{"id":"https://openalex.org/W3012330110","doi":"https://doi.org/10.1109/iros45743.2020.9341462","title":"Fast Online Adaptation in Robotics through Meta-Learning Embeddings of Simulated Priors","display_name":"Fast Online Adaptation in Robotics through Meta-Learning Embeddings of Simulated Priors","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3012330110","doi":"https://doi.org/10.1109/iros45743.2020.9341462","mag":"3012330110"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341462","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.04663","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072492839","display_name":"Rituraj Kaushik","orcid":"https://orcid.org/0000-0003-2598-8804"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Rituraj Kaushik","raw_affiliation_strings":["Inria, CNRS, Universit\u00e9 de Lorraine, Nancy, France","Universit\u00e9 de Lorraine,Inria, CNRS,Nancy,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, CNRS, Universit\u00e9 de Lorraine, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Universit\u00e9 de Lorraine,Inria, CNRS,Nancy,France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102883278","display_name":"Timoth\u00e9e Anne","orcid":"https://orcid.org/0000-0002-4805-0213"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Timothee Anne","raw_affiliation_strings":["Inria, CNRS, Universit\u00e9 de Lorraine, Nancy, France","Universit\u00e9 de Lorraine,Inria, CNRS,Nancy,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, CNRS, Universit\u00e9 de Lorraine, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Universit\u00e9 de Lorraine,Inria, CNRS,Nancy,France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032227198","display_name":"Jean-Baptiste Mouret","orcid":"https://orcid.org/0000-0002-2513-027X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Baptiste Mouret","raw_affiliation_strings":["Inria, CNRS, Universit\u00e9 de Lorraine, Nancy, France","French Institute for Research in Computer Science and Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, CNRS, Universit\u00e9 de Lorraine, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"French Institute for Research in Computer Science and Automation","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3009,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84439081,"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":"5269","last_page":"5276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/T10876","display_name":"Fault Detection and Control Systems","score":0.9799000024795532,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7293366193771362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.713920533657074},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.641348659992218},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6248471736907959},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.6117011904716492},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6110016703605652},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5894198417663574},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5666961073875427},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5040634870529175},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4906069338321686},{"id":"https://openalex.org/keywords/terrain","display_name":"Terrain","score":0.4607487916946411},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.41140806674957275},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.16989505290985107},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.133492112159729},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13204911351203918}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7293366193771362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713920533657074},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.641348659992218},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6248471736907959},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.6117011904716492},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6110016703605652},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5894198417663574},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5666961073875427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5040634870529175},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4906069338321686},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.4607487916946411},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.41140806674957275},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.16989505290985107},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.133492112159729},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13204911351203918},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"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/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/iros45743.2020.9341462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341462","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"},{"id":"pmh:oai:arXiv.org:2003.04663","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.04663","pdf_url":"https://arxiv.org/pdf/2003.04663","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":"","raw_type":"text"},{"id":"mag:3012330110","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2003.04663","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":"pmh:oai:HAL:hal-02909452v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02909452","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020, Las Vegas, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2003.04663","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.04663","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"},{"id":"doi:10.13140/rg.2.2.25765.45282","is_oa":true,"landing_page_url":"https://doi.org/10.13140/rg.2.2.25765.45282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.04663","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.04663","pdf_url":"https://arxiv.org/pdf/2003.04663","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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W758372786","https://openalex.org/W1498369939","https://openalex.org/W1587009522","https://openalex.org/W1738827650","https://openalex.org/W1825573441","https://openalex.org/W2015630562","https://openalex.org/W2058702345","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2158899491","https://openalex.org/W2462548332","https://openalex.org/W2604763608","https://openalex.org/W2604883922","https://openalex.org/W2606327391","https://openalex.org/W2726187156","https://openalex.org/W2727901370","https://openalex.org/W2736601468","https://openalex.org/W2738778707","https://openalex.org/W2770616710","https://openalex.org/W2771827793","https://openalex.org/W2790355818","https://openalex.org/W2794363191","https://openalex.org/W2794757725","https://openalex.org/W2795900505","https://openalex.org/W2810424651","https://openalex.org/W2905438253","https://openalex.org/W2962687375","https://openalex.org/W2962812027","https://openalex.org/W2962872206","https://openalex.org/W2963930274","https://openalex.org/W2963960193","https://openalex.org/W2964267629","https://openalex.org/W2995736683","https://openalex.org/W2997896361","https://openalex.org/W3001500946","https://openalex.org/W6622219343","https://openalex.org/W6629718364","https://openalex.org/W6654039626","https://openalex.org/W6680657880","https://openalex.org/W6683738474","https://openalex.org/W6736057607","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6744508621","https://openalex.org/W6750254146","https://openalex.org/W6751494529","https://openalex.org/W6753051720","https://openalex.org/W6756873541"],"related_works":["https://openalex.org/W3045714531","https://openalex.org/W3102566342","https://openalex.org/W2952193948","https://openalex.org/W2964093801","https://openalex.org/W2957144066","https://openalex.org/W3160665951","https://openalex.org/W2990458647","https://openalex.org/W2753160622","https://openalex.org/W3011929509","https://openalex.org/W3001500946","https://openalex.org/W3130076912","https://openalex.org/W2968854004","https://openalex.org/W2055593999","https://openalex.org/W1796186189","https://openalex.org/W3115080916","https://openalex.org/W1838356191","https://openalex.org/W3011301783","https://openalex.org/W3035486480","https://openalex.org/W2121103318","https://openalex.org/W3197314723"],"abstract_inverted_index":{"Meta-learning":[0],"algorithms":[1,9],"can":[2,25,69],"accelerate":[3],"the":[4,18,23,30,34,43,64,67,112,121,145,152,159,162,212],"model-based":[5],"reinforcement":[6],"learning":[7],"(MBRL)":[8],"by":[10,134],"finding":[11,57],"an":[12,126],"initial":[13,137,141],"set":[14,96],"of":[15,33,66,97,109,120],"parameters":[16,99],"for":[17,143,189],"dynamical":[19],"model":[20,24,119,146,160,180],"such":[21,90],"that":[22,82,130,198],"be":[26,70],"trained":[27],"to":[28,56,115,150,157,161,174,202,204],"match":[29],"actual":[31],"dynamics":[32,65],"system":[35,114],"with":[36,165,177,181],"only":[37,166],"a":[38,46,60,94,101,106,117,167,178],"few":[39,168],"data-points.":[40],"However,":[41],"in":[42,59,207],"real":[44,113,193],"world,":[45],"robot":[47,68],"might":[48],"encounter":[49],"any":[50],"situation":[51,164],"starting":[52,102,138,155],"from":[53,73,111],"motor":[54],"failures":[55],"itself":[58],"rocky":[61],"terrain":[62],"where":[63],"significantly":[71,208],"different":[72],"one":[74],"another.":[75],"In":[76],"this":[77,132],"paper,":[78],"first,":[79],"we":[80,124],"show":[81,197],"when":[83],"meta-training":[84,135],"situations":[85],"(the":[86],"prior":[87],"situations)":[88],"have":[89],"diverse":[91],"dynamics,":[92],"using":[93],"single":[95],"meta-trained":[98,179],"as":[100],"point":[103,156],"still":[104],"requires":[105],"large":[107],"number":[108],"observations":[110],"learn":[116],"useful":[118],"dynamics.":[122],"Second,":[123],"propose":[125],"algorithm":[127,187],"called":[128],"FAMLE":[129,173,199],"mitigates":[131],"limitation":[133],"several":[136],"points":[139],"(i.e.,":[140],"parameters)":[142],"training":[144],"and":[147,183,192,196],"allows":[148,200],"robots":[149,201],"select":[151],"most":[153],"suitable":[154],"adapt":[158,203],"current":[163],"gradient":[169],"steps.":[170],"We":[171],"compare":[172],"MBRL,":[175],"MBRL":[176],"MAML,":[182],"model-free":[184],"policy":[185],"search":[186],"PPO":[188],"various":[190],"simulated":[191],"robotic":[194],"tasks,":[195],"novel":[205],"damages":[206],"fewer":[209],"time-steps":[210],"than":[211],"baselines.":[213]},"counts_by_year":[{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2020-03-23T00:00:00"}