<> <http://www.w3.org/2000/01/rdf-schema#comment> "The repository administrator has not yet configured an RDF license."^^<http://www.w3.org/2001/XMLSchema#string> .
<> <http://xmlns.com/foaf/0.1/primaryTopic> <https://discovery.ucl.ac.uk/id/eprint/10083560> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/ontology/bibo/Article> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/dc/terms/title> "Meta reinforcement learning with latent variable Gaussian processes"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/ontology/bibo/abstract> "Learning from small data sets is critical in many practical applications where data collection is time consuming or expensive, e.g., robotics, animal experiments or drug design. Meta learning is one way to increase the data efficiency of learning algorithms by generalizing learned concepts from a set of training tasks to unseen, but related, tasks. Often, this relationship between tasks is hard coded or relies in some other way on human expertise. In this paper, we frame meta learning as a hierarchical latent variable model and infer the relationship between tasks automatically from data. We apply our framework in a modelbased reinforcement learning setting and show that our meta-learning model effectively generalizes to novel tasks by identifying how new tasks relate to prior ones from minimal data. This results in up to a 60% reduction in the average interaction time needed to solve tasks compared to strong baselines."^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/dc/terms/date> "2018-08-06" .
<https://discovery.ucl.ac.uk/id/document/986869> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/ontology/bibo/Document> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/ontology/bibo/volume> "34" .
<https://discovery.ucl.ac.uk/id/org/ext-7aa3a61e56bb04e13e2b12e81642656a> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Organization> .
<https://discovery.ucl.ac.uk/id/org/ext-7aa3a61e56bb04e13e2b12e81642656a> <http://xmlns.com/foaf/0.1/name> "Association for Uncertainty in Artificial Intelligence (AUAI)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/dc/terms/publisher> <https://discovery.ucl.ac.uk/id/org/ext-7aa3a61e56bb04e13e2b12e81642656a> .
<https://discovery.ucl.ac.uk/id/publication/ext-221970f9eceac64ae9ea14c13a207f13> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/ontology/bibo/Collection> .
<https://discovery.ucl.ac.uk/id/publication/ext-221970f9eceac64ae9ea14c13a207f13> <http://xmlns.com/foaf/0.1/name> "34th Conference on Uncertainty in Artificial Intelligence 2018, UAI 2018"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/dc/terms/isPartOf> <https://discovery.ucl.ac.uk/id/publication/ext-221970f9eceac64ae9ea14c13a207f13> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/ontology/bibo/status> <http://purl.org/ontology/bibo/status/published> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/dc/terms/creator> <https://discovery.ucl.ac.uk/id/person/ext-6030d191e52045afbc1fffb94bb1ec4e> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/ontology/bibo/authorList> <https://discovery.ucl.ac.uk/id/eprint/10083560#authors> .
<https://discovery.ucl.ac.uk/id/eprint/10083560#authors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_1> <https://discovery.ucl.ac.uk/id/person/ext-6030d191e52045afbc1fffb94bb1ec4e> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/dc/terms/creator> <https://discovery.ucl.ac.uk/id/person/ext-5dd52a9c1e4ad4bf463ac44c41fdb135> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/ontology/bibo/authorList> <https://discovery.ucl.ac.uk/id/eprint/10083560#authors> .
<https://discovery.ucl.ac.uk/id/eprint/10083560#authors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_2> <https://discovery.ucl.ac.uk/id/person/ext-5dd52a9c1e4ad4bf463ac44c41fdb135> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/dc/terms/creator> <https://discovery.ucl.ac.uk/id/person/ext-305543b9a468f38beddf5dc967dbe156> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/ontology/bibo/authorList> <https://discovery.ucl.ac.uk/id/eprint/10083560#authors> .
<https://discovery.ucl.ac.uk/id/eprint/10083560#authors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_3> <https://discovery.ucl.ac.uk/id/person/ext-305543b9a468f38beddf5dc967dbe156> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://www.loc.gov/loc.terms/relators/EDT> <https://discovery.ucl.ac.uk/id/person/ext-af96c6599e6d395c1cd445691ac6b7bf> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/ontology/bibo/editorList> <https://discovery.ucl.ac.uk/id/eprint/10083560#editors> .
<https://discovery.ucl.ac.uk/id/eprint/10083560#editors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_1> <https://discovery.ucl.ac.uk/id/person/ext-af96c6599e6d395c1cd445691ac6b7bf> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://www.loc.gov/loc.terms/relators/EDT> <https://discovery.ucl.ac.uk/id/person/ext-c829c9123fbd0c2d2012083e409d63f5> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/ontology/bibo/editorList> <https://discovery.ucl.ac.uk/id/eprint/10083560#editors> .
<https://discovery.ucl.ac.uk/id/eprint/10083560#editors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_2> <https://discovery.ucl.ac.uk/id/person/ext-c829c9123fbd0c2d2012083e409d63f5> .
<https://discovery.ucl.ac.uk/id/person/ext-5dd52a9c1e4ad4bf463ac44c41fdb135> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Person> .
<https://discovery.ucl.ac.uk/id/person/ext-5dd52a9c1e4ad4bf463ac44c41fdb135> <http://xmlns.com/foaf/0.1/givenName> "K"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-5dd52a9c1e4ad4bf463ac44c41fdb135> <http://xmlns.com/foaf/0.1/familyName> "Hofmann"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-5dd52a9c1e4ad4bf463ac44c41fdb135> <http://xmlns.com/foaf/0.1/name> "K Hofmann"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-af96c6599e6d395c1cd445691ac6b7bf> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Person> .
<https://discovery.ucl.ac.uk/id/person/ext-af96c6599e6d395c1cd445691ac6b7bf> <http://xmlns.com/foaf/0.1/givenName> "G"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-af96c6599e6d395c1cd445691ac6b7bf> <http://xmlns.com/foaf/0.1/familyName> "Elidan"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-af96c6599e6d395c1cd445691ac6b7bf> <http://xmlns.com/foaf/0.1/name> "G Elidan"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-305543b9a468f38beddf5dc967dbe156> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Person> .
<https://discovery.ucl.ac.uk/id/person/ext-305543b9a468f38beddf5dc967dbe156> <http://xmlns.com/foaf/0.1/givenName> "MP"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-305543b9a468f38beddf5dc967dbe156> <http://xmlns.com/foaf/0.1/familyName> "Deisenroth"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-305543b9a468f38beddf5dc967dbe156> <http://xmlns.com/foaf/0.1/name> "MP Deisenroth"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-c829c9123fbd0c2d2012083e409d63f5> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Person> .
<https://discovery.ucl.ac.uk/id/person/ext-c829c9123fbd0c2d2012083e409d63f5> <http://xmlns.com/foaf/0.1/givenName> "K"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-c829c9123fbd0c2d2012083e409d63f5> <http://xmlns.com/foaf/0.1/familyName> "Kersting"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-c829c9123fbd0c2d2012083e409d63f5> <http://xmlns.com/foaf/0.1/name> "K Kersting"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-6030d191e52045afbc1fffb94bb1ec4e> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Person> .
<https://discovery.ucl.ac.uk/id/person/ext-6030d191e52045afbc1fffb94bb1ec4e> <http://xmlns.com/foaf/0.1/givenName> "S"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-6030d191e52045afbc1fffb94bb1ec4e> <http://xmlns.com/foaf/0.1/familyName> "Sæmundsson"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-6030d191e52045afbc1fffb94bb1ec4e> <http://xmlns.com/foaf/0.1/name> "S Sæmundsson"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/ontology/bibo/Article> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/ontology/bibo/presentedAt> <https://discovery.ucl.ac.uk/id/event/ext-36af485bff5bb20f0a2099b1c018e3c2> .
<https://discovery.ucl.ac.uk/id/event/ext-36af485bff5bb20f0a2099b1c018e3c2> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/ontology/bibo/Conference> .
<https://discovery.ucl.ac.uk/id/event/ext-36af485bff5bb20f0a2099b1c018e3c2> <http://purl.org/dc/terms/title> "34th Conference on Uncertainty in Artificial Intelligence (uai 2018), 6-10 August 2018, Monterey, CA, USA"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/EPrint> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/ProceedingsSectionEPrint> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/dc/terms/isPartOf> <https://discovery.ucl.ac.uk/id/repository> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986869> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/986869> <http://www.w3.org/2000/01/rdf-schema#label> "Meta reinforcement learning with latent variable Gaussian processes (Text)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://purl.org/dc/elements/1.1/hasVersion> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://eprints.org/ontology/hasPublished> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986869> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10083560/1/Deisenroth_permitted%20VoR_235.pdf> .
<https://discovery.ucl.ac.uk/id/document/986869> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10083560/1/Deisenroth_permitted%20VoR_235.pdf> .
<https://discovery.ucl.ac.uk/id/eprint/10083560/1/Deisenroth_permitted%20VoR_235.pdf> <http://www.w3.org/2000/01/rdf-schema#label> "Deisenroth_permitted VoR_235.pdf"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/986870> .
<https://discovery.ucl.ac.uk/id/document/986870> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/986870> <http://www.w3.org/2000/01/rdf-schema#label> "Meta reinforcement learning with latent variable Gaussian processes (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/986870> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986870> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986870> <http://eprints.org/relation/islightboxThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986870> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10083560/2/lightbox.jpg> .
<https://discovery.ucl.ac.uk/id/document/986870> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10083560/2/lightbox.jpg> .
<https://discovery.ucl.ac.uk/id/eprint/10083560/2/lightbox.jpg> <http://www.w3.org/2000/01/rdf-schema#label> "lightbox.jpg"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/986871> .
<https://discovery.ucl.ac.uk/id/document/986871> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/986871> <http://www.w3.org/2000/01/rdf-schema#label> "Meta reinforcement learning with latent variable Gaussian processes (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/986871> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986871> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986871> <http://eprints.org/relation/ispreviewThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986871> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10083560/3/preview.jpg> .
<https://discovery.ucl.ac.uk/id/document/986871> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10083560/3/preview.jpg> .
<https://discovery.ucl.ac.uk/id/eprint/10083560/3/preview.jpg> <http://www.w3.org/2000/01/rdf-schema#label> "preview.jpg"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/986872> .
<https://discovery.ucl.ac.uk/id/document/986872> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/986872> <http://www.w3.org/2000/01/rdf-schema#label> "Meta reinforcement learning with latent variable Gaussian processes (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/986872> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986872> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986872> <http://eprints.org/relation/ismediumThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986872> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10083560/4/medium.jpg> .
<https://discovery.ucl.ac.uk/id/document/986872> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10083560/4/medium.jpg> .
<https://discovery.ucl.ac.uk/id/eprint/10083560/4/medium.jpg> <http://www.w3.org/2000/01/rdf-schema#label> "medium.jpg"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/986873> .
<https://discovery.ucl.ac.uk/id/document/986873> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/986873> <http://www.w3.org/2000/01/rdf-schema#label> "Meta reinforcement learning with latent variable Gaussian processes (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/986873> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986873> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986873> <http://eprints.org/relation/issmallThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986873> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10083560/5/small.jpg> .
<https://discovery.ucl.ac.uk/id/document/986873> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10083560/5/small.jpg> .
<https://discovery.ucl.ac.uk/id/eprint/10083560/5/small.jpg> <http://www.w3.org/2000/01/rdf-schema#label> "small.jpg"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/986874> .
<https://discovery.ucl.ac.uk/id/document/986874> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/986874> <http://www.w3.org/2000/01/rdf-schema#label> "Meta reinforcement learning with latent variable Gaussian processes (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/986874> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986874> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986874> <http://eprints.org/relation/isIndexCodesVersionOf> <https://discovery.ucl.ac.uk/id/document/986869> .
<https://discovery.ucl.ac.uk/id/document/986874> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10083560/6/indexcodes.txt> .
<https://discovery.ucl.ac.uk/id/document/986874> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10083560/6/indexcodes.txt> .
<https://discovery.ucl.ac.uk/id/eprint/10083560/6/indexcodes.txt> <http://www.w3.org/2000/01/rdf-schema#label> "indexcodes.txt"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10083560> <http://www.w3.org/2000/01/rdf-schema#seeAlso> <https://discovery.ucl.ac.uk/id/eprint/10083560/> .
<https://discovery.ucl.ac.uk/id/eprint/10083560/> <http://purl.org/dc/elements/1.1/title> "HTML Summary of #10083560 \n\nMeta reinforcement learning with latent variable Gaussian processes\n\n" .
<https://discovery.ucl.ac.uk/id/eprint/10083560/> <http://purl.org/dc/elements/1.1/format> "text/html" .
<https://discovery.ucl.ac.uk/id/eprint/10083560/> <http://xmlns.com/foaf/0.1/primaryTopic> <https://discovery.ucl.ac.uk/id/eprint/10083560> .