{"id":"https://openalex.org/W4401596665","doi":"https://doi.org/10.1109/lra.2024.3443496","title":"Unsupervised Meta-Testing With Conditional Neural Processes for Hybrid Meta-Reinforcement Learning","display_name":"Unsupervised Meta-Testing With Conditional Neural Processes for Hybrid Meta-Reinforcement Learning","publication_year":2024,"publication_date":"2024-08-14","ids":{"openalex":"https://openalex.org/W4401596665","doi":"https://doi.org/10.1109/lra.2024.3443496"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3443496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3443496","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.04399","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043035757","display_name":"Suzan Ece Ada","orcid":"https://orcid.org/0000-0003-1901-8473"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Suzan Ece Ada","raw_affiliation_strings":["Department of Computer Engineering, Bogazici University, Istanbul, Türkiye"],"raw_orcid":"https://orcid.org/0000-0003-1901-8473","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bogazici University, Istanbul, Türkiye","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048165304","display_name":"Emre U\u011fur","orcid":"https://orcid.org/0000-0001-9597-2731"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Emre Ugur","raw_affiliation_strings":["Department of Computer Engineering, Bogazici University, Istanbul, Türkiye"],"raw_orcid":"https://orcid.org/0000-0001-9597-2731","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bogazici University, Istanbul, Türkiye","institution_ids":["https://openalex.org/I4405392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043035757"],"corresponding_institution_ids":["https://openalex.org/I4405392"],"apc_list":null,"apc_paid":null,"fwci":1.2621,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79706749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"9","issue":"10","first_page":"8427","last_page":"8434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9861000180244446,"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"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9861000180244446,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9825999736785889,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9779000282287598,"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/meta-learning","display_name":"Meta learning (computer science)","score":0.6331197023391724},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.623281717300415},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5906180143356323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5082904696464539},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.482636034488678},{"id":"https://openalex.org/keywords/meta-analysis","display_name":"Meta-analysis","score":0.4495500326156616},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42350947856903076},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4133192002773285},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2762548327445984},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08199048042297363},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.06391662359237671},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.061604470014572144}],"concepts":[{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.6331197023391724},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.623281717300415},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5906180143356323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5082904696464539},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.482636034488678},{"id":"https://openalex.org/C95190672","wikidata":"https://www.wikidata.org/wiki/Q815382","display_name":"Meta-analysis","level":2,"score":0.4495500326156616},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42350947856903076},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4133192002773285},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2762548327445984},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08199048042297363},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.06391662359237671},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.061604470014572144},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/lra.2024.3443496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3443496","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2506.04399","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.04399","pdf_url":"https://arxiv.org/pdf/2506.04399","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:zenodo.org:14651097","is_oa":true,"landing_page_url":"https://doi.org/10.1109/LRA.2024.3443496","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.04399","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.04399","pdf_url":"https://arxiv.org/pdf/2506.04399","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2073787051","https://openalex.org/W2158782408","https://openalex.org/W2736601468","https://openalex.org/W2742093937","https://openalex.org/W2770616710","https://openalex.org/W2903630557","https://openalex.org/W2965567119","https://openalex.org/W3175254947","https://openalex.org/W3211889820","https://openalex.org/W4280638670","https://openalex.org/W4298857966","https://openalex.org/W4309500176","https://openalex.org/W4312633720","https://openalex.org/W4317670814","https://openalex.org/W4360584316","https://openalex.org/W4392244955","https://openalex.org/W6627932998","https://openalex.org/W6637967152","https://openalex.org/W6640963894","https://openalex.org/W6735944222","https://openalex.org/W6736057607","https://openalex.org/W6741002519","https://openalex.org/W6742288159","https://openalex.org/W6747943641","https://openalex.org/W6748600884","https://openalex.org/W6751494529","https://openalex.org/W6752040014","https://openalex.org/W6755476724","https://openalex.org/W6758711939","https://openalex.org/W6760036574","https://openalex.org/W6760698134","https://openalex.org/W6767291801","https://openalex.org/W6769269530","https://openalex.org/W6777635358","https://openalex.org/W6780559895","https://openalex.org/W6844225899","https://openalex.org/W6846147591","https://openalex.org/W6846514807","https://openalex.org/W6849169497","https://openalex.org/W6850848110"],"related_works":["https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W3203657119","https://openalex.org/W2891227010","https://openalex.org/W2964032613","https://openalex.org/W2796429358","https://openalex.org/W4387891205","https://openalex.org/W2895106137","https://openalex.org/W3139344044","https://openalex.org/W2963154787"],"abstract_inverted_index":{"We":[0,129],"introduce":[1],"Unsupervised":[2],"Meta-Testing":[3],"with":[4,110,124,159,166],"Conditional":[5,61],"Neural":[6,62],"Processes":[7,63],"(UMCNP),":[8],"a":[9,105],"novel":[10],"hybrid":[11],"few-shot":[12,30],"meta-reinforcement":[13],"learning":[14,87],"(meta-RL)":[15],"method":[16,44,132],"that":[17],"uniquely":[18],"combines,":[19],"yet":[20],"distinctly":[21],"separates,":[22],"parameterized":[23],"policy":[24],"gradient-based":[25],"(PPG)":[26],"and":[27,58,152],"task":[28,88,108,139],"inference-based":[29],"meta-RL.":[31],"Tailored":[32],"for":[33,86,120],"settings":[34],"where":[35],"the":[36,56,67,96,100,125,147],"reward":[37],"signal":[38],"is":[39],"missing":[40],"during":[41,144],"meta-testing,":[42],"our":[43,131],"increases":[45],"sample":[46],"efficiency":[47,57],"without":[48],"requiring":[49],"additional":[50],"samples":[51,77,143],"in":[52,73,90,149],"meta-training.":[53],"UMCNP":[54,94],"leverages":[55],"scalability":[59],"of":[60,69,99],"(CNPs)":[64],"to":[65,117,135],"reduce":[66],"number":[68],"online":[70],"interactions":[71],"required":[72],"meta-testing.":[74],"During":[75],"meta-training,":[76],"previously":[78],"collected":[79],"through":[80],"PPG":[81],"meta-RL":[82,155],"are":[83],"efficiently":[84],"reused":[85],"inference":[89],"an":[91,136],"offline":[92],"manner.":[93],"infers":[95],"latent":[97],"representation":[98],"transition":[101],"dynamics":[102,127,168],"model":[103],"from":[104],"single":[106],"test":[107,138],"rollout":[109],"unknown":[111,160],"parameters.":[112,169],"This":[113],"approach":[114],"allows":[115],"us":[116],"generate":[118],"rollouts":[119],"self-adaptation":[121],"by":[122],"interacting":[123],"learned":[126],"model.":[128],"demonstrate":[130],"can":[133],"adapt":[134],"unseen":[137],"using":[140],"significantly":[141],"fewer":[142],"meta-testing":[145],"than":[146],"baselines":[148],"2D-Point":[150],"Agent":[151],"continuous":[153],"control":[154],"benchmarks,":[156],"namely,":[157],"cartpole":[158],"angle":[161],"sensor":[162],"bias,":[163],"walker":[164],"agent":[165],"randomized":[167]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}