{"id":"https://openalex.org/W7123340430","doi":"https://doi.org/10.1109/cdc57313.2025.11312186","title":"Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning","display_name":"Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123340430","doi":"https://doi.org/10.1109/cdc57313.2025.11312186"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5122895754","display_name":"Donglin Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donglin Zhan","raw_affiliation_strings":["Columbia University,Department of Electrical Engineering,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,Department of Electrical Engineering,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048610577","display_name":"Leonardo Toso","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonardo F. Toso","raw_affiliation_strings":["Columbia University,Department of Electrical Engineering,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,Department of Electrical Engineering,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":null,"display_name":"James Anderson","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Anderson","raw_affiliation_strings":["Columbia University,Department of Electrical Engineering,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,Department of Electrical Engineering,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":5.0304,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.961716,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4167","last_page":"4173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.42649999260902405,"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":0.42649999260902405,"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":0.14339999854564667,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.07419999688863754,"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/redundancy","display_name":"Redundancy (engineering)","score":0.6158999800682068},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5839999914169312},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5364000201225281},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.39239999651908875},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3865000009536743},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3840999901294708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.673799991607666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6168000102043152},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6158999800682068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6014000177383423},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5839999914169312},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5364000201225281},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3865000009536743},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.32739999890327454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W45588701","https://openalex.org/W1680189815","https://openalex.org/W2107411554","https://openalex.org/W2149479912","https://openalex.org/W2158782408","https://openalex.org/W2963614114","https://openalex.org/W3098412154","https://openalex.org/W3130568950","https://openalex.org/W4206699377","https://openalex.org/W4310238750","https://openalex.org/W4312585885","https://openalex.org/W4391019913","https://openalex.org/W4391020659","https://openalex.org/W4402917091","https://openalex.org/W4407949646","https://openalex.org/W4409364165","https://openalex.org/W7123340430"],"related_works":[],"abstract_inverted_index":{"We":[0,158],"study":[1],"how":[2,54],"task":[3,28,42,69,113,147,172],"selection":[4,43,70,114,148,173],"can":[5,25],"enhance":[6],"sample":[7,121],"efficiency":[8],"in":[9,58],"model-agnostic":[10],"meta-reinforcement":[11],"learning.":[12],"Traditional":[13],"meta-RL":[14],"typically":[15],"assumes":[16],"that":[17,45],"all":[18],"available":[19],"tasks":[20,51,98],"are":[21,57],"equally":[22],"important,":[23],"which":[24],"lead":[26],"to":[27,77,96,115,125],"redundancy":[29],"when":[30,134],"they":[31,56],"share":[32],"significant":[33],"similarities.":[34],"To":[35],"address":[36],"this,":[37],"we":[38,111],"propose":[39],"a":[40,47,84,93,108,120,150],"coreset-based":[41],"approach":[44],"selects":[46],"weighted":[48],"subset":[49],"of":[50,74,86,171],"based":[52],"on":[53,102],"diverse":[55,66],"gradient":[59,140],"space,":[60],"prioritizing":[61],"the":[62,72,103,139,169,175],"most":[63,104],"informative":[64],"and":[65,118,155],"tasks.":[67,106],"Such":[68],"reduces":[71],"number":[73],"samples":[75],"needed":[76],"find":[78],"an":[79],"\u03f5-close":[80],"stationary":[81],"solution":[82],"by":[83],"factor":[85],"$\\mathcal{O}(1/":[87],"\\in":[88,130],")$.":[89],"Consequently,":[90],"it":[91],"guarantees":[92,145],"faster":[94],"adaptation":[95],"unseen":[97],"while":[99],"focusing":[100],"training":[101],"relevant":[105],"As":[107],"case":[109],"study,":[110],"incorporate":[112],"MAML-LQR":[116],"[1],":[117],"prove":[119],"complexity":[122],"reduction":[123],"proportional":[124],"$\\mathcal{O}\\left(":[126],"{\\log":[127],"\\left(":[128],"{1/":[129],"}":[131],"\\right)}":[132],"\\right)$":[133],"task-specific":[135],"costs":[136],"also":[137],"satisfy":[138],"dominance":[141],"property.":[142],"Our":[143],"theoretical":[144],"underscore":[146],"as":[149],"key":[151],"component":[152],"for":[153],"scalable":[154],"sample-efficient":[156],"meta-RL.":[157],"numerically":[159],"validate":[160],"this":[161],"trend":[162],"across":[163],"multiple":[164],"RL":[165],"benchmark":[166],"problems,":[167],"illustrating":[168],"benefits":[170],"beyond":[174],"LQR":[176],"baseline.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-14T00:00:00"}