<> <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/10193105> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/ontology/bibo/Thesis> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/ontology/bibo/Article> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://purl.org/dc/terms/title> "Hippocampus-Inspired Representation Learning for Artificial Agents"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://purl.org/ontology/bibo/abstract> "Spatial representations found in the hippocampal formation of freely moving mammals, such as those of grid cells, appear optimal for spatial navigation, and also afford flexible and generalisable non-spatial behaviours. In this thesis, I propose models for learning and representing the structure underlying high-dimensional observation space in artificial agents, drawing inspiration from hippocampal neuroscience.\r\n\r\nIn the first part of the thesis, I study the construction and identification of latent representations. I propose a novel model for grid cell firing based on Fourier analysis of\r\ntranslation-invariant transition dynamics. I show that effects of arbitrary actions can be predicted using a single neural representation and action-dependent weight modulation, and how this model unifies existing models of grid cells based on predictive planning, continuous attractors, and oscillatory interference. Next, I consider the problem of unsupervised learning of the structured latent manifold underlying population neuronal spiking, such that interdependent behavioural variables can be accurately decoded. I propose a novel amortised inference framework such that the recognition networks explicitly parametrise the posterior latent dependency structure, relaxing the full-factorisation assumption.\r\n\r\nIn the second part, I propose representation learning methods inspired by neuroscience and study their application in reinforcement learning. Inspired by the observation of hippocampal “replay” in both temporally forward and backward directions, I show that incorporating temporally backward predictive reconstruction self-supervision into training world models leads to better sample efficiency and stronger generalisability on continuous control tasks. I then\r\npropose a novel intrinsic exploration framework under a similar premise, where the intrinsic novelty bonus is constructed based on both prospective and retrospective information. The resulting agents exhibit higher exploration efficiency and ethologically plausible exploration strategies.\r\n\r\nI conclude by discussing the general implications of learning and utilisation of latent structures in both artificial and biological intelligence, and potential applications of neural-inspired representation learning beyond reinforcement learning."^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://purl.org/dc/terms/date> "2024-06-28" .
<https://discovery.ucl.ac.uk/id/document/1750106> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/ontology/bibo/Document> .
<https://discovery.ucl.ac.uk/id/org/ext-a64c3df5861c6582807add1abaadf2af> <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-a64c3df5861c6582807add1abaadf2af> <http://xmlns.com/foaf/0.1/name> "UCL (University College London)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://purl.org/dc/terms/issuer> <https://discovery.ucl.ac.uk/id/org/ext-a64c3df5861c6582807add1abaadf2af> .
<https://discovery.ucl.ac.uk/id/org/ext-8f7ed5b3450912d77936e05323506a1f> <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-8f7ed5b3450912d77936e05323506a1f> <http://xmlns.com/foaf/0.1/name> "Computer Science, UCL (University College London)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/org/ext-8f7ed5b3450912d77936e05323506a1f> <http://purl.org/dc/terms/isPartOf> <https://discovery.ucl.ac.uk/id/org/ext-a64c3df5861c6582807add1abaadf2af> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://purl.org/dc/terms/issuer> <https://discovery.ucl.ac.uk/id/org/ext-8f7ed5b3450912d77936e05323506a1f> .
<https://discovery.ucl.ac.uk/id/org/ext-a64c3df5861c6582807add1abaadf2af> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/org/ext-8f7ed5b3450912d77936e05323506a1f> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://purl.org/ontology/bibo/status> <http://purl.org/ontology/bibo/status/unpublished> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://purl.org/dc/terms/creator> <https://discovery.ucl.ac.uk/id/person/ext-76e701511272c74355f8651218c7a405> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://purl.org/ontology/bibo/authorList> <https://discovery.ucl.ac.uk/id/eprint/10193105#authors> .
<https://discovery.ucl.ac.uk/id/eprint/10193105#authors> <http://www.w3.org/1999/02/22-rdf-syntax-ns#_1> <https://discovery.ucl.ac.uk/id/person/ext-76e701511272c74355f8651218c7a405> .
<https://discovery.ucl.ac.uk/id/person/ext-76e701511272c74355f8651218c7a405> <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-76e701511272c74355f8651218c7a405> <http://xmlns.com/foaf/0.1/givenName> "Changmin"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-76e701511272c74355f8651218c7a405> <http://xmlns.com/foaf/0.1/familyName> "Yu"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/person/ext-76e701511272c74355f8651218c7a405> <http://xmlns.com/foaf/0.1/name> "Changmin Yu"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/EPrint> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/ThesisEPrint> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://purl.org/dc/terms/isPartOf> <https://discovery.ucl.ac.uk/id/repository> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750106> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/1750106> <http://www.w3.org/2000/01/rdf-schema#label> "Hippocampus-Inspired Representation Learning for Artificial Agents (Text)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://eprints.org/ontology/hasOther> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750106> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10193105/1/thesis_final.pdf> .
<https://discovery.ucl.ac.uk/id/document/1750106> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10193105/1/thesis_final.pdf> .
<https://discovery.ucl.ac.uk/id/eprint/10193105/1/thesis_final.pdf> <http://www.w3.org/2000/01/rdf-schema#label> "thesis_final.pdf"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/eprint/10193105> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1750107> .
<https://discovery.ucl.ac.uk/id/document/1750107> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/1750107> <http://www.w3.org/2000/01/rdf-schema#label> "Hippocampus-Inspired Representation Learning for Artificial Agents (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/1750107> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750107> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750107> <http://eprints.org/relation/islightboxThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750107> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10193105/2/lightbox.jpg> .
<https://discovery.ucl.ac.uk/id/document/1750107> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10193105/2/lightbox.jpg> .
<https://discovery.ucl.ac.uk/id/eprint/10193105/2/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/10193105> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1750108> .
<https://discovery.ucl.ac.uk/id/document/1750108> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/1750108> <http://www.w3.org/2000/01/rdf-schema#label> "Hippocampus-Inspired Representation Learning for Artificial Agents (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/1750108> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750108> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750108> <http://eprints.org/relation/ispreviewThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750108> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10193105/3/preview.jpg> .
<https://discovery.ucl.ac.uk/id/document/1750108> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10193105/3/preview.jpg> .
<https://discovery.ucl.ac.uk/id/eprint/10193105/3/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/10193105> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1750109> .
<https://discovery.ucl.ac.uk/id/document/1750109> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/1750109> <http://www.w3.org/2000/01/rdf-schema#label> "Hippocampus-Inspired Representation Learning for Artificial Agents (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/1750109> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750109> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750109> <http://eprints.org/relation/ismediumThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750109> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10193105/4/medium.jpg> .
<https://discovery.ucl.ac.uk/id/document/1750109> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10193105/4/medium.jpg> .
<https://discovery.ucl.ac.uk/id/eprint/10193105/4/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/10193105> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1750110> .
<https://discovery.ucl.ac.uk/id/document/1750110> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/1750110> <http://www.w3.org/2000/01/rdf-schema#label> "Hippocampus-Inspired Representation Learning for Artificial Agents (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/1750110> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750110> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750110> <http://eprints.org/relation/issmallThumbnailVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750110> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10193105/5/small.jpg> .
<https://discovery.ucl.ac.uk/id/document/1750110> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10193105/5/small.jpg> .
<https://discovery.ucl.ac.uk/id/eprint/10193105/5/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/10193105> <http://eprints.org/ontology/hasDocument> <https://discovery.ucl.ac.uk/id/document/1750111> .
<https://discovery.ucl.ac.uk/id/document/1750111> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://eprints.org/ontology/Document> .
<https://discovery.ucl.ac.uk/id/document/1750111> <http://www.w3.org/2000/01/rdf-schema#label> "Hippocampus-Inspired Representation Learning for Artificial Agents (Other)"^^<http://www.w3.org/2001/XMLSchema#string> .
<https://discovery.ucl.ac.uk/id/document/1750111> <http://eprints.org/relation/isVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750111> <http://eprints.org/relation/isVolatileVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750111> <http://eprints.org/relation/isIndexCodesVersionOf> <https://discovery.ucl.ac.uk/id/document/1750106> .
<https://discovery.ucl.ac.uk/id/document/1750111> <http://eprints.org/ontology/hasFile> <https://discovery.ucl.ac.uk/id/eprint/10193105/6/indexcodes.txt> .
<https://discovery.ucl.ac.uk/id/document/1750111> <http://purl.org/dc/terms/hasPart> <https://discovery.ucl.ac.uk/id/eprint/10193105/6/indexcodes.txt> .
<https://discovery.ucl.ac.uk/id/eprint/10193105/6/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/10193105> <http://www.w3.org/2000/01/rdf-schema#seeAlso> <https://discovery.ucl.ac.uk/id/eprint/10193105/> .
<https://discovery.ucl.ac.uk/id/eprint/10193105/> <http://purl.org/dc/elements/1.1/title> "HTML Summary of #10193105 \n\nHippocampus-Inspired Representation Learning for Artificial Agents\n\n" .
<https://discovery.ucl.ac.uk/id/eprint/10193105/> <http://purl.org/dc/elements/1.1/format> "text/html" .
<https://discovery.ucl.ac.uk/id/eprint/10193105/> <http://xmlns.com/foaf/0.1/primaryTopic> <https://discovery.ucl.ac.uk/id/eprint/10193105> .