{"id":"https://openalex.org/W4385756663","doi":"https://doi.org/10.1109/lra.2023.3304561","title":"Torque-Based Deep Reinforcement Learning for Task-and-Robot Agnostic Learning on Bipedal Robots Using Sim-to-Real Transfer","display_name":"Torque-Based Deep Reinforcement Learning for Task-and-Robot Agnostic Learning on Bipedal Robots Using Sim-to-Real Transfer","publication_year":2023,"publication_date":"2023-08-11","ids":{"openalex":"https://openalex.org/W4385756663","doi":"https://doi.org/10.1109/lra.2023.3304561"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3304561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3304561","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041763219","display_name":"Donghyeon Kim","orcid":"https://orcid.org/0000-0002-9549-8758"},"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":"Donghyeon Kim","raw_affiliation_strings":["Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-9549-8758","affiliations":[{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045351810","display_name":"Glen Berseth","orcid":"https://orcid.org/0000-0001-7351-8028"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Glen Berseth","raw_affiliation_strings":["Université de Montréal, Quebec, Canada"],"raw_orcid":"https://orcid.org/0000-0001-7351-8028","affiliations":[{"raw_affiliation_string":"Université de Montréal, Quebec, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087352737","display_name":"Mathew Schwartz","orcid":"https://orcid.org/0000-0003-3662-7203"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mathew Schwartz","raw_affiliation_strings":["College of Architecture and Design, New Jersey Institute of Technology, Newark, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0003-3662-7203","affiliations":[{"raw_affiliation_string":"College of Architecture and Design, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031070386","display_name":"Jaeheung Park","orcid":"https://orcid.org/0000-0002-5062-8264"},"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"]},{"id":"https://openalex.org/I4210120602","display_name":"Advanced Institute of Convergence Technology","ror":"https://ror.org/01w62yz22","country_code":"KR","type":"facility","lineage":["https://openalex.org/I139264467","https://openalex.org/I4210120602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeheung Park","raw_affiliation_strings":["Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea","ASRI, RICS, Seoul National University, Seoul, Republic of Korea","Advanced Institutes and Advanced Institutes of Convergence Technology (AICT), Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-5062-8264","affiliations":[{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"ASRI, RICS, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Advanced Institutes and Advanced Institutes of Convergence Technology (AICT), Suwon, Republic of Korea","institution_ids":["https://openalex.org/I4210120602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6292,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.82367338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"8","issue":"10","first_page":"6251","last_page":"6258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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/T11685","display_name":"Zebrafish Biomedical Research Applications","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8573588132858276},{"id":"https://openalex.org/keywords/torque","display_name":"Torque","score":0.7539930939674377},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.740946888923645},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6675289869308472},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6219163537025452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5553923845291138},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5290419459342957},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4954768419265747},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4890631139278412},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45101669430732727},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41224104166030884},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.37443122267723083},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3453747630119324},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2363225519657135}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8573588132858276},{"id":"https://openalex.org/C144171764","wikidata":"https://www.wikidata.org/wiki/Q48103","display_name":"Torque","level":2,"score":0.7539930939674377},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.740946888923645},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6675289869308472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6219163537025452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5553923845291138},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5290419459342957},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4954768419265747},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4890631139278412},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45101669430732727},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41224104166030884},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.37443122267723083},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3453747630119324},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2363225519657135},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3304561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3304561","pdf_url":null,"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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5400000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2014505645","https://openalex.org/W2015149365","https://openalex.org/W2119088038","https://openalex.org/W2157822824","https://openalex.org/W2295584263","https://openalex.org/W2736601468","https://openalex.org/W2767050701","https://openalex.org/W2788030459","https://openalex.org/W2796290181","https://openalex.org/W2890302476","https://openalex.org/W2911087563","https://openalex.org/W2963184939","https://openalex.org/W3093922502","https://openalex.org/W3101442004","https://openalex.org/W3104515094","https://openalex.org/W3104876774","https://openalex.org/W3112664346","https://openalex.org/W3175254947","https://openalex.org/W3206804182","https://openalex.org/W3207491493","https://openalex.org/W4300892751","https://openalex.org/W4312869615","https://openalex.org/W4313563011","https://openalex.org/W4313563049","https://openalex.org/W4390481291","https://openalex.org/W6741002519","https://openalex.org/W6778428183","https://openalex.org/W6842936555"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"In":[0],"this":[1],"letter,":[2],"we":[3,94],"review":[4],"the":[5,58,82,96,102,114],"question":[6],"of":[7,88,119],"which":[8],"action":[9,70],"space":[10,71],"is":[11,54],"best":[12,59],"suited":[13],"for":[14,49,109],"controlling":[15],"a":[16,68,120,127],"real":[17,128],"biped":[18,130],"robot":[19],"in":[20],"combination":[21],"with":[22,44,76],"Sim2Real":[23],"training.":[24],"Position":[25],"control":[26],"has":[27,32],"been":[28,33],"popular":[29],"as":[30],"it":[31],"shown":[34],"to":[35,42,56,104],"be":[36],"more":[37],"sample":[38],"efficient":[39],"and":[40,80],"intuitive":[41],"combine":[43],"other":[45],"planning":[46],"algorithms.":[47],"However,":[48],"position":[50],"control,":[51],"gain":[52],"tuning":[53,79],"required":[55],"achieve":[57],"possible":[60],"policy":[61,103,125],"performance.":[62],"We":[63],"show":[64],"that,":[65],"instead,":[66],"using":[67],"torque-based":[69,121],"enables":[72],"task-and-robot":[73],"agnostic":[74],"learning":[75,124],"less":[77],"parameter":[78],"mitigates":[81],"sim-to-reality":[83],"gap":[84],"by":[85,100,107],"taking":[86],"advantage":[87],"torque":[89],"control's":[90],"inherent":[91],"compliance.":[92],"Also,":[93],"accelerate":[95],"torque-based-policy":[97],"training":[98],"process":[99],"pre-training":[101],"remain":[105],"upright":[106],"compensating":[108],"gravity.":[110],"The":[111],"letter":[112],"showcases":[113],"first":[115],"successful":[116],"sim-to-real":[117],"transfer":[118],"deep":[122],"reinforcement":[123],"on":[126],"human-sized":[129],"robot.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2023-08-12T00:00:00"}