{"id":"https://openalex.org/W3040408533","doi":"https://doi.org/10.15607/rss.2020.xvi.053","title":"Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning","display_name":"Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning","publication_year":2020,"publication_date":"2020-06-30","ids":{"openalex":"https://openalex.org/W3040408533","doi":"https://doi.org/10.15607/rss.2020.xvi.053","mag":"3040408533"},"language":"en","primary_location":{"id":"doi:10.15607/rss.2020.xvi.053","is_oa":true,"landing_page_url":"https://doi.org/10.15607/rss.2020.xvi.053","pdf_url":"https://doi.org/10.15607/rss.2020.xvi.053","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics: Science and Systems XVI","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.15607/rss.2020.xvi.053","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033189369","display_name":"Archit Sharma","orcid":"https://orcid.org/0000-0001-9487-1576"},"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"]},{"id":"https://openalex.org/I4210106247","display_name":"Corvallis Environmental Center","ror":"https://ror.org/01kdb6822","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210106247"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Archit Sharma","raw_affiliation_strings":["Robotics: Science and Systems Corvalis, Oregon, USA","Google Research"],"affiliations":[{"raw_affiliation_string":"Robotics: Science and Systems Corvalis, Oregon, USA","institution_ids":["https://openalex.org/I4210106247"]},{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050964166","display_name":"Michael J. Ahn","orcid":"https://orcid.org/0000-0002-4018-8584"},"institutions":[{"id":"https://openalex.org/I4210106247","display_name":"Corvallis Environmental Center","ror":"https://ror.org/01kdb6822","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210106247"]},{"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":"Michael Ahn","raw_affiliation_strings":["Robotics: Science and Systems Corvalis, Oregon, USA","Google Research"],"affiliations":[{"raw_affiliation_string":"Robotics: Science and Systems Corvalis, Oregon, USA","institution_ids":["https://openalex.org/I4210106247"]},{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743"},"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"]},{"id":"https://openalex.org/I4210106247","display_name":"Corvallis Environmental Center","ror":"https://ror.org/01kdb6822","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210106247"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["Robotics: Science and Systems Corvalis, Oregon, USA","Google Research"],"affiliations":[{"raw_affiliation_string":"Robotics: Science and Systems Corvalis, Oregon, USA","institution_ids":["https://openalex.org/I4210106247"]},{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101582321","display_name":"Vikash Kumar","orcid":"https://orcid.org/0000-0003-0284-0823"},"institutions":[{"id":"https://openalex.org/I4210106247","display_name":"Corvallis Environmental Center","ror":"https://ror.org/01kdb6822","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210106247"]},{"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":"Vikash Kumar","raw_affiliation_strings":["Robotics: Science and Systems Corvalis, Oregon, USA","Google Research"],"affiliations":[{"raw_affiliation_string":"Robotics: Science and Systems Corvalis, Oregon, USA","institution_ids":["https://openalex.org/I4210106247"]},{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088777896","display_name":"Karol Hausman","orcid":"https://orcid.org/0000-0002-1504-6197"},"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"]},{"id":"https://openalex.org/I4210106247","display_name":"Corvallis Environmental Center","ror":"https://ror.org/01kdb6822","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210106247"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karol Hausman","raw_affiliation_strings":["Robotics: Science and Systems Corvalis, Oregon, USA","Google Research"],"affiliations":[{"raw_affiliation_string":"Robotics: Science and Systems Corvalis, Oregon, USA","institution_ids":["https://openalex.org/I4210106247"]},{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061613634","display_name":"Shixiang Gu","orcid":null},"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"]},{"id":"https://openalex.org/I4210106247","display_name":"Corvallis Environmental Center","ror":"https://ror.org/01kdb6822","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210106247"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shixiang Gu","raw_affiliation_strings":["Robotics: Science and Systems Corvalis, Oregon, USA","Google Research"],"affiliations":[{"raw_affiliation_string":"Robotics: Science and Systems Corvalis, Oregon, USA","institution_ids":["https://openalex.org/I4210106247"]},{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5033189369"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210106247"],"apc_list":null,"apc_paid":null,"fwci":2.05603368,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88455843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.996399998664856,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9922000169754028,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8431792855262756},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6365230083465576},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.618220329284668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4867837131023407}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8431792855262756},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6365230083465576},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.618220329284668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4867837131023407}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.15607/rss.2020.xvi.053","is_oa":true,"landing_page_url":"https://doi.org/10.15607/rss.2020.xvi.053","pdf_url":"https://doi.org/10.15607/rss.2020.xvi.053","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics: Science and Systems XVI","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.15607/rss.2020.xvi.053","is_oa":true,"landing_page_url":"https://doi.org/10.15607/rss.2020.xvi.053","pdf_url":"https://doi.org/10.15607/rss.2020.xvi.053","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics: Science and Systems XVI","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3040408533.pdf","grobid_xml":"https://content.openalex.org/works/W3040408533.grobid-xml"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W59183349","https://openalex.org/W166862392","https://openalex.org/W200118319","https://openalex.org/W1514587017","https://openalex.org/W1515851193","https://openalex.org/W1554318634","https://openalex.org/W1556824961","https://openalex.org/W1863227302","https://openalex.org/W1977655452","https://openalex.org/W1999874108","https://openalex.org/W2000514530","https://openalex.org/W2004303440","https://openalex.org/W2012392077","https://openalex.org/W2034806191","https://openalex.org/W2074499097","https://openalex.org/W2083954950","https://openalex.org/W2098774185","https://openalex.org/W2106469529","https://openalex.org/W2109910161","https://openalex.org/W2111967991","https://openalex.org/W2127412976","https://openalex.org/W2139053308","https://openalex.org/W2181068523","https://openalex.org/W2290354866","https://openalex.org/W2340679559","https://openalex.org/W2411690432","https://openalex.org/W2416041116","https://openalex.org/W2419612459","https://openalex.org/W2575705757","https://openalex.org/W2606433045","https://openalex.org/W2614839826","https://openalex.org/W2620671107","https://openalex.org/W2626804490","https://openalex.org/W2769541360","https://openalex.org/W2781726626","https://openalex.org/W2803281228","https://openalex.org/W2810785043","https://openalex.org/W2883433335","https://openalex.org/W2902298341","https://openalex.org/W2904246096","https://openalex.org/W2907537824","https://openalex.org/W2949604932","https://openalex.org/W2950268955","https://openalex.org/W2950471160","https://openalex.org/W2950614095","https://openalex.org/W2953326529","https://openalex.org/W2954142106","https://openalex.org/W2962730405","https://openalex.org/W2962802563","https://openalex.org/W2963276097","https://openalex.org/W2963438456","https://openalex.org/W2963523627","https://openalex.org/W2963674921","https://openalex.org/W2963780574","https://openalex.org/W2963864421","https://openalex.org/W2964227312","https://openalex.org/W2988072049","https://openalex.org/W2995058766","https://openalex.org/W3020712699","https://openalex.org/W3028821797","https://openalex.org/W3031634197","https://openalex.org/W3035717769","https://openalex.org/W4288102901","https://openalex.org/W4288289109","https://openalex.org/W4288363736","https://openalex.org/W4297795006","https://openalex.org/W4298101950","https://openalex.org/W4298857966","https://openalex.org/W4321392130"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2358668433","https://openalex.org/W2138720691","https://openalex.org/W3203657119","https://openalex.org/W4286952720"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,7,16,50,95,110],"provides":[2,106],"a":[3,20,28,73],"general":[4],"framework":[5],"for":[6,31,65,91,162],"robotic":[8],"skills":[9,55,64,136,154],"while":[10],"minimizing":[11],"engineering":[12],"effort.However,":[13],"most":[14],"reinforcement":[15,49,94],"algorithms":[17],"assume":[18],"that":[19,32,52,72,102,134,151],"well-designed":[21],"reward":[22,34,36,58],"function":[23],"is":[24],"provided,":[25],"and":[26,60,123,140],"learn":[27],"single":[29,33],"behavior":[30],"function.Such":[35],"functions":[37],"can":[38,80,155],"be":[39,81,156],"difficult":[40],"to":[41],"design":[42],"in":[43,96,109],"practice.Can":[44],"we":[45,70,100,117,132],"instead":[46],"develop":[47],"efficient":[48,85],"methods":[51],"acquire":[53],"diverse":[54,138],"without":[56,144,165],"any":[57,145,166],"function,":[59],"then":[61],"re-purpose":[62],"these":[63],"downstream":[66],"tasks?In":[67],"this":[68],"paper,":[69],"demonstrate":[71,150],"recently":[74],"proposed":[75,104],"unsupervised":[76,93],"skill":[77],"discovery":[78],"algorithm":[79,105,126],"extended":[82],"into":[83],"an":[84],"off-policy":[86],"method,":[87],"making":[88,112],"it":[89],"suitable":[90],"performing":[92],"the":[97,120,125,152],"real":[98,128],"world.Firstly,":[99],"show":[101],"our":[103],"substantial":[107],"improvement":[108],"efficiency,":[111],"rewardfree":[113],"real-world":[114],"training":[115],"feasible.Secondly,":[116],"move":[118],"beyond":[119],"simulation":[121],"environments":[122],"evaluate":[124],"on":[127],"physical":[129],"hardware.On":[130],"quadrupeds,":[131],"observe":[133],"locomotion":[135],"with":[137],"gaits":[139],"different":[141],"orientations":[142],"emerge":[143],"rewards":[146],"or":[147],"demonstrations.We":[148],"also":[149],"learned":[153],"composed":[157],"using":[158],"model":[159],"predictive":[160],"control":[161],"goal-oriented":[163],"navigation,":[164],"additional":[167],"training.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}