{"id":"https://openalex.org/W3093090008","doi":"https://doi.org/10.1109/lra.2021.3064509","title":"Hyperparameter Auto-Tuning in Self-Supervised Robotic Learning","display_name":"Hyperparameter Auto-Tuning in Self-Supervised Robotic Learning","publication_year":2021,"publication_date":"2021-03-08","ids":{"openalex":"https://openalex.org/W3093090008","doi":"https://doi.org/10.1109/lra.2021.3064509","mag":"3093090008"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3064509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3064509","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.08252","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067576582","display_name":"Jiancong Huang","orcid":"https://orcid.org/0000-0002-4959-6664"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiancong Huang","raw_affiliation_strings":["School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4959-6664","affiliations":[{"raw_affiliation_string":"School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060257108","display_name":"Juan Rojas","orcid":"https://orcid.org/0000-0002-6552-4572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Juan Rojas","raw_affiliation_strings":["School of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-6552-4572","affiliations":[{"raw_affiliation_string":"School of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028712584","display_name":"Matthieu Zimmer","orcid":"https://orcid.org/0000-0002-8029-308X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Matthieu Zimmer","raw_affiliation_strings":["UM-SJTU Joint Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8029-308X","affiliations":[{"raw_affiliation_string":"UM-SJTU Joint Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040144876","display_name":"Hongmin Wu","orcid":"https://orcid.org/0000-0001-8517-5296"},"institutions":[{"id":"https://openalex.org/I4210103524","display_name":"Guangdong Academy of Sciences","ror":"https://ror.org/01g9hkj35","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210103524"]},{"id":"https://openalex.org/I4210142539","display_name":"Guangdong Institute of Intelligent Manufacturing","ror":"https://ror.org/049jpjz09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210142539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongmin Wu","raw_affiliation_strings":["Institute of Intelligent Manufacturing, Guangdong Academy of Sciences, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Manufacturing, Guangdong Academy of Sciences, Guangzhou, China","institution_ids":["https://openalex.org/I4210142539","https://openalex.org/I4210103524"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013471002","display_name":"Yisheng Guan","orcid":"https://orcid.org/0000-0002-7011-0331"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yisheng Guan","raw_affiliation_strings":["School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7011-0331","affiliations":[{"raw_affiliation_string":"School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073106112","display_name":"Paul Weng","orcid":"https://orcid.org/0000-0002-2008-4569"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Paul Weng","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China","UM-SJTU Joint Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2008-4569","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"UM-SJTU Joint Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3993,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84411411,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"6","issue":"2","first_page":"3537","last_page":"3544"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9968000054359436,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9941999912261963,"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/hyperparameter","display_name":"Hyperparameter","score":0.8528225421905518},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8050482273101807},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7439266443252563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5884226560592651},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5814955234527588},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4716324508190155},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.46312791109085083},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45796847343444824},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43271946907043457},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4178420603275299},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07563439011573792},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.07191139459609985}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8528225421905518},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8050482273101807},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7439266443252563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5884226560592651},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5814955234527588},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4716324508190155},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.46312791109085083},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45796847343444824},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43271946907043457},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4178420603275299},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07563439011573792},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07191139459609985},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2021.3064509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3064509","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"},{"id":"pmh:oai:arXiv.org:2010.08252","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.08252","pdf_url":"https://arxiv.org/pdf/2010.08252","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.08252","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.08252","pdf_url":"https://arxiv.org/pdf/2010.08252","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1219423884","display_name":null,"funder_award_id":"51975126","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1512516973","display_name":null,"funder_award_id":"61950410758","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4650637785","display_name":null,"funder_award_id":"51905105","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5010798040","display_name":null,"funder_award_id":"61872238","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1487444668","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W2004303440","https://openalex.org/W2007339694","https://openalex.org/W2097998348","https://openalex.org/W2106411961","https://openalex.org/W2182396527","https://openalex.org/W2192203593","https://openalex.org/W2434741482","https://openalex.org/W2471761533","https://openalex.org/W2557283755","https://openalex.org/W2616430965","https://openalex.org/W2750384547","https://openalex.org/W2753738274","https://openalex.org/W2754517384","https://openalex.org/W2798650501","https://openalex.org/W2823112946","https://openalex.org/W2903327785","https://openalex.org/W2903782687","https://openalex.org/W2919115771","https://openalex.org/W2922007426","https://openalex.org/W2942580059","https://openalex.org/W2945774545","https://openalex.org/W2946006146","https://openalex.org/W2949676527","https://openalex.org/W2949759968","https://openalex.org/W2951557330","https://openalex.org/W2953772919","https://openalex.org/W2960531549","https://openalex.org/W2962779867","https://openalex.org/W2962897394","https://openalex.org/W2962897886","https://openalex.org/W2963120839","https://openalex.org/W2963145887","https://openalex.org/W2963226019","https://openalex.org/W2963293881","https://openalex.org/W2964342357","https://openalex.org/W2965920802","https://openalex.org/W2970961807","https://openalex.org/W2982130342","https://openalex.org/W2995617888","https://openalex.org/W3007031922","https://openalex.org/W3032077725","https://openalex.org/W3035717769","https://openalex.org/W3042532592","https://openalex.org/W3100008240","https://openalex.org/W4288359387","https://openalex.org/W4289242739","https://openalex.org/W4289303873","https://openalex.org/W4391602018","https://openalex.org/W6616173779","https://openalex.org/W6639732818","https://openalex.org/W6674385629","https://openalex.org/W6676179485","https://openalex.org/W6687482969","https://openalex.org/W6718140377","https://openalex.org/W6721095443","https://openalex.org/W6737937804","https://openalex.org/W6743688258","https://openalex.org/W6744123322","https://openalex.org/W6744627333","https://openalex.org/W6749101112","https://openalex.org/W6753060773","https://openalex.org/W6760560886","https://openalex.org/W6762263229","https://openalex.org/W6762319895","https://openalex.org/W6762796984","https://openalex.org/W6762863188","https://openalex.org/W6766156165","https://openalex.org/W6769166761","https://openalex.org/W6771730547","https://openalex.org/W6773436215"],"related_works":["https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W2140186469","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W2775233965","https://openalex.org/W4318559728","https://openalex.org/W4360995913","https://openalex.org/W4281847915","https://openalex.org/W3000635674"],"abstract_inverted_index":{"Policy":[0],"optimization":[1,20],"in":[2,38,70],"reinforcement":[3,91],"learning":[4,30,43,60,127],"requires":[5],"the":[6,64,75,87,99,103,113,153,160,178],"selection":[7],"of":[8,77,105,115,159],"numerous":[9],"hyperparameters":[10],"across":[11],"different":[12],"environments.":[13],"Fixing":[14],"them":[15],"incorrectly":[16],"may":[17],"negatively":[18],"impact":[19],"performance":[21,155],"leading":[22],"notably":[23],"to":[24,32,34,57],"insufficient":[25],"or":[26],"redundant":[27,42],"learning.":[28,92],"Insufficient":[29],"(due":[31],"convergence":[33],"local":[35],"optima)":[36],"results":[37],"under-performing":[39],"policies":[40,56],"whilst":[41],"wastes":[44],"time":[45,161],"and":[46,112,151,162,167,171],"resources.":[47,164],"The":[48],"effects":[49],"are":[50],"further":[51],"exacerbated":[52],"when":[53],"using":[54,135],"single":[55],"solve":[58],"multi-task":[59],"problems.":[61],"Observing":[62],"that":[63,145],"Evidence":[65],"Lower":[66],"Bound":[67],"(ELBO)":[68],"used":[69],"Variational":[71],"Auto-Encoders":[72],"correlates":[73],"with":[74,131],"diversity":[76],"image":[78],"samples,":[79],"we":[80],"propose":[81],"an":[82],"auto-tuning":[83],"technique":[84],"based":[85],"on":[86],"ELBO":[88],"for":[89,140,169],"self-supervised":[90,125],"Our":[93],"approach":[94],"can":[95,148,174],"auto-tune":[96,149],"three":[97],"hyperparameters:":[98],"replay":[100],"buffer":[101],"size,":[102],"number":[104,114],"policy":[106],"gradient":[107],"updates":[108],"during":[109,118],"each":[110,119],"epoch,":[111],"exploration":[116],"steps":[117],"epoch.":[120],"We":[121],"use":[122],"a":[123,157],"state-of-the-art":[124],"robot":[126],"framework":[128],"(Reinforcement":[129],"Learning":[130],"Imagined":[132],"Goals":[133],"(RIG)":[134],"Soft":[136],"Actor-Critic)":[137],"as":[138],"baseline":[139],"experimental":[141],"verification.":[142],"Experiments":[143],"show":[144],"our":[146],"method":[147],"online":[150],"yields":[152],"best":[154],"at":[156,177],"fraction":[158],"computational":[163],"Code,":[165],"video,":[166],"appendix":[168],"simulated":[170],"real-robot":[172],"experiments":[173],"be":[175],"found":[176],"project":[179],"page":[180],"www.JuanRojas.net/autotune.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}