{"id":"https://openalex.org/W2897205373","doi":"https://doi.org/10.1109/icra.2019.8794310","title":"A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies","display_name":"A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2897205373","doi":"https://doi.org/10.1109/icra.2019.8794310","mag":"2897205373"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8794310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/1810.04871","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064794691","display_name":"Homanga Bharadhwaj","orcid":"https://orcid.org/0000-0001-5056-8516"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Homanga Bharadhwaj","raw_affiliation_strings":["Department of Computer Science and Engineering, IIT Kanpur, India","Department of Computer Science & Engineering, IIT Kanpur, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIT Kanpur, India","institution_ids":["https://openalex.org/I94234084"]},{"raw_affiliation_string":"Department of Computer Science & Engineering, IIT Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380107","display_name":"Zihan Wang","orcid":"https://orcid.org/0000-0003-0493-2668"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Zihan Wang","raw_affiliation_strings":["Division of Engineering Science, University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Division of Engineering Science, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"institutions":[{"id":"https://openalex.org/I4210155582","display_name":"Centre Universitaire de Mila","ror":"https://ror.org/05s3cw058","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210155582"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA","DZ"],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["Mila, Universite de Montreal","Mila, Universit\u00e9 de Montreal"],"affiliations":[{"raw_affiliation_string":"Mila, Universite de Montreal","institution_ids":["https://openalex.org/I4210155582","https://openalex.org/I70931966"]},{"raw_affiliation_string":"Mila, Universit\u00e9 de Montreal","institution_ids":["https://openalex.org/I4210155582","https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037065865","display_name":"Liam Paull","orcid":"https://orcid.org/0000-0003-2492-6660"},"institutions":[{"id":"https://openalex.org/I4210155582","display_name":"Centre Universitaire de Mila","ror":"https://ror.org/05s3cw058","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210155582"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA","DZ"],"is_corresponding":false,"raw_author_name":"Liam Paull","raw_affiliation_strings":["Mila, Universite de Montreal","Mila, Universit\u00e9 de Montreal"],"affiliations":[{"raw_affiliation_string":"Mila, Universite de Montreal","institution_ids":["https://openalex.org/I4210155582","https://openalex.org/I70931966"]},{"raw_affiliation_string":"Mila, Universit\u00e9 de Montreal","institution_ids":["https://openalex.org/I4210155582","https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064794691"],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":0.7233,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77609428,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"782","last_page":"788"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8077291250228882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7382190823554993},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7004765868186951},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6028808355331421},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5545873045921326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5406091213226318},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.4960249364376068},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47809430956840515},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.47487112879753113},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45610764622688293},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4319351613521576},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3913373351097107},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3842659294605255}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8077291250228882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382190823554993},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7004765868186951},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6028808355331421},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5545873045921326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5406091213226318},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.4960249364376068},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47809430956840515},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.47487112879753113},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45610764622688293},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4319351613521576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3913373351097107},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3842659294605255},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra.2019.8794310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1810.04871","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.04871","pdf_url":"https://arxiv.org/pdf/1810.04871","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:2897205373","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1810.04871.pdf","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.1810.04871","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1810.04871","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1810.04871","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.04871","pdf_url":"https://arxiv.org/pdf/1810.04871","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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2897205373.pdf","grobid_xml":"https://content.openalex.org/works/W2897205373.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2042520683","https://openalex.org/W2121615981","https://openalex.org/W2174364281","https://openalex.org/W2258731934","https://openalex.org/W2399033357","https://openalex.org/W2521863123","https://openalex.org/W2528489519","https://openalex.org/W2543474074","https://openalex.org/W2550182557","https://openalex.org/W2567101557","https://openalex.org/W2575705757","https://openalex.org/W2578206533","https://openalex.org/W2593768305","https://openalex.org/W2604763608","https://openalex.org/W2605102758","https://openalex.org/W2617317556","https://openalex.org/W2725320964","https://openalex.org/W2737347195","https://openalex.org/W2739083961","https://openalex.org/W2766108544","https://openalex.org/W2766614170","https://openalex.org/W2770468159","https://openalex.org/W2771114757","https://openalex.org/W2784596339","https://openalex.org/W2786465559","https://openalex.org/W2787387965","https://openalex.org/W2795756076","https://openalex.org/W2798273187","https://openalex.org/W2805278171","https://openalex.org/W2805481182","https://openalex.org/W2807352135","https://openalex.org/W2949987290","https://openalex.org/W2952606116","https://openalex.org/W2952629144","https://openalex.org/W2962736495","https://openalex.org/W2962743868","https://openalex.org/W2962787403","https://openalex.org/W2963184939","https://openalex.org/W2969329576","https://openalex.org/W3101442004","https://openalex.org/W6637373629","https://openalex.org/W6678317597","https://openalex.org/W6685200760","https://openalex.org/W6692405165","https://openalex.org/W6712906272","https://openalex.org/W6721345134","https://openalex.org/W6726908607","https://openalex.org/W6728752378","https://openalex.org/W6728925229","https://openalex.org/W6729433768","https://openalex.org/W6731344955","https://openalex.org/W6736057607","https://openalex.org/W6738647363","https://openalex.org/W6740023956","https://openalex.org/W6741977017","https://openalex.org/W6745102044","https://openalex.org/W6745421424","https://openalex.org/W6745744936","https://openalex.org/W6746260573","https://openalex.org/W6746428009","https://openalex.org/W6748317118","https://openalex.org/W6748331328","https://openalex.org/W6748729045","https://openalex.org/W6750409132","https://openalex.org/W6751959828","https://openalex.org/W6752031173","https://openalex.org/W6966558720"],"related_works":["https://openalex.org/W3023661178","https://openalex.org/W2738129230","https://openalex.org/W3179146632","https://openalex.org/W2914688076","https://openalex.org/W2806835385","https://openalex.org/W3045280543","https://openalex.org/W2528734395","https://openalex.org/W2766614170","https://openalex.org/W3207591725","https://openalex.org/W2565122071","https://openalex.org/W2962709623","https://openalex.org/W2922299896","https://openalex.org/W3174979795","https://openalex.org/W3035756007","https://openalex.org/W3016259407","https://openalex.org/W2918049070","https://openalex.org/W3046387304","https://openalex.org/W2953129341","https://openalex.org/W200871178","https://openalex.org/W2522340145"],"abstract_inverted_index":{"Learning":[0],"effective":[1],"visuomotor":[2],"policies":[3],"for":[4],"robots":[5],"purely":[6],"from":[7,166,179],"data":[8,69],"is":[9,59,139],"challenging,":[10],"but":[11,163],"also":[12],"appealing":[13],"since":[14,46],"a":[15,29,33,83,100,117,124,143,159,186,202],"learning-based":[16],"system":[17],"should":[18],"not":[19],"require":[20],"manual":[21],"tuning":[22,193],"or":[23],"calibration.":[24],"In":[25,78],"the":[26,36,51,71,76,94,107,114,128,134,155,167,174,180,194],"case":[27],"of":[28,53,133,161],"robot":[30],"operating":[31],"in":[32,88,146,213],"real":[34,95,170,181,204],"environment":[35],"training":[37],"process":[38],"can":[39],"be":[40,62],"costly,":[41],"time-consuming,":[42],"and":[43,67,90,110,122,136,169,182],"even":[44],"dangerous":[45],"failures":[47],"are":[48],"common":[49],"at":[50],"start":[52],"training.":[54],"For":[55],"this":[56,79],"reason,":[57],"it":[58],"desirable":[60],"to":[61,64,70,74,93,116,126,172,176,185],"able":[63],"leverage":[65],"simulation":[66,89,168],"off-policy":[68],"extent":[72],"possible":[73],"train":[75],"robot.":[77],"work,":[80],"we":[81,208],"introduce":[82],"robust":[84],"framework":[85],"that":[86],"plans":[87,123],"transfers":[91],"well":[92],"environment.":[96],"Our":[97],"model":[98,196],"incorporates":[99],"gradient-descent":[101],"based":[102],"planning":[103,211],"module,":[104],"which,":[105],"given":[106],"initial":[108],"image":[109],"goal":[111],"image,":[112],"encodes":[113],"images":[115,165,178],"lower":[118],"dimensional":[119],"latent":[120,189],"state":[121],"trajectory":[125],"reach":[127],"goal.":[129],"The":[130],"model,":[131],"consisting":[132],"encoder":[135,156,175],"planner":[137],"modules,":[138],"first":[140],"trained":[141],"through":[142],"meta-learning":[144],"strategy":[145],"simulation.":[147],"We":[148],"subsequently":[149],"perform":[150],"adversarial":[151],"domain":[152],"transfer":[153],"on":[154],"by":[157],"using":[158],"bank":[160],"unlabelled":[162],"random":[164],"environments":[171,184],"enable":[173],"map":[177],"simulated":[183],"similarly":[187],"distributed":[188],"representation.":[190],"By":[191],"fine":[192],"entire":[195],"(encoder":[197],"+":[198],"planner)":[199],"with":[200],"only":[201],"few":[203],"world":[205],"expert":[206],"demonstrations,":[207],"show":[209],"successful":[210],"performances":[212],"different":[214],"navigation":[215],"tasks.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}