{"id":"https://openalex.org/W4377971355","doi":"https://doi.org/10.1109/tnnls.2023.3270298","title":"Meta-Reinforcement Learning in Nonstationary and Nonparametric Environments","display_name":"Meta-Reinforcement Learning in Nonstationary and Nonparametric Environments","publication_year":2023,"publication_date":"2023-05-24","ids":{"openalex":"https://openalex.org/W4377971355","doi":"https://doi.org/10.1109/tnnls.2023.3270298","pmid":"https://pubmed.ncbi.nlm.nih.gov/37224358"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3270298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3270298","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mediatum.ub.tum.de/1710825","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060444894","display_name":"Zhenshan Bing","orcid":"https://orcid.org/0000-0002-0896-2517"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zhenshan Bing","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0896-2517","affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010032708","display_name":"Lukas Knak","orcid":"https://orcid.org/0009-0003-6181-8594"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lukas Knak","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022496550","display_name":"Long Cheng","orcid":"https://orcid.org/0000-0002-9993-0077"},"institutions":[{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Cheng","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9993-0077","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China","institution_ids":["https://openalex.org/I146620803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088159741","display_name":"Fabrice O. Morin","orcid":"https://orcid.org/0000-0003-0185-7420"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabrice O. Morin","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0185-7420","affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768452","display_name":"Kai Huang","orcid":"https://orcid.org/0000-0003-0359-7810"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Huang","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0359-7810","affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063781430","display_name":"Alois Knoll","orcid":"https://orcid.org/0000-0003-4840-076X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alois Knoll","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4840-076X","affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6225,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91500242,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"35","issue":"10","first_page":"13604","last_page":"13618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9959999918937683,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9890999794006348,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8673889636993408},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.786665678024292},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7258135080337524},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.6557023525238037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6550275087356567},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6533081531524658},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.6325530409812927},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6112217903137207},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5779839158058167},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4990544319152832},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4335680603981018},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3218955397605896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08260369300842285}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8673889636993408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786665678024292},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7258135080337524},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.6557023525238037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6550275087356567},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6533081531524658},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.6325530409812927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6112217903137207},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5779839158058167},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4990544319152832},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4335680603981018},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3218955397605896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08260369300842285},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2023.3270298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3270298","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37224358","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37224358","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:mediatum.ub.tum.de:node/1710825","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1710825","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"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":"article"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1710825","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1710825","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"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":"article"},"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5335103388","display_name":null,"funder_award_id":"61902442","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6483959550","display_name":"Human Brain Project Specific Grant Agreement 3","funder_award_id":"945539","funder_id":"https://openalex.org/F4320338336","funder_display_name":"H2020 Future and Emerging Technologies"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8767435255","display_name":"Human Brain Project Specific Grant Agreement 3","funder_award_id":"945539","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338336","display_name":"H2020 Future and Emerging Technologies","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2556467266","https://openalex.org/W2578206533","https://openalex.org/W2736601468","https://openalex.org/W2903630557","https://openalex.org/W2907537824","https://openalex.org/W2945020056","https://openalex.org/W2962974944","https://openalex.org/W2966461828","https://openalex.org/W2981030070","https://openalex.org/W2981344907","https://openalex.org/W3153573172","https://openalex.org/W3164385739","https://openalex.org/W3198015624","https://openalex.org/W3210013777","https://openalex.org/W4300971732","https://openalex.org/W4311415873","https://openalex.org/W4385245566","https://openalex.org/W6692846177","https://openalex.org/W6729433768","https://openalex.org/W6730333270","https://openalex.org/W6731982132","https://openalex.org/W6736057607","https://openalex.org/W6741002519","https://openalex.org/W6745777752","https://openalex.org/W6747473740","https://openalex.org/W6747943641","https://openalex.org/W6748600884","https://openalex.org/W6755476724","https://openalex.org/W6756463683","https://openalex.org/W6757223306","https://openalex.org/W6760698134","https://openalex.org/W6762959241","https://openalex.org/W6767099637","https://openalex.org/W6769269530","https://openalex.org/W6769596995","https://openalex.org/W6774268721","https://openalex.org/W6780559895","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4243114048","https://openalex.org/W2529605301","https://openalex.org/W4237896776","https://openalex.org/W4231665652","https://openalex.org/W1837630526","https://openalex.org/W2000242494","https://openalex.org/W2335589441","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W2891227010"],"abstract_inverted_index":{"Recent":[0],"state-of-the-art":[1,181],"artificial":[2],"agents":[3],"lack":[4],"the":[5,75,115,118,122,126,132,136,151,169,174],"ability":[6],"to":[7,10,27,44,57,113,149,153,155,190],"adapt":[8,154],"rapidly":[9],"new":[11,29],"tasks,":[12],"as":[13],"they":[14],"are":[15],"trained":[16],"exclusively":[17],"for":[18,100],"specific":[19],"objectives":[20],"and":[21,60,67,94,102,129,172,196,200],"require":[22],"massive":[23],"amounts":[24],"of":[25,117,138,177,186],"interaction":[26],"learn":[28],"skills.":[30],"Meta-reinforcement":[31],"learning":[32,128],"(meta-RL)":[33],"addresses":[34],"this":[35,79],"challenge":[36],"by":[37],"leveraging":[38],"knowledge":[39],"learned":[40],"from":[41,125],"training":[42,124],"tasks":[43,71,166],"perform":[45],"well":[46],"in":[47,74,184,198],"previously":[48],"unseen":[49],"tasks.":[50,119],"However,":[51],"current":[52],"meta-RL":[53,85,182],"approaches":[54,183],"limit":[55],"themselves":[56],"narrow":[58],"parametric":[59],"stationary":[61],"task":[62,157],"distributions,":[63],"ignoring":[64],"qualitative":[65],"differences":[66],"nonstationary":[68,103,156,201],"changes":[69],"between":[70],"that":[72],"occur":[73],"real":[76],"world.":[77],"In":[78],"article,":[80],"we":[81],"introduce":[82],"a":[83,107,111,145,161],"Task-Inference-based":[84],"algorithm":[86],"using":[87],"explicitly":[88],"parameterized":[89],"Gaussian":[90],"variational":[91],"autoencoders":[92],"(VAEs)":[93],"gated":[95],"Recurrent":[96],"units":[97],"(TIGR),":[98],"designed":[99],"nonparametric":[101,199],"environments.":[104],"We":[105,120,143,159],"employ":[106],"generative":[108],"model":[109],"involving":[110],"VAE":[112],"capture":[114],"multimodality":[116],"decouple":[121],"policy":[123],"task-inference":[127],"efficiently":[130],"train":[131],"inference":[133],"mechanism":[134],"on":[135,168],"basis":[137],"an":[139],"unsupervised":[140],"reconstruction":[141],"objective.":[142],"establish":[144],"zero-shot":[146,204],"adaptation":[147],"procedure":[148],"enable":[150],"agent":[152],"changes.":[158],"provide":[160],"benchmark":[162],"with":[163,180,203],"qualitatively":[164],"distinct":[165],"based":[167],"half-cheetah":[170],"environment":[171],"demonstrate":[173],"superior":[175],"performance":[176],"TIGR":[178],"compared":[179],"terms":[185],"sample":[187],"efficiency":[188],"(three":[189],"ten":[191],"times":[192],"faster),":[193],"asymptotic":[194],"performance,":[195],"applicability":[197],"environments":[202],"adaptation.":[205],"Videos":[206],"can":[207],"be":[208],"viewed":[209],"at":[210],"https://videoviewsite.wixsite.com/tigr.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}