<> <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/10198782> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/ontology/bibo/Article> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/dc/terms/title> "Distributionally Robust Model-based Reinforcement Learning with Large State Spaces"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/ontology/bibo/abstract> "Three major challenges in reinforcement learning are the complex dynamical systems with large state spaces, the costly data acquisition processes, and the deviation of real-world dynamics from the training environment deployment. To overcome these issues, we study distributionally robust Markov decision processes with continuous state spaces under the widely used Kullback–Leibler, chi-square, and total variation uncertainty sets. We propose a model-based approach that utilizes Gaussian Processes and the maximum variance reduction algorithm to efficiently learn multi-output nominal transition dynamics, leveraging access to a generative model (i.e., simulator). We further demonstrate the statistical sample complexity of the proposed method for different uncertainty sets. These complexity bounds are independent of the number of states and extend beyond linear dynamics, ensuring the effectiveness of our approach in identifying near-optimal distributionally-robust policies. The proposed method can be further combined with other model-free distributionally robust reinforcement learning methods to obtain a near-optimal robust policy. Experimental results demonstrate the robustness of our algorithm to distributional shifts and its superior performance in terms of the number of samples needed."^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/dc/terms/date> "2024" . <https://discovery.ucl.ac.uk/id/document/1788704> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/ontology/bibo/Document> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/ontology/bibo/volume> "238" . <https://discovery.ucl.ac.uk/id/org/ext-c44fee47f6cbb4f306cc4879197e423d> <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-c44fee47f6cbb4f306cc4879197e423d> <http://xmlns.com/foaf/0.1/name> "PMLR"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/dc/terms/publisher> <https://discovery.ucl.ac.uk/id/org/ext-c44fee47f6cbb4f306cc4879197e423d> . <https://discovery.ucl.ac.uk/id/publication/ext-4890b7d5e2b8e1598b603b8f439ab378> <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-4890b7d5e2b8e1598b603b8f439ab378> <http://xmlns.com/foaf/0.1/name> "INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 238"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/dc/terms/isPartOf> <https://discovery.ucl.ac.uk/id/publication/ext-4890b7d5e2b8e1598b603b8f439ab378> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/ontology/bibo/status> <http://purl.org/ontology/bibo/status/published> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/dc/terms/creator> <https://discovery.ucl.ac.uk/id/person/ext-48d7c6c22f293f5c3931c6da05f8f32c> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/ontology/bibo/authorList> <https://discovery.ucl.ac.uk/id/eprint/10198782#authors> . <https://discovery.ucl.ac.uk/id/eprint/10198782#authors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_1> <https://discovery.ucl.ac.uk/id/person/ext-48d7c6c22f293f5c3931c6da05f8f32c> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/dc/terms/creator> <https://discovery.ucl.ac.uk/id/person/ext-8168df7206a037f07072aa5cb5e915bd> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/ontology/bibo/authorList> <https://discovery.ucl.ac.uk/id/eprint/10198782#authors> . <https://discovery.ucl.ac.uk/id/eprint/10198782#authors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_2> <https://discovery.ucl.ac.uk/id/person/ext-8168df7206a037f07072aa5cb5e915bd> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/dc/terms/creator> <https://discovery.ucl.ac.uk/id/person/ext-7d8e9e404a271bd5b4e0481504da7183> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/ontology/bibo/authorList> <https://discovery.ucl.ac.uk/id/eprint/10198782#authors> . <https://discovery.ucl.ac.uk/id/eprint/10198782#authors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_3> <https://discovery.ucl.ac.uk/id/person/ext-7d8e9e404a271bd5b4e0481504da7183> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/dc/terms/creator> <https://discovery.ucl.ac.uk/id/person/ext-4e2790eb5414c16a6d3905770c2173a8> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/ontology/bibo/authorList> <https://discovery.ucl.ac.uk/id/eprint/10198782#authors> . <https://discovery.ucl.ac.uk/id/eprint/10198782#authors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_4> <https://discovery.ucl.ac.uk/id/person/ext-4e2790eb5414c16a6d3905770c2173a8> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/dc/terms/creator> <https://discovery.ucl.ac.uk/id/person/ext-60791be0cc389bd013dfa29ab9e12476> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/ontology/bibo/authorList> <https://discovery.ucl.ac.uk/id/eprint/10198782#authors> . <https://discovery.ucl.ac.uk/id/eprint/10198782#authors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_5> <https://discovery.ucl.ac.uk/id/person/ext-60791be0cc389bd013dfa29ab9e12476> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://www.loc.gov/loc.terms/relators/EDT> <https://discovery.ucl.ac.uk/id/person/ext-27468806fa8edd29fcee7a7a609518bf> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/ontology/bibo/editorList> <https://discovery.ucl.ac.uk/id/eprint/10198782#editors> . <https://discovery.ucl.ac.uk/id/eprint/10198782#editors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_1> <https://discovery.ucl.ac.uk/id/person/ext-27468806fa8edd29fcee7a7a609518bf> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://www.loc.gov/loc.terms/relators/EDT> <https://discovery.ucl.ac.uk/id/person/ext-00553f1cca31cb08a417a7161ca119e0> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/ontology/bibo/editorList> <https://discovery.ucl.ac.uk/id/eprint/10198782#editors> . <https://discovery.ucl.ac.uk/id/eprint/10198782#editors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_2> <https://discovery.ucl.ac.uk/id/person/ext-00553f1cca31cb08a417a7161ca119e0> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://www.loc.gov/loc.terms/relators/EDT> <https://discovery.ucl.ac.uk/id/person/ext-d04e13dc0a3581305ae8c923440e8905> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/ontology/bibo/editorList> <https://discovery.ucl.ac.uk/id/eprint/10198782#editors> . <https://discovery.ucl.ac.uk/id/eprint/10198782#editors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_3> <https://discovery.ucl.ac.uk/id/person/ext-d04e13dc0a3581305ae8c923440e8905> . <https://discovery.ucl.ac.uk/id/person/ext-27468806fa8edd29fcee7a7a609518bf> <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-27468806fa8edd29fcee7a7a609518bf> <http://xmlns.com/foaf/0.1/givenName> "S"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-27468806fa8edd29fcee7a7a609518bf> <http://xmlns.com/foaf/0.1/familyName> "Dasgupta"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-27468806fa8edd29fcee7a7a609518bf> <http://xmlns.com/foaf/0.1/name> "S Dasgupta"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-4e2790eb5414c16a6d3905770c2173a8> <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-4e2790eb5414c16a6d3905770c2173a8> <http://xmlns.com/foaf/0.1/givenName> "Andreas"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-4e2790eb5414c16a6d3905770c2173a8> <http://xmlns.com/foaf/0.1/familyName> "Krause"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-4e2790eb5414c16a6d3905770c2173a8> <http://xmlns.com/foaf/0.1/name> "Andreas Krause"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-60791be0cc389bd013dfa29ab9e12476> <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-60791be0cc389bd013dfa29ab9e12476> <http://xmlns.com/foaf/0.1/givenName> "Ilija"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-60791be0cc389bd013dfa29ab9e12476> <http://xmlns.com/foaf/0.1/familyName> "Bogunovic"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-60791be0cc389bd013dfa29ab9e12476> <http://xmlns.com/foaf/0.1/name> "Ilija Bogunovic"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-8168df7206a037f07072aa5cb5e915bd> <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-8168df7206a037f07072aa5cb5e915bd> <http://xmlns.com/foaf/0.1/givenName> "Pier Giuseppe"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-8168df7206a037f07072aa5cb5e915bd> <http://xmlns.com/foaf/0.1/familyName> "Sessa"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-8168df7206a037f07072aa5cb5e915bd> <http://xmlns.com/foaf/0.1/name> "Pier Giuseppe Sessa"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-48d7c6c22f293f5c3931c6da05f8f32c> <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-48d7c6c22f293f5c3931c6da05f8f32c> <http://xmlns.com/foaf/0.1/givenName> "Shyam Sundhar"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-48d7c6c22f293f5c3931c6da05f8f32c> <http://xmlns.com/foaf/0.1/familyName> "Ramesh"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-48d7c6c22f293f5c3931c6da05f8f32c> <http://xmlns.com/foaf/0.1/name> "Shyam Sundhar Ramesh"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-7d8e9e404a271bd5b4e0481504da7183> <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-7d8e9e404a271bd5b4e0481504da7183> <http://xmlns.com/foaf/0.1/givenName> "Yifan"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-7d8e9e404a271bd5b4e0481504da7183> <http://xmlns.com/foaf/0.1/familyName> "Hu"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-7d8e9e404a271bd5b4e0481504da7183> <http://xmlns.com/foaf/0.1/name> "Yifan Hu"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-d04e13dc0a3581305ae8c923440e8905> <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-d04e13dc0a3581305ae8c923440e8905> <http://xmlns.com/foaf/0.1/givenName> "Y"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-d04e13dc0a3581305ae8c923440e8905> <http://xmlns.com/foaf/0.1/familyName> "Li"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-d04e13dc0a3581305ae8c923440e8905> <http://xmlns.com/foaf/0.1/name> "Y Li"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-00553f1cca31cb08a417a7161ca119e0> <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-00553f1cca31cb08a417a7161ca119e0> <http://xmlns.com/foaf/0.1/givenName> "S"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-00553f1cca31cb08a417a7161ca119e0> <http://xmlns.com/foaf/0.1/familyName> "Mandt"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/person/ext-00553f1cca31cb08a417a7161ca119e0> <http://xmlns.com/foaf/0.1/name> "S Mandt"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/ontology/bibo/Article> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/ontology/bibo/presentedAt> <https://discovery.ucl.ac.uk/id/event/ext-95a475ba27176b63a589ac64e810d1ed> . <https://discovery.ucl.ac.uk/id/event/ext-95a475ba27176b63a589ac64e810d1ed> <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-95a475ba27176b63a589ac64e810d1ed> <http://purl.org/dc/terms/title> "27th International Conference on Artificial Intelligence and Statistics (AISTATS)"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/event/ext-95a475ba27176b63a589ac64e810d1ed> <http://purl.org/NET/c4dm/event.owl#place> <https://discovery.ucl.ac.uk/id/location/ext-ffe61fe41d764b5e539d384c05b80e9e> . <https://discovery.ucl.ac.uk/id/event/ext-95a475ba27176b63a589ac64e810d1ed> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/NET/c4dm/event.owl#Event> . <https://discovery.ucl.ac.uk/id/event/ext-95a475ba27176b63a589ac64e810d1ed> <http://purl.org/NET/c4dm/event.owl#place> <https://discovery.ucl.ac.uk/id/location/ext-ffe61fe41d764b5e539d384c05b80e9e> . <https://discovery.ucl.ac.uk/id/location/ext-ffe61fe41d764b5e539d384c05b80e9e> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://www.w3.org/2003/01/geo/wgs84_pos#SpatialThing> . <https://discovery.ucl.ac.uk/id/location/ext-ffe61fe41d764b5e539d384c05b80e9e> <http://www.w3.org/2000/01/rdf-schema#label> "Valencia, Spain"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/EPrint> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/ProceedingsSectionEPrint> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/dc/terms/isPartOf> <https://discovery.ucl.ac.uk/id/repository> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788704> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> . <https://discovery.ucl.ac.uk/id/document/1788704> <http://www.w3.org/2000/01/rdf-schema#label> "Distributionally Robust Model-based Reinforcement Learning with Large State Spaces (Text)"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://purl.org/dc/elements/1.1/hasVersion> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://eprints.org/ontology/hasPublished> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788704> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10198782/1/sundhar-ramesh24a.pdf> . <https://discovery.ucl.ac.uk/id/document/1788704> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10198782/1/sundhar-ramesh24a.pdf> . <https://discovery.ucl.ac.uk/id/eprint/10198782/1/sundhar-ramesh24a.pdf> <http://www.w3.org/2000/01/rdf-schema#label> "sundhar-ramesh24a.pdf"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/eprint/10198782> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1788705> . <https://discovery.ucl.ac.uk/id/document/1788705> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> . <https://discovery.ucl.ac.uk/id/document/1788705> <http://www.w3.org/2000/01/rdf-schema#label> "Distributionally Robust Model-based Reinforcement Learning with Large State Spaces (Other)"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/document/1788705> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788705> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788705> <http://eprints.org/relation/isIndexCodesVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788705> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10198782/2/indexcodes.txt> . <https://discovery.ucl.ac.uk/id/document/1788705> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10198782/2/indexcodes.txt> . <https://discovery.ucl.ac.uk/id/eprint/10198782/2/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/10198782> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1788706> . <https://discovery.ucl.ac.uk/id/document/1788706> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> . <https://discovery.ucl.ac.uk/id/document/1788706> <http://www.w3.org/2000/01/rdf-schema#label> "Distributionally Robust Model-based Reinforcement Learning with Large State Spaces (Other)"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/document/1788706> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788706> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788706> <http://eprints.org/relation/islightboxThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788706> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10198782/3/lightbox.jpg> . <https://discovery.ucl.ac.uk/id/document/1788706> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10198782/3/lightbox.jpg> . <https://discovery.ucl.ac.uk/id/eprint/10198782/3/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/10198782> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1788707> . <https://discovery.ucl.ac.uk/id/document/1788707> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> . <https://discovery.ucl.ac.uk/id/document/1788707> <http://www.w3.org/2000/01/rdf-schema#label> "Distributionally Robust Model-based Reinforcement Learning with Large State Spaces (Other)"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/document/1788707> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788707> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788707> <http://eprints.org/relation/ispreviewThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788707> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10198782/4/preview.jpg> . <https://discovery.ucl.ac.uk/id/document/1788707> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10198782/4/preview.jpg> . <https://discovery.ucl.ac.uk/id/eprint/10198782/4/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/10198782> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1788708> . <https://discovery.ucl.ac.uk/id/document/1788708> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> . <https://discovery.ucl.ac.uk/id/document/1788708> <http://www.w3.org/2000/01/rdf-schema#label> "Distributionally Robust Model-based Reinforcement Learning with Large State Spaces (Other)"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/document/1788708> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788708> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788708> <http://eprints.org/relation/ismediumThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788708> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10198782/5/medium.jpg> . <https://discovery.ucl.ac.uk/id/document/1788708> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10198782/5/medium.jpg> . <https://discovery.ucl.ac.uk/id/eprint/10198782/5/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/10198782> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1788709> . <https://discovery.ucl.ac.uk/id/document/1788709> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> . <https://discovery.ucl.ac.uk/id/document/1788709> <http://www.w3.org/2000/01/rdf-schema#label> "Distributionally Robust Model-based Reinforcement Learning with Large State Spaces (Other)"^^<http://www.w3.org/2001/XMLSchema#string> . <https://discovery.ucl.ac.uk/id/document/1788709> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788709> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788709> <http://eprints.org/relation/issmallThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/1788704> . <https://discovery.ucl.ac.uk/id/document/1788709> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10198782/6/small.jpg> . <https://discovery.ucl.ac.uk/id/document/1788709> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10198782/6/small.jpg> . <https://discovery.ucl.ac.uk/id/eprint/10198782/6/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/10198782> <http://www.w3.org/2000/01/rdf-schema#seeAlso> <https://discovery.ucl.ac.uk/id/eprint/10198782/> . <https://discovery.ucl.ac.uk/id/eprint/10198782/> <http://purl.org/dc/elements/1.1/title> "HTML Summary of #10198782 \n\nDistributionally Robust Model-based Reinforcement Learning with Large State Spaces\n\n" . <https://discovery.ucl.ac.uk/id/eprint/10198782/> <http://purl.org/dc/elements/1.1/format> "text/html" . <https://discovery.ucl.ac.uk/id/eprint/10198782/> <http://xmlns.com/foaf/0.1/primaryTopic> <https://discovery.ucl.ac.uk/id/eprint/10198782> .