{"id":"https://openalex.org/W2968717280","doi":"https://doi.org/10.1109/icra.2019.8793864","title":"Using Deep Reinforcement Learning to Learn High-Level Policies on the ATRIAS Biped","display_name":"Using Deep Reinforcement Learning to Learn High-Level Policies on the ATRIAS Biped","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2968717280","doi":"https://doi.org/10.1109/icra.2019.8793864","mag":"2968717280"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8793864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8793864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","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/A5100379461","display_name":"Tianyu Li","orcid":"https://orcid.org/0000-0003-2531-8253"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyu Li","raw_affiliation_strings":["Mechanical Engineenng, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mechanical Engineenng, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078844630","display_name":"Hartmut Geyer","orcid":"https://orcid.org/0000-0003-3238-3299"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hartmut Geyer","raw_affiliation_strings":["Robotics Institute, School of Computer Science, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, School of Computer Science, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055330939","display_name":"Christopher G. Atkeson","orcid":"https://orcid.org/0000-0003-4265-8452"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher G. Atkeson","raw_affiliation_strings":["Robotics Institute, School of Computer Science, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, School of Computer Science, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007198769","display_name":"Akshara Rai","orcid":"https://orcid.org/0009-0005-5767-9848"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Akshara Rai","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6397,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.96709675,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"263","last_page":"269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9941999912261963,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9832000136375427,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8239256143569946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7580921649932861},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6374011635780334},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6225025653839111},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5646419525146484},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5269078612327576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48880264163017273},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4500664472579956},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.42101776599884033},{"id":"https://openalex.org/keywords/evolutionary-robotics","display_name":"Evolutionary robotics","score":0.4168645739555359},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.40176713466644287},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10300642251968384}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8239256143569946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580921649932861},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6374011635780334},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6225025653839111},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5646419525146484},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5269078612327576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48880264163017273},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4500664472579956},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.42101776599884033},{"id":"https://openalex.org/C199505168","wikidata":"https://www.wikidata.org/wiki/Q3267529","display_name":"Evolutionary robotics","level":3,"score":0.4168645739555359},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.40176713466644287},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10300642251968384},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2019.8793864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8793864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1602448039","https://openalex.org/W1738827650","https://openalex.org/W1771410628","https://openalex.org/W1979146515","https://openalex.org/W2051228319","https://openalex.org/W2142641780","https://openalex.org/W2158782408","https://openalex.org/W2161427949","https://openalex.org/W2173248099","https://openalex.org/W2205975260","https://openalex.org/W2257979135","https://openalex.org/W2415959992","https://openalex.org/W2607198029","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2962749646","https://openalex.org/W2963090983","https://openalex.org/W2963184939","https://openalex.org/W2963277051","https://openalex.org/W2963411833","https://openalex.org/W2963647792","https://openalex.org/W2963864421","https://openalex.org/W2990747716","https://openalex.org/W3101442004","https://openalex.org/W4295549420","https://openalex.org/W4297687493","https://openalex.org/W6638018090","https://openalex.org/W6680724558","https://openalex.org/W6684921986","https://openalex.org/W6718092244","https://openalex.org/W6734129231","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6741361698","https://openalex.org/W6743747171","https://openalex.org/W6744563498","https://openalex.org/W6770858630"],"related_works":["https://openalex.org/W2381850946","https://openalex.org/W4380449851","https://openalex.org/W3125091513","https://openalex.org/W4318832338","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W4381586542"],"abstract_inverted_index":{"Learning":[0],"controllers":[1,33,48,74],"for":[2,34,79],"bipedal":[3,82],"robots":[4],"is":[5,115,127],"a":[6,44,110,116,119,248],"challenging":[7],"problem,":[8],"often":[9],"requiring":[10],"expert":[11,144,256],"knowledge":[12],"and":[13,55,105,138,172,182,189,199,213,232],"extensive":[14],"tuning":[15],"of":[16,61,71,102,118,133,159,168,186,195,229,239,250,262],"parameters":[17],"that":[18,49,149,204],"vary":[19],"in":[20,37,92,129,161,211],"different":[21],"situations.":[22],"Recently,":[23],"deep":[24],"reinforcement":[25],"learning":[26,32,47,160],"has":[27,40,219],"shown":[28],"promise":[29],"at":[30],"automatically":[31],"complex":[35],"systems":[36],"simulation.":[38],"This":[39,218],"been":[41],"followed":[42],"by":[43,142],"push":[45],"towards":[46],"can":[50,67,94,139,153,207],"be":[51,95,140,209],"transferred":[52,96],"between":[53,170,197],"simulation":[54,93,171,198,212],"hardware,":[56],"primarily":[57],"with":[58,99],"the":[59,69,100,124,131,134,143,157,184,193,223,226,230,233,237,240],"use":[60,101],"domain":[62,65],"randomization.":[63],"However,":[64],"randomization":[66],"make":[68],"problem":[70],"finding":[72],"stable":[73],"even":[75],"more":[76,120],"challenging,":[77],"especially":[78],"under":[80],"actuated":[81],"robots.":[83],"In":[84,243],"this":[85,151,244],"work,":[86],"we":[87,246],"explore":[88,183],"whether":[89],"policies":[90,169,206],"learned":[91,128,210],"to":[97,254],"hardware":[98,216],"high-fidelity":[103],"simulators":[104],"structured":[106,121,205],"controllers.":[107],"We":[108,147,174],"learn":[109],"neural":[111,125,234,252],"network":[112,126,235],"policy":[113],"which":[114],"part":[117],"controller.":[122],"While":[123],"simulation,":[130,162],"rest":[132],"controller":[135],"stays":[136],"fixed,":[137],"tuned":[141],"as":[145,163,165,222],"needed.":[146],"show":[148,203],"using":[150,251],"approach":[152],"greatly":[154],"speed":[155],"up":[156],"rate":[158,194],"well":[164],"enable":[166],"transfer":[167,196],"hardware.":[173,200],"present":[175],"our":[176],"results":[177,202],"on":[178,192,215],"an":[179],"ATRIAS":[180],"robot":[181],"effect":[185],"action":[187],"spaces":[188],"cost":[190],"functions":[191],"Our":[201],"indeed":[208],"implemented":[214],"successfully.":[217],"several":[220],"advantages,":[221],"structure":[224],"preserves":[225],"intuitive":[227],"nature":[228],"policy,":[231],"improves":[236],"performance":[238],"hand-designed":[241],"policy.":[242],"way,":[245],"propose":[247],"way":[249],"networks":[253],"improve":[255],"designed":[257],"controllers,":[258],"while":[259],"maintaining":[260],"ease":[261],"understanding.":[263]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}