{"id":"https://openalex.org/W4283365039","doi":"https://doi.org/10.1109/tpami.2022.3185549","title":"Meta-Reinforcement Learning in Non-Stationary and Dynamic Environments","display_name":"Meta-Reinforcement Learning in Non-Stationary and Dynamic Environments","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4283365039","doi":"https://doi.org/10.1109/tpami.2022.3185549","pmid":"https://pubmed.ncbi.nlm.nih.gov/35737617"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3185549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3185549","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/1662422","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":true,"raw_author_name":"Zhenshan Bing","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany"],"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/A5024321232","display_name":"David Lerch","orcid":"https://orcid.org/0000-0002-2348-6280"},"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":"David Lerch","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany"],"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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Huang","raw_affiliation_strings":["Sun Yat-sen University, Shenzhen, China","Guangzhou and Peng cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Guangzhou and Peng cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"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"],"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":4,"corresponding_author_ids":["https://openalex.org/A5060444894"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":8.2738,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.97946999,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"45","issue":"3","first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9890000224113464,"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/T12810","display_name":"Real-time simulation and control systems","score":0.9876000285148621,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8896275162696838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8415114879608154},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.623191237449646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6168510913848877},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5307801961898804},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5212339162826538},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.5191899538040161},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5165694952011108},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5059308409690857}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8896275162696838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8415114879608154},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.623191237449646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6168510913848877},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5307801961898804},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5212339162826538},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.5191899538040161},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5165694952011108},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5059308409690857},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2022.3185549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3185549","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:35737617","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35737617","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 pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:mediatum.ub.tum.de:node/1662422","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1662422","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of 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/1662422","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1662422","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of 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":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2158782408","https://openalex.org/W2519091744","https://openalex.org/W2578206533","https://openalex.org/W2604763608","https://openalex.org/W2787501667","https://openalex.org/W2788904251","https://openalex.org/W2904861519","https://openalex.org/W2945020056","https://openalex.org/W2951595529","https://openalex.org/W2952526277","https://openalex.org/W2962854145","https://openalex.org/W2962974944","https://openalex.org/W2963887494","https://openalex.org/W2966461828","https://openalex.org/W2981344907","https://openalex.org/W3037897643","https://openalex.org/W4289388948","https://openalex.org/W4300971732","https://openalex.org/W4385245566","https://openalex.org/W6638836233","https://openalex.org/W6640963894","https://openalex.org/W6692846177","https://openalex.org/W6729433768","https://openalex.org/W6731982132","https://openalex.org/W6736057607","https://openalex.org/W6739901393","https://openalex.org/W6745777752","https://openalex.org/W6747473740","https://openalex.org/W6747943641","https://openalex.org/W6748566876","https://openalex.org/W6748600884","https://openalex.org/W6751659697","https://openalex.org/W6755476724","https://openalex.org/W6756463683","https://openalex.org/W6757223306","https://openalex.org/W6760698134","https://openalex.org/W6762959241","https://openalex.org/W6763197473","https://openalex.org/W6769596995","https://openalex.org/W6774268721","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","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":{"In":[0,118],"recent":[1,100],"years,":[2],"the":[3,91],"subject":[4],"of":[5,38,56,77,83],"deep":[6],"reinforcement":[7],"learning":[8,58,94,208,211],"(DRL)":[9],"has":[10,60],"developed":[11],"very":[12,51],"rapidly,":[13],"and":[14,25,108,125,183,222],"is":[15,102,131,167],"now":[16],"applied":[17],"in":[18,187,200,226],"various":[19],"fields,":[20],"such":[21],"as":[22,136,138,203,205],"decision":[23],"making":[24],"control":[26,160],"tasks.":[27,233],"However,":[28],"artificial":[29],"agents":[30,66],"trained":[31],"with":[32,85,96,163,173,190,229],"RL":[33],"algorithms":[34],"require":[35],"great":[36],"amounts":[37],"training":[39,128],"data,":[40],"unlike":[41],"humans":[42],"that":[43,130,166],"are":[44],"able":[45],"to":[46,64,67,90,104,133,147,170,197],"learn":[47,68],"new":[48,71],"skills":[49,72],"from":[50,73],"few":[52],"examples.":[53],"The":[54],"concept":[55],"meta-reinforcement":[57],"(meta-RL)":[59],"been":[61],"recently":[62],"proposed":[63],"enable":[65],"similar":[69],"but":[70],"a":[74,81,86,127,139,206],"small":[75],"amount":[76],"experience":[78],"by":[79],"leveraging":[80],"set":[82],"tasks":[84,112],"shared":[87],"structure.":[88],"Due":[89],"task":[92,106,140,150,213,224,227],"representation":[93,141],"strategy":[95,129],"few-shot":[97,174],"adaptation,":[98],"most":[99],"work":[101],"limited":[103],"narrow":[105],"distributions":[107,228],"stationary":[109,171,188],"environments,":[110,135],"where":[111],"do":[113],"not":[114],"change":[115],"within":[116],"episodes.":[117],"this":[119],"work,":[120],"we":[121],"address":[122],"those":[123],"limitations":[124],"introduce":[126],"applicable":[132,169],"non-stationary":[134,201],"well":[137,204],"based":[142],"on":[143,156],"Gaussian":[144],"mixture":[145],"models":[146],"model":[148],"clustered":[149],"distributions.":[151],"We":[152],"evaluate":[153],"our":[154,176,194,216],"method":[155],"several":[157],"continuous":[158],"robotic":[159],"benchmarks.":[161],"Compared":[162],"state-of-the-art":[164],"literature":[165],"only":[168],"environments":[172,189],"adaption,":[175],"algorithm":[177,195,217],"first":[178],"achieves":[179],"competitive":[180],"asymptotic":[181],"performance":[182],"superior":[184],"sample":[185],"efficiency":[186],"zero-shot":[191],"adaption.":[192],"Second,":[193],"learns":[196,218],"perform":[198],"successfully":[199],"settings":[202],"continual":[207],"setting,":[209],"while":[210],"well-structured":[212,223],"representations.":[214],"Last,":[215],"basic":[219],"distinct":[220,232],"behaviors":[221],"representations":[225],"multiple":[230],"qualitatively":[231]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}