{"id":"https://openalex.org/W3198015624","doi":"https://doi.org/10.1109/tnnls.2021.3105407","title":"Meta-Reinforcement Learning With Dynamic Adaptiveness Distillation","display_name":"Meta-Reinforcement Learning With Dynamic Adaptiveness Distillation","publication_year":2021,"publication_date":"2021-08-31","ids":{"openalex":"https://openalex.org/W3198015624","doi":"https://doi.org/10.1109/tnnls.2021.3105407","mag":"3198015624","pmid":"https://pubmed.ncbi.nlm.nih.gov/34464267"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3105407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3105407","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026968126","display_name":"H. Hu","orcid":"https://orcid.org/0000-0002-9825-8186"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangkai Hu","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9825-8186","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013240918","display_name":"Gao Huang","orcid":"https://orcid.org/0000-0002-7251-0988"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao Huang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7251-0988","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331032","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-0699-1904"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0699-1904","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068624597","display_name":"Shiji Song","orcid":"https://orcid.org/0000-0001-7361-9283"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiji Song","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7361-9283","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8189,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.7806293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"34","issue":"3","first_page":"1454","last_page":"1464"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9926999807357788,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6932531595230103},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.596206784248352},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5313119888305664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5050089955329895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3965233564376831},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32620352506637573},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2506452798843384},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10473152995109558},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10366538166999817},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.08092352747917175}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6932531595230103},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.596206784248352},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5313119888305664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5050089955329895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3965233564376831},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32620352506637573},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2506452798843384},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10473152995109558},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10366538166999817},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.08092352747917175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3105407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3105407","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:34464267","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34464267","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}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1198472114","display_name":null,"funder_award_id":"61803321","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3236263913","display_name":null,"funder_award_id":"2018AAA0101604","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G6609410551","display_name":null,"funder_award_id":"2018AAA0101604","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G6879802318","display_name":null,"funder_award_id":"61906106","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8753403390","display_name":null,"funder_award_id":"62022048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1486056878","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2790355818","https://openalex.org/W2892979040","https://openalex.org/W2963523627","https://openalex.org/W2966461828","https://openalex.org/W2997289589","https://openalex.org/W3035524453","https://openalex.org/W6637967152","https://openalex.org/W6687681856","https://openalex.org/W6717230150","https://openalex.org/W6729433768","https://openalex.org/W6731982132","https://openalex.org/W6735033012","https://openalex.org/W6736057607","https://openalex.org/W6740472315","https://openalex.org/W6742288159","https://openalex.org/W6747473740","https://openalex.org/W6747625265","https://openalex.org/W6747943641","https://openalex.org/W6748317118","https://openalex.org/W6748600884","https://openalex.org/W6750254146","https://openalex.org/W6754471908","https://openalex.org/W6755476724","https://openalex.org/W6755654293","https://openalex.org/W6756303580","https://openalex.org/W6756463683","https://openalex.org/W6757560991","https://openalex.org/W6760698134","https://openalex.org/W6761008914","https://openalex.org/W6767629743","https://openalex.org/W6768602481","https://openalex.org/W6774410480","https://openalex.org/W6991064601"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,16],"is":[3],"confronted":[4],"with":[5,77],"problems":[6],"of":[7,47,87,120],"sampling":[8],"inefficiency":[9],"and":[10,29,49,59,124],"poor":[11],"task":[12],"migration":[13],"capability.":[14],"Meta-reinforcement":[15],"(meta-RL)":[17],"enables":[18,113],"meta-learners":[19,76,101,115],"to":[20,32,84,97,116],"utilize":[21],"the":[22,42,75,85,100,103,107,114,118],"task-solving":[23],"skills":[24],"trained":[25],"on":[26],"similar":[27],"tasks":[28],"quickly":[30],"adapt":[31,83],"new":[33],"tasks.":[34,88],"However,":[35],"meta-RL":[36,71],"methods":[37],"lack":[38],"enough":[39],"queries":[40],"toward":[41,80],"relationship":[43],"between":[44],"task-agnostic":[45,121],"exploitation":[46],"data":[48],"task-related":[50,125],"knowledge":[51],"introduced":[52],"by":[53],"latent":[54,128],"context,":[55],"limiting":[56],"their":[57],"effectiveness":[58],"generalization":[60],"ability.":[61],"In":[62,89,131],"this":[63],"article,":[64],"we":[65,92],"develop":[66],"an":[67],"algorithm":[68],"for":[69,144],"off-policy":[70],"that":[72],"can":[73],"provide":[74],"self-oriented":[78,122],"cognition":[79],"how":[81,99],"they":[82],"family":[86],"our":[90,132,134],"approach,":[91],"perform":[93],"dynamic":[94],"task-adaptiveness":[95],"distillation":[96],"describe":[98],"adjust":[102],"exploration":[104],"strategy":[105],"in":[106],"meta-training":[108],"process.":[109],"Our":[110],"approach":[111],"also":[112],"balance":[117],"influence":[119],"adaption":[123],"information":[126],"through":[127],"context":[129],"reorganization.":[130],"experiments,":[133],"method":[135],"achieves":[136],"10%-20%":[137],"higher":[138],"asymptotic":[139],"reward":[140],"than":[141],"probabilistic":[142],"embeddings":[143],"actor-critic":[145],"RL":[146],"(PEARL).":[147]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}