{"id":"https://openalex.org/W3134395475","doi":"https://doi.org/10.1109/iros51168.2021.9636628","title":"Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms","display_name":"Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3134395475","doi":"https://doi.org/10.1109/iros51168.2021.9636628","mag":"3134395475"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636628","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-285972","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038342432","display_name":"Ali Ghadirzadeh","orcid":null},"institutions":[{"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":["US"],"is_corresponding":false,"raw_author_name":"Ali Ghadirzadeh","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329939","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0002-3577-3308"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005900989","display_name":"Petra Poklukar","orcid":"https://orcid.org/0000-0001-6920-5109"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Petra Poklukar","raw_affiliation_strings":["KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005431772","display_name":"Chelsea Finn","orcid":"https://orcid.org/0000-0001-6298-0874"},"institutions":[{"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":["US"],"is_corresponding":false,"raw_author_name":"Chelsea Finn","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082269387","display_name":"M\u00e5rten Bj\u00f6rkman","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Marten Bjorkman","raw_affiliation_strings":["KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023792180","display_name":"Danica Kragi\u0107","orcid":"https://orcid.org/0000-0003-2965-2953"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Danica Kragic","raw_affiliation_strings":["KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7815,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.92314302,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1274","last_page":"1280"},"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":0.998199999332428,"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":0.998199999332428,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9933000206947327,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9840999841690063,"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/computer-science","display_name":"Computer science","score":0.7622604370117188},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.710995078086853},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.69105464220047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.660748302936554},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6550211906433105},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.6290985941886902},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6148660778999329},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5684071779251099},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5128071904182434},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4845668375492096},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.4449707865715027},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11239117383956909}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622604370117188},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.710995078086853},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.69105464220047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.660748302936554},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6550211906433105},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.6290985941886902},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6148660778999329},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5684071779251099},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5128071904182434},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4845668375492096},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.4449707865715027},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11239117383956909},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros51168.2021.9636628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636628","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:kth-285972","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-285972","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"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":"","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-285972","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-285972","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":97,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1777783943","https://openalex.org/W1959608418","https://openalex.org/W2155007355","https://openalex.org/W2528489519","https://openalex.org/W2592538810","https://openalex.org/W2601322194","https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2736601468","https://openalex.org/W2755546070","https://openalex.org/W2762872434","https://openalex.org/W2767050701","https://openalex.org/W2785342287","https://openalex.org/W2787053496","https://openalex.org/W2788904251","https://openalex.org/W2805481182","https://openalex.org/W2889970038","https://openalex.org/W2895558617","https://openalex.org/W2903630557","https://openalex.org/W2908369924","https://openalex.org/W2922427205","https://openalex.org/W2949517868","https://openalex.org/W2950501399","https://openalex.org/W2951004968","https://openalex.org/W2951262671","https://openalex.org/W2951762469","https://openalex.org/W2962696179","https://openalex.org/W2962732055","https://openalex.org/W2962799101","https://openalex.org/W2962974944","https://openalex.org/W2963094133","https://openalex.org/W2963176272","https://openalex.org/W2963276406","https://openalex.org/W2963547174","https://openalex.org/W2963703448","https://openalex.org/W2963887494","https://openalex.org/W2964105864","https://openalex.org/W2964112702","https://openalex.org/W2964121937","https://openalex.org/W2964161785","https://openalex.org/W2964262254","https://openalex.org/W2964335674","https://openalex.org/W2990747716","https://openalex.org/W3004116079","https://openalex.org/W3009295642","https://openalex.org/W3016943329","https://openalex.org/W3017409624","https://openalex.org/W3022659297","https://openalex.org/W3028676366","https://openalex.org/W3036236109","https://openalex.org/W3041686449","https://openalex.org/W3042940089","https://openalex.org/W3044290186","https://openalex.org/W3046419021","https://openalex.org/W3047403664","https://openalex.org/W3090612618","https://openalex.org/W3090943552","https://openalex.org/W3093118788","https://openalex.org/W3101442004","https://openalex.org/W3102248919","https://openalex.org/W3115727409","https://openalex.org/W3130568950","https://openalex.org/W3138863790","https://openalex.org/W4285719527","https://openalex.org/W4288356697","https://openalex.org/W4295676892","https://openalex.org/W4300514939","https://openalex.org/W4327691454","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6682849425","https://openalex.org/W6735236233","https://openalex.org/W6735944222","https://openalex.org/W6736057607","https://openalex.org/W6741002519","https://openalex.org/W6744181227","https://openalex.org/W6748331328","https://openalex.org/W6748566876","https://openalex.org/W6748600884","https://openalex.org/W6751959828","https://openalex.org/W6753073282","https://openalex.org/W6753311412","https://openalex.org/W6754628760","https://openalex.org/W6754782557","https://openalex.org/W6756469835","https://openalex.org/W6757740418","https://openalex.org/W6763120227","https://openalex.org/W6766092863","https://openalex.org/W6769609827","https://openalex.org/W6776458826","https://openalex.org/W6779436940","https://openalex.org/W6780218565","https://openalex.org/W6780559457","https://openalex.org/W6780759987","https://openalex.org/W6780940409","https://openalex.org/W6784333816"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W3130669838","https://openalex.org/W2785397462","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W2891227010"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,115],"methods":[2,200],"can":[3,105,176],"achieve":[4,109],"significant":[5],"performance":[6],"but":[7],"require":[8],"a":[9,33,50,55,58,79,89,114,119,134,144,148,179],"large":[10],"amount":[11],"of":[12,48,67,118,162,166,193],"training":[13],"data":[14,26],"collected":[15],"on":[16,71,143],"the":[17,37,45,72,84,93,126,130,159,173,191,202],"same":[18],"robotic":[19,60,99,167,184],"platform.":[20],"A":[21],"policy":[22,181,205],"trained":[23,52,180],"with":[24,133,186],"expensive":[25],"is":[27,86],"rendered":[28],"useless":[29],"after":[30],"making":[31],"even":[32],"minor":[34],"change":[35],"to":[36,53,57,87,182,198],"robot":[38,68],"hardware.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"address":[44],"challenging":[46],"problem":[47,82],"adapting":[49],"policy,":[51],"perform":[54],"task,":[56],"novel":[59,187],"hardware":[61],"platform":[62],"given":[63],"only":[64],"few":[65],"demonstrations":[66],"motion":[69],"trajectories":[70],"target":[73],"robot.":[74],"We":[75,108,138],"formulate":[76],"it":[77],"as":[78],"few-shot":[80,131,204],"meta-learning":[81,122,195],"where":[83],"goal":[85],"find":[88],"meta-model":[90],"that":[91,102,124,172],"captures":[92],"common":[94],"structure":[95],"shared":[96],"across":[97],"different":[98,183],"platforms":[100,185],"such":[101,110],"data-efficient":[103],"adaptation":[104,111,206],"be":[106],"performed.":[107],"by":[112,157],"introducing":[113],"framework":[116,142],"consisting":[117],"probabilistic":[120],"gradient-based":[121],"algorithm":[123,196],"models":[125],"uncertainty":[127],"arising":[128],"from":[129],"setting":[132],"low-dimensional":[135],"latent":[136],"variable.":[137],"experimentally":[139],"evaluate":[140],"our":[141,194],"simulated":[145,154],"reaching":[146],"and":[147,190],"real-robot":[149],"picking":[150],"task":[151],"using":[152],"400":[153],"robots":[155],"generated":[156],"varying":[158],"physical":[160,188],"parameters":[161,189],"an":[163],"existing":[164],"set":[165],"platforms.":[168],"Our":[169],"results":[170],"show":[171],"proposed":[174],"method":[175],"successfully":[177],"adapt":[178],"superiority":[192],"compared":[197],"state-of-the-art":[199],"for":[201],"introduced":[203],"problem.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}