openalex.org/W6767334564","https://openalex.org/W6767349745","https://openalex.org/W6776730770","https://openalex.org/W6780571964","https://openalex.org/W6789305357","https://openalex.org/W6791208179","https://openalex.org/W6793715182","https://openalex.org/W6802227391","https://openalex.org/W6966301428"],"related_works":["https://openalex.org/W2377402383","https://openalex.org/W4294690775","https://openalex.org/W4389574494","https://openalex.org/W4200195314","https://openalex.org/W2156329176","https://openalex.org/W4226458444","https://openalex.org/W3213331859","https://openalex.org/W4390637946","https://openalex.org/W2909067415","https://openalex.org/W4226082913"],"abstract_inverted_index":{"Domain":[0],"randomization":[1,108],"introduces":[2],"perturbations":[3,30],"in":[4,105],"the":[5,13,62,84,96,102,106,123],"simulation":[6,92],"to":[7,12,34,125],"make":[8],"controllers":[9],"less":[10],"susceptible":[11],"reality":[14],"gap,":[15],"which":[16],"enables":[17],"remarkable":[18],"sim-to-real":[19],"transfer":[20],"on":[21,115],"real":[22],"quadruped":[23],"robots.":[24],"However,":[25],"aleatoric":[26],"uncertainty":[27,78],"originating":[28],"from":[29],"could":[31],"often":[32],"lead":[33],"suboptimal":[35],"controllers.":[36],"In":[37],"this":[38],"work,":[39],"we":[40],"present":[41],"a":[42,57],"novel":[43],"algorithm":[44],"called":[45],"Distributional":[46,72],"Ensemble":[47],"Actor-Critic":[48],"(DEAC)":[49],"that":[50,95],"blends":[51],"three":[52],"ideas:":[53],"distributional":[54],"representation":[55,73],"of":[56,61,67,83],"critic,":[58],"lower":[59,81],"bounds":[60,82],"value":[63,85],"distribution,":[64],"and":[65,70,74,122,134],"ensembling":[66,75],"multiple":[68],"critics":[69],"actors.":[71],"provide":[76],"reasonable":[77],"estimates,":[79],"while":[80],"distribution":[86],"offer":[87],"finer-grained":[88],"error":[89],"control.":[90],"The":[91,110],"results":[93],"show":[94],"controller":[97,112],"trained":[98,111],"by":[99],"DEAC":[100],"outperforms":[101],"other":[103],"baselines":[104],"domain":[107],"setting.":[109],"is":[113],"deployed":[114],"an":[116],"A1-like":[117],"robot,":[118],"demonstrating":[119],"high-speed":[120],"running":[121],"ability":[124],"traverse":[126],"diverse":[127],"terrains":[128],"such":[129],"as":[130],"slippery":[131],"plates,":[132],"grassland,":[133],"wet":[135],"dirt.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
