{"id":"https://openalex.org/W3152791938","doi":"https://doi.org/10.1109/icra48506.2021.9561384","title":"Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention","display_name":"Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3152791938","doi":"https://doi.org/10.1109/icra48506.2021.9561384","mag":"3152791938"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.11203","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017906439","display_name":"Abhishek Gupta","orcid":"https://orcid.org/0000-0003-1117-325X"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Gupta","raw_affiliation_strings":["UC Berkeley","UC Berkeley#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley#TAB#","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101440767","display_name":"Justin Yu","orcid":"https://orcid.org/0009-0006-3683-878X"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Yu","raw_affiliation_strings":["UC Berkeley","UC Berkeley#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley#TAB#","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041306134","display_name":"Tony Z. Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tony Z. Zhao","raw_affiliation_strings":["UC Berkeley","UC Berkeley#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley#TAB#","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101582318","display_name":"Vikash Kumar","orcid":"https://orcid.org/0000-0001-6422-6066"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikash Kumar","raw_affiliation_strings":["University of Washington","University of Washington ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045672280","display_name":"Aaron Rovinsky","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron Rovinsky","raw_affiliation_strings":["UC Berkeley","UC Berkeley#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley#TAB#","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060717631","display_name":"Kelvin Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kelvin Xu","raw_affiliation_strings":["UC Berkeley","UC Berkeley#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley#TAB#","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109989928","display_name":"T. Devlin","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Devlin","raw_affiliation_strings":["UC Berkeley","UC Berkeley#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley#TAB#","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["UC Berkeley","UC Berkeley#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley#TAB#","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2172,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78206884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6664","last_page":"6671"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998000264167786,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.967199981212616,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reset","display_name":"Reset (finance)","score":0.8916821479797363},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7794840335845947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7440732717514038},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7337753772735596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5902029275894165},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5189194679260254},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.467507928609848},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4503523111343384},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4455804228782654},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4158300757408142},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3711807131767273},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11053338646888733},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.09630656242370605}],"concepts":[{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.8916821479797363},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7794840335845947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440732717514038},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7337753772735596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5902029275894165},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5189194679260254},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.467507928609848},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4503523111343384},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4455804228782654},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4158300757408142},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3711807131767273},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11053338646888733},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.09630656242370605},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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":4,"locations":[{"id":"doi:10.1109/icra48506.2021.9561384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.11203","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.11203","pdf_url":"https://arxiv.org/pdf/2104.11203","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3152791938","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2104.11203","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.11203","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.11203","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.11203","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.11203","pdf_url":"https://arxiv.org/pdf/2104.11203","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3152791938.pdf","grobid_xml":"https://content.openalex.org/works/W3152791938.grobid-xml"},"referenced_works_count":95,"referenced_works":["https://openalex.org/W770013183","https://openalex.org/W1969074599","https://openalex.org/W2019165997","https://openalex.org/W2021927715","https://openalex.org/W2073408938","https://openalex.org/W2112036576","https://openalex.org/W2126909264","https://openalex.org/W2129629060","https://openalex.org/W2156737235","https://openalex.org/W2161273941","https://openalex.org/W2161697934","https://openalex.org/W2201912979","https://openalex.org/W2210408922","https://openalex.org/W2221677593","https://openalex.org/W2416041116","https://openalex.org/W2473208550","https://openalex.org/W2528734395","https://openalex.org/W2529573675","https://openalex.org/W2552241273","https://openalex.org/W2584377191","https://openalex.org/W2592538810","https://openalex.org/W2603088459","https://openalex.org/W2624871570","https://openalex.org/W2726187156","https://openalex.org/W2734960757","https://openalex.org/W2753818635","https://openalex.org/W2769541360","https://openalex.org/W2789805345","https://openalex.org/W2796290181","https://openalex.org/W2810785043","https://openalex.org/W2885163910","https://openalex.org/W2890538051","https://openalex.org/W2899205164","https://openalex.org/W2904246096","https://openalex.org/W2951456741","https://openalex.org/W2953326529","https://openalex.org/W2954970763","https://openalex.org/W2962736495","https://openalex.org/W2962858248","https://openalex.org/W2963170432","https://openalex.org/W2963199420","https://openalex.org/W2963411833","https://openalex.org/W2964118020","https://openalex.org/W2964342357","https://openalex.org/W2965293401","https://openalex.org/W2968340082","https://openalex.org/W2990747716","https://openalex.org/W2996086858","https://openalex.org/W2997359900","https://openalex.org/W3013821552","https://openalex.org/W3020712699","https://openalex.org/W3029539653","https://openalex.org/W3030520603","https://openalex.org/W3031634197","https://openalex.org/W3032377877","https://openalex.org/W3039737909","https://openalex.org/W3094138303","https://openalex.org/W3208422024","https://openalex.org/W4244930641","https://openalex.org/W6683195989","https://openalex.org/W6683526187","https://openalex.org/W6685726866","https://openalex.org/W6697071109","https://openalex.org/W6720501231","https://openalex.org/W6727830657","https://openalex.org/W6728499154","https://openalex.org/W6732837357","https://openalex.org/W6735789912","https://openalex.org/W6739365718","https://openalex.org/W6740222838","https://openalex.org/W6740879895","https://openalex.org/W6744563498","https://openalex.org/W6746595151","https://openalex.org/W6748523217","https://openalex.org/W6753060773","https://openalex.org/W6753243525","https://openalex.org/W6754005058","https://openalex.org/W6756303580","https://openalex.org/W6757592117","https://openalex.org/W6765240361","https://openalex.org/W6765741874","https://openalex.org/W6766433728","https://openalex.org/W6767997047","https://openalex.org/W6768008868","https://openalex.org/W6768397756","https://openalex.org/W6769596995","https://openalex.org/W6770858630","https://openalex.org/W6771179988","https://openalex.org/W6771876938","https://openalex.org/W6772034216","https://openalex.org/W6774126978","https://openalex.org/W6775647304","https://openalex.org/W6782841687","https://openalex.org/W6784062865","https://openalex.org/W6841112233"],"related_works":["https://openalex.org/W3098815154","https://openalex.org/W2963780574","https://openalex.org/W2891076394","https://openalex.org/W2950600380","https://openalex.org/W3135512538","https://openalex.org/W3090054427","https://openalex.org/W2962918551","https://openalex.org/W2952672470","https://openalex.org/W2914584948","https://openalex.org/W2963311874","https://openalex.org/W2977416770","https://openalex.org/W2982701845","https://openalex.org/W3034672970","https://openalex.org/W3033074320","https://openalex.org/W3035093572","https://openalex.org/W3003653070","https://openalex.org/W2968227116","https://openalex.org/W2616430965","https://openalex.org/W3213728790","https://openalex.org/W3167658443"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"algorithms":[3,30,71],"can":[4,100,151,162,180,194],"in":[5,18,36,54,87,123,208,237,256],"principle":[6],"acquire":[7],"complex":[8,203,233],"robotic":[9],"skills":[10],"by":[11],"learning":[12,138,171,193,198,218,223,230],"from":[13],"large":[14,102],"amounts":[15],"of":[16,104,160,184,191],"data":[17,64],"the":[19,114,118,136,154,185,221,249,257],"real":[20,258],"world,":[21],"collected":[22],"via":[23],"trial":[24],"and":[25,44,175,225,240],"error.":[26],"However,":[27,93,117],"most":[28],"RL":[29,132,261],"use":[31],"a":[32,148,213],"carefully":[33],"engineered":[34],"setup":[35],"order":[37],"to":[38,46,75,111,164,200,231,251],"collect":[39],"data,":[40],"requiring":[41],"human":[42,82,264],"supervision":[43],"intervention":[45],"provide":[47],"episodic":[48],"resets.":[49,245],"This":[50,189,246],"is":[51,126],"particularly":[52],"evident":[53],"challenging":[55],"robotics":[56],"problems,":[57,204],"such":[58,67],"as":[59,205],"dexterous":[60,234],"manipulation.":[61],"To":[62],"make":[63,113,122],"collection":[65],"scalable,":[66],"applications":[68],"require":[69],"reset-free":[70,137,155,197,222],"that":[72,99,127,219],"are":[73],"able":[74],"learn":[76,182,252],"autonomously,":[77],"without":[78,242,262],"explicit":[79,244],"instrumentation":[80],"or":[81],"intervention.":[83,265],"Most":[84],"prior":[85],"work":[86,125,247],"this":[88,108,124],"area":[89],"handles":[90],"single-task":[91],"learning.":[92],"we":[94,121,179,206],"might":[95],"also":[96],"want":[97],"robots":[98],"perform":[101,165],"repertoires":[103],"skills.":[105],"At":[106],"first,":[107],"would":[109],"appear":[110],"only":[112],"problem":[115,150,156],"harder.":[116],"key":[119],"observation":[120],"an":[128],"appropriately":[129,176],"chosen":[130],"multi-task":[131,149,192,217],"setting":[133],"actually":[134],"alleviates":[135],"challenge,":[139],"with":[140,260],"minimal":[141],"additional":[142],"machinery":[143],"required.":[144],"In":[145],"effect,":[146],"solving":[147],"directly":[152],"solve":[153,232],"since":[157],"different":[158],"combinations":[159],"tasks":[161,173,186,236],"serve":[163],"resets":[166],"for":[167,216],"other":[168],"tasks.":[169],"By":[170],"multiple":[172],"together":[174,187],"sequencing":[177],"them,":[178],"effectively":[181,195],"all":[183],"reset-free.":[188],"type":[190],"scale":[196],"schemes":[199],"much":[201],"more":[202],"demonstrate":[207],"our":[209],"experiments.":[210],"We":[211],"propose":[212],"simple":[214],"scheme":[215],"tackles":[220],"problem,":[224],"show":[226],"its":[227],"effectiveness":[228],"at":[229],"manipulation":[235,254],"both":[238],"hardware":[239],"simulation":[241],"any":[243,263],"shows":[248],"ability":[250],"in-hand":[253],"behaviors":[255],"world":[259]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}