{"id":"https://openalex.org/W3129853634","doi":"https://doi.org/10.1109/iros45743.2020.9341777","title":"Learning Agile Locomotion via Adversarial Training","display_name":"Learning Agile Locomotion via Adversarial Training","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3129853634","doi":"https://doi.org/10.1109/iros45743.2020.9341777","mag":"3129853634"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5100669158","display_name":"Yujin Tang","orcid":"https://orcid.org/0000-0002-0141-7380"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yujin Tang","raw_affiliation_strings":["Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo","Google Brain, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Google Brain, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103241086","display_name":"Jie Tan","orcid":"https://orcid.org/0000-0002-7947-0333"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Tan","raw_affiliation_strings":["Google Brain, Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain, Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042711470","display_name":"Tatsuya Harada","orcid":"https://orcid.org/0000-0002-3712-3691"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Harada","raw_affiliation_strings":["Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8714,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.71475825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6098","last_page":"6105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9818000197410583,"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/T11135","display_name":"Virology and Viral Diseases","score":0.9632999897003174,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.85384601354599},{"id":"https://openalex.org/keywords/agile-software-development","display_name":"Agile software development","score":0.8447393178939819},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.7855491638183594},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7218714952468872},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.68874591588974},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6855369806289673},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6361489295959473},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6022489070892334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5521862506866455},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.47127315402030945},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4112316370010376},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.12009403109550476},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1132156252861023}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.85384601354599},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.8447393178939819},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.7855491638183594},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7218714952468872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.68874591588974},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6855369806289673},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6361489295959473},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6022489070892334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5521862506866455},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.47127315402030945},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4112316370010376},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.12009403109550476},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1132156252861023},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros45743.2020.9341777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W102487131","https://openalex.org/W1528676759","https://openalex.org/W1754506687","https://openalex.org/W1927753533","https://openalex.org/W1966784014","https://openalex.org/W1978102433","https://openalex.org/W1988135991","https://openalex.org/W1991811360","https://openalex.org/W2079533635","https://openalex.org/W2093941824","https://openalex.org/W2098329609","https://openalex.org/W2099618002","https://openalex.org/W2148831627","https://openalex.org/W2156737235","https://openalex.org/W2165150801","https://openalex.org/W2257979135","https://openalex.org/W2290134019","https://openalex.org/W2395575420","https://openalex.org/W2396783599","https://openalex.org/W2420347861","https://openalex.org/W2562736583","https://openalex.org/W2565989828","https://openalex.org/W2584009249","https://openalex.org/W2593412525","https://openalex.org/W2596367596","https://openalex.org/W2602275733","https://openalex.org/W2602963933","https://openalex.org/W2604283518","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2772709170","https://openalex.org/W2787938642","https://openalex.org/W2789525339","https://openalex.org/W2899496413","https://openalex.org/W2911087563","https://openalex.org/W2920329277","https://openalex.org/W2962938168","https://openalex.org/W2963000099","https://openalex.org/W2963184939","https://openalex.org/W2963637944","https://openalex.org/W2963881016","https://openalex.org/W2964338167","https://openalex.org/W2973525135","https://openalex.org/W2977527020","https://openalex.org/W2978148161","https://openalex.org/W2995520132","https://openalex.org/W3003523736","https://openalex.org/W3039737909","https://openalex.org/W3105609823","https://openalex.org/W4210966338","https://openalex.org/W4252284432","https://openalex.org/W4256333068","https://openalex.org/W4295113716","https://openalex.org/W4297810554","https://openalex.org/W4299802797","https://openalex.org/W4302570325","https://openalex.org/W6683195989","https://openalex.org/W6684205842","https://openalex.org/W6712181171","https://openalex.org/W6712348848","https://openalex.org/W6713411898","https://openalex.org/W6733306783","https://openalex.org/W6735641298","https://openalex.org/W6735650757","https://openalex.org/W6735677848","https://openalex.org/W6736622323","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6745190604","https://openalex.org/W6746177919","https://openalex.org/W6748839928","https://openalex.org/W6748929038","https://openalex.org/W6755667589","https://openalex.org/W6767919266","https://openalex.org/W6768731700","https://openalex.org/W6786189056","https://openalex.org/W6841112233","https://openalex.org/W6912248530"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006","https://openalex.org/W4320018150","https://openalex.org/W2918664383","https://openalex.org/W2040808657","https://openalex.org/W4320855730","https://openalex.org/W106056076","https://openalex.org/W2135200719"],"abstract_inverted_index":{"Developing":[0],"controllers":[1],"for":[2,9,122],"agile":[3,82],"locomotion":[4,135],"is":[5,36,120],"a":[6,50,56,116],"long-standing":[7],"challenge":[8],"legged":[10],"robots.":[11],"Reinforcement":[12],"learning":[13,52],"(RL)":[14],"and":[15,32],"Evolution":[16],"Strategy":[17],"(ES)":[18],"hold":[19],"the":[20,24,67,88,123,134],"promise":[21],"of":[22,27,109,112],"automating":[23],"design":[25,39,91],"process":[26,78],"such":[28],"controllers.":[29],"However,":[30],"dedicated":[31],"careful":[33],"human":[34],"effort":[35],"required":[37],"to":[38,42,61,70,95,125],"training":[40,77,106,140],"environments":[41],"promote":[43],"agility.":[44,127],"In":[45,93],"this":[46,75],"paper,":[47],"we":[48,103,131],"present":[49],"multi-agent":[51],"system,":[53],"in":[54,115],"which":[55,113],"quadruped":[57],"robot":[58,64],"(protagonist)":[59],"learns":[60,69],"chase":[62],"another":[63],"(adversary)":[65],"while":[66],"latter":[68],"escape.":[71],"We":[72],"find":[73,104],"that":[74,98,105,133],"adversarial":[76,139],"not":[79],"only":[80,100],"encourages":[81],"behaviors":[83],"but":[84],"also":[85],"effectively":[86],"alleviates":[87],"laborious":[89],"environment":[90],"effort.":[92],"contrast":[94],"prior":[96],"works":[97],"used":[99],"one":[101],"adversary,":[102],"an":[107],"ensemble":[108],"adversaries,":[110],"each":[111],"specializes":[114],"different":[117],"escaping":[118],"strategy,":[119],"essential":[121],"protagonist":[124],"master":[126],"Through":[128],"extensive":[129],"experiments,":[130],"show":[132],"controller":[136],"learned":[137],"with":[138],"significantly":[141],"outperforms":[142],"carefully":[143],"designed":[144],"baselines.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}