{"id":"https://openalex.org/W4394627413","doi":"https://doi.org/10.1109/tpami.2024.3386780","title":"Context-Based Meta-Reinforcement Learning With Bayesian Nonparametric Models","display_name":"Context-Based Meta-Reinforcement Learning With Bayesian Nonparametric Models","publication_year":2024,"publication_date":"2024-04-09","ids":{"openalex":"https://openalex.org/W4394627413","doi":"https://doi.org/10.1109/tpami.2024.3386780","pmid":"https://pubmed.ncbi.nlm.nih.gov/38593010"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3386780","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3386780","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/4359286/10495171.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/34/4359286/10495171.pdf","any_repository_has_fulltext":false},"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, München, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0896-2517","affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, München, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101206794","display_name":"Yuqi Yun","orcid":"https://orcid.org/0009-0006-4397-1538"},"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":"Yuqi Yun","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, München, Germany"],"raw_orcid":"https://orcid.org/0009-0006-4397-1538","affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, München, 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 Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0359-7810","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, 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, München, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4840-076X","affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, München, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.89,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.91412891,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"46","issue":"10","first_page":"6948","last_page":"6965"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9934999942779541,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9934999942779541,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9751999974250793,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9703999757766724,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7232296466827393},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6857602000236511},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6701604127883911},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6081359386444092},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5896106958389282},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5627242922782898},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.5497666597366333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32200920581817627},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18430998921394348},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.16805195808410645}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7232296466827393},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6857602000236511},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6701604127883911},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6081359386444092},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5896106958389282},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5627242922782898},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.5497666597366333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32200920581817627},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18430998921394348},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.16805195808410645},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3386780","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3386780","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/4359286/10495171.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:38593010","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38593010","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}],"best_oa_location":{"id":"doi:10.1109/tpami.2024.3386780","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3386780","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/4359286/10495171.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394627413.pdf","grobid_xml":"https://content.openalex.org/works/W4394627413.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W2007339694","https://openalex.org/W2069429561","https://openalex.org/W2115870554","https://openalex.org/W2127498532","https://openalex.org/W2151967501","https://openalex.org/W2162021827","https://openalex.org/W2187089797","https://openalex.org/W2500228126","https://openalex.org/W2556467266","https://openalex.org/W2578206533","https://openalex.org/W2730106296","https://openalex.org/W2777922598","https://openalex.org/W2904246096","https://openalex.org/W2904861519","https://openalex.org/W2938321354","https://openalex.org/W2962974944","https://openalex.org/W2963887494","https://openalex.org/W2965787265","https://openalex.org/W2980555752","https://openalex.org/W2990500698","https://openalex.org/W3037897643","https://openalex.org/W3046093665","https://openalex.org/W3047868264","https://openalex.org/W3058625773","https://openalex.org/W3176613769","https://openalex.org/W4283365039","https://openalex.org/W4288024349","https://openalex.org/W4289388948","https://openalex.org/W4298222718","https://openalex.org/W4300971732","https://openalex.org/W6679688910","https://openalex.org/W6685380521","https://openalex.org/W6723243674","https://openalex.org/W6729433768","https://openalex.org/W6730333270","https://openalex.org/W6731412260","https://openalex.org/W6731982132","https://openalex.org/W6736057607","https://openalex.org/W6745777752","https://openalex.org/W6755476724","https://openalex.org/W6756463683","https://openalex.org/W6757223306","https://openalex.org/W6757592117","https://openalex.org/W6760698134","https://openalex.org/W6764998394","https://openalex.org/W6769269530","https://openalex.org/W6769596995","https://openalex.org/W6770196601","https://openalex.org/W6774268721","https://openalex.org/W6780559895","https://openalex.org/W6781695082","https://openalex.org/W6790269317","https://openalex.org/W6824062597"],"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/W4296826658","https://openalex.org/W1979697693","https://openalex.org/W2164312800"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,21],"agents":[3],"usually":[4],"need":[5],"to":[6,13,24,27,55,77,96,102,128,163,182,217],"collect":[7],"a":[8,15,31,43,62,81,132,137,173,207,212,244],"large":[9],"number":[10],"of":[11,34,45,83,148,188],"interactions":[12],"solve":[14],"single":[16],"task.":[17],"In":[18,203],"contrast,":[19],"meta-reinforcement":[20],"(meta-RL)":[22],"aims":[23],"quickly":[25],"adapt":[26],"new":[28,129],"tasks":[29,125,130,171,234],"using":[30,196],"small":[32],"amount":[33],"experience":[35],"by":[36],"leveraging":[37],"the":[38,53,57,66,86,90,103,152,159,170,185,189,219],"knowledge":[39],"from":[40],"training":[41],"on":[42,65,144],"set":[44],"similar":[46],"tasks.":[47],"State-of-the-art":[48],"context-based":[49],"meta-RL":[50,264],"algorithms":[51],"use":[52],"context":[54,214],"encode":[56],"task":[58,69,91,166,191,249],"information":[59],"and":[60,93,126,158,168,211,222,238,247,252,258],"train":[61],"policy":[63],"conditioned":[64],"inferred":[67],"latent":[68,250],"encoding.":[70],"However,":[71],"most":[72],"recent":[73],"works":[74],"are":[75],"limited":[76],"parametric":[78,237],"tasks,":[79],"where":[80],"handful":[82],"variables":[84,200],"control":[85,233],"full":[87],"variation":[88],"in":[89,98,131,172,227],"distribution,":[92,192],"also":[94,253],"failed":[95],"work":[97],"non-stationary":[99,228],"environments":[100],"due":[101],"few-shot":[104],"adaptation":[105,209],"setting.":[106],"To":[107],"address":[108],"those":[109],"limitations,":[110],"we":[111,205],"propose":[112,206],"MEta-reinforcement":[113],"Learning":[114],"with":[115,235,262],"Task":[116],"Self-discovery":[117],"(MELTS),":[118],"which":[119,150,193],"adaptively":[120,183],"learns":[121],"qualitatively":[122],"different":[123],"nonparametric":[124,190,239],"adapts":[127],"zero-shot":[133,208],"manner.":[134],"We":[135],"introduce":[136],"novel":[138],"deep":[139],"clustering":[140],"framework":[141],"(DPMM-VAE)":[142],"based":[143],"an":[145],"infinite":[146],"mixture":[147,155],"Gaussians,":[149],"combines":[151],"Dirichlet":[153],"process":[154],"model":[156],"(DPMM)":[157],"variational":[160],"autoencoder":[161],"(VAE),":[162],"simultaneously":[164],"learn":[165],"representations":[167],"cluster":[169],"self-adaptive":[174,248],"way.":[175],"Integrating":[176],"DPMM-VAE":[177],"into":[178],"MELTS":[179],"enables":[180],"it":[181],"discover":[184],"multi-modal":[186],"structure":[187],"previous":[194],"methods":[195],"isotropic":[197],"Gaussian":[198],"random":[199],"cannot":[201],"model.":[202],"addition,":[204],"mechanism":[210],"recurrence-based":[213],"encoding":[215],"strategy":[216],"improve":[218],"data":[220],"efficiency":[221,257],"make":[223],"our":[224,241],"algorithm":[225,242],"applicable":[226],"environments.":[229],"On":[230],"various":[231],"continuous":[232],"both":[236],"variations,":[240],"produces":[243],"more":[245],"structured":[246],"space":[251],"achieves":[254],"superior":[255],"sample":[256],"asymptotic":[259],"performance":[260],"compared":[261],"state-of-the-art":[263],"algorithms.":[265]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}