{"id":"https://openalex.org/W3026304494","doi":"https://doi.org/10.1109/icra40945.2020.9197125","title":"Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning","display_name":"Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3026304494","doi":"https://doi.org/10.1109/icra40945.2020.9197125","mag":"3026304494"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.10872","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009589018","display_name":"Michelle A. Lee","orcid":"https://orcid.org/0000-0002-9893-3591"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Michelle A. Lee","raw_affiliation_strings":["Nvidia","Stanford University","nVidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]},{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"nVidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001534200","display_name":"Carlos Florensa","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"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":["GB","US"],"is_corresponding":false,"raw_author_name":"Carlos Florensa","raw_affiliation_strings":["Nvidia","University of California, Berkeley","nVidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"nVidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052530128","display_name":"Jonathan Tremblay","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jonathan Tremblay","raw_affiliation_strings":["Nvidia","nVidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]},{"raw_affiliation_string":"nVidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017897684","display_name":"Nathan Ratliff","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nathan Ratliff","raw_affiliation_strings":["Nvidia","nVidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]},{"raw_affiliation_string":"nVidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061193324","display_name":"Animesh Garg","orcid":"https://orcid.org/0000-0003-0482-4296"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA","GB"],"is_corresponding":false,"raw_author_name":"Animesh Garg","raw_affiliation_strings":["Nvidia","University of Toronto","nVidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]},{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"nVidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062619542","display_name":"F\u00e1bio Ramos","orcid":"https://orcid.org/0000-0002-2996-2188"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["AU","GB"],"is_corresponding":false,"raw_author_name":"Fabio Ramos","raw_affiliation_strings":["Nvidia","University of Sydney","nVidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]},{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"nVidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108257764","display_name":"Dieter Fox","orcid":"https://orcid.org/0009-0009-4694-9127"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"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":["GB","US"],"is_corresponding":false,"raw_author_name":"Dieter Fox","raw_affiliation_strings":["Nvidia","University of Washington","nVidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]},{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"nVidia","institution_ids":["https://openalex.org/I1304085615"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7505","last_page":"7512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9980000257492065,"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":0.9828000068664551,"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/computer-science","display_name":"Computer science","score":0.7411316633224487},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7324243783950806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6724398732185364},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6421070694923401},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6367204785346985},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6309798359870911},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6212752461433411},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5751050114631653},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5632920861244202},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.458721399307251},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.43576693534851074},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1548137664794922},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09366238117218018}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411316633224487},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7324243783950806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6724398732185364},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6421070694923401},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6367204785346985},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6309798359870911},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6212752461433411},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5751050114631653},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5632920861244202},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.458721399307251},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.43576693534851074},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1548137664794922},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09366238117218018},{"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra40945.2020.9197125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.10872","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.10872","pdf_url":"https://arxiv.org/pdf/2005.10872","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"},{"id":"mag:3026304494","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2005.10872","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.2005.10872","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.10872","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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.10872","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.10872","pdf_url":"https://arxiv.org/pdf/2005.10872","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":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3026304494.pdf","grobid_xml":"https://content.openalex.org/works/W3026304494.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1424654272","https://openalex.org/W1526868886","https://openalex.org/W1536308292","https://openalex.org/W1991544872","https://openalex.org/W2012804028","https://openalex.org/W2293883387","https://openalex.org/W2295692686","https://openalex.org/W2580726517","https://openalex.org/W2741122588","https://openalex.org/W2753738274","https://openalex.org/W2768879211","https://openalex.org/W2783192199","https://openalex.org/W2787666871","https://openalex.org/W2793264449","https://openalex.org/W2893763910","https://openalex.org/W2895439318","https://openalex.org/W2905364877","https://openalex.org/W2907572567","https://openalex.org/W2915414978","https://openalex.org/W2949275450","https://openalex.org/W2950921159","https://openalex.org/W2962736495","https://openalex.org/W2962902376","https://openalex.org/W2963099939","https://openalex.org/W2963188159","https://openalex.org/W2963286043","https://openalex.org/W2963293881","https://openalex.org/W2963311874","https://openalex.org/W2963403593","https://openalex.org/W2963525569","https://openalex.org/W2963641140","https://openalex.org/W2963756608","https://openalex.org/W2964161785","https://openalex.org/W2964333597","https://openalex.org/W2964342357","https://openalex.org/W2967717386","https://openalex.org/W2967727187","https://openalex.org/W2968095426","https://openalex.org/W2968116426","https://openalex.org/W2968340082","https://openalex.org/W2970377754","https://openalex.org/W3000962825","https://openalex.org/W3003629310","https://openalex.org/W3027372030","https://openalex.org/W6616173779","https://openalex.org/W6631711059","https://openalex.org/W6682849425","https://openalex.org/W6704571135","https://openalex.org/W6736368053","https://openalex.org/W6737214707","https://openalex.org/W6737937804","https://openalex.org/W6741302124","https://openalex.org/W6745401828","https://openalex.org/W6747473740","https://openalex.org/W6748202546","https://openalex.org/W6753060773","https://openalex.org/W6754677871","https://openalex.org/W6754838991","https://openalex.org/W6755109041","https://openalex.org/W6755561334","https://openalex.org/W6756742327","https://openalex.org/W6756848961","https://openalex.org/W6759032116","https://openalex.org/W6765008394","https://openalex.org/W6772921146"],"related_works":["https://openalex.org/W3091552533","https://openalex.org/W3003777383","https://openalex.org/W2945500224","https://openalex.org/W3045280543","https://openalex.org/W2950600380","https://openalex.org/W3149922422","https://openalex.org/W2963859851","https://openalex.org/W2999490157","https://openalex.org/W2907704766","https://openalex.org/W3043612295","https://openalex.org/W2565122071","https://openalex.org/W3175580674","https://openalex.org/W2513373085","https://openalex.org/W3174195775","https://openalex.org/W2626860042","https://openalex.org/W2782446262","https://openalex.org/W2598674267","https://openalex.org/W2968491743","https://openalex.org/W2979605429","https://openalex.org/W3015442441"],"abstract_inverted_index":{"Traditional":[0],"robotic":[1],"approaches":[2,38],"rely":[3],"on":[4,159],"an":[5],"accurate":[6],"model":[7],"of":[8,14,28,68,74],"the":[9,18,29,33,53,66,72,89,98,109,114],"environment,":[10],"a":[11,21,48,79,139,160],"detailed":[12],"description":[13],"how":[15],"to":[16,25,51,77,85,107],"perform":[17],"task,":[19,54],"and":[20,59,120],"robust":[22],"perception":[23],"system":[24],"keep":[26],"track":[27],"current":[30],"state.":[31],"On":[32],"other":[34],"hand,":[35],"reinforcement":[36],"learning":[37],"can":[39,142],"operate":[40],"directly":[41,145],"from":[42],"raw":[43,147],"sensory":[44,148],"inputs":[45],"with":[46,71,97,146],"only":[47],"reward":[49],"signal":[50],"describe":[52],"but":[55],"are":[56,167],"extremely":[57],"sampleinefficient":[58],"brittle.":[60],"In":[61,132],"this":[62],"work,":[63],"we":[64,136],"combine":[65],"strengths":[67],"model-based":[69,116],"methods":[70,76],"flexibility":[73],"learning-based":[75],"obtain":[78],"general":[80],"method":[81],"that":[82,138],"is":[83,101,118],"able":[84],"overcome":[86],"inaccuracies":[87],"in":[88,111],"robotics":[90],"perception/actuation":[91],"pipeline,":[92],"while":[93],"requiring":[94],"minimal":[95],"interactions":[96],"environment.":[99],"This":[100],"achieved":[102],"by":[103],"leveraging":[104],"uncertainty":[105],"estimates":[106],"divide":[108],"space":[110],"regions":[112,121],"where":[113,122],"given":[115],"policy":[117],"reliable,":[119],"it":[123],"may":[124],"have":[125],"flaws":[126],"or":[127],"not":[128],"be":[129,143],"well":[130],"defined.":[131],"these":[133],"uncertain":[134],"regions,":[135],"show":[137],"locally":[140],"learned-policy":[141],"used":[144],"inputs.":[149],"We":[150],"test":[151],"our":[152],"algorithm,":[153],"Guided":[154],"Uncertainty-Aware":[155],"Policy":[156],"Optimization":[157],"(GUAPO),":[158],"real-world":[161],"robot":[162],"performing":[163],"peg":[164],"insertion.":[165],"Videos":[166],"available":[168],"at:":[169],"https://sites.google.com/view/guapo-rl.":[170]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}