Matches in SemOpenAlex for { <https://semopenalex.org/work/W130805539> ?p ?o ?g. }
- W130805539 endingPage "40" @default.
- W130805539 startingPage "31" @default.
- W130805539 abstract "AbstractTraditional Reinforcement Learning methods are insufficient for AGIs who must be able to learn to deal with Partially Observable Markov Decision Processes. We investigate a novel method for dealing with this problem: standard RL techniques using as input the hidden layer output of a Sequential Constant-Size Compressor (SCSC). The SCSC takes the form of a sequential Recurrent Auto-Associative Memory, trained through standard back-propagation. Results illustrate the feasibility of this approach — this system learns to deal with high-dimensional visual observations (up to 640 pixels) in partially observable environments where there are long time lags (up to 12 steps) between relevant sensory information and necessary action.Keywordsrecurrent auto-associative memoryreinforcement-learning" @default.
- W130805539 created "2016-06-24" @default.
- W130805539 creator A5034551188 @default.
- W130805539 creator A5059050556 @default.
- W130805539 creator A5071172037 @default.
- W130805539 creator A5088043381 @default.
- W130805539 date "2011-01-01" @default.
- W130805539 modified "2023-09-23" @default.
- W130805539 title "Sequential Constant Size Compressors for Reinforcement Learning" @default.
- W130805539 cites W1907796993 @default.
- W130805539 cites W1970789124 @default.
- W130805539 cites W1971844566 @default.
- W130805539 cites W1982291194 @default.
- W130805539 cites W2011171037 @default.
- W130805539 cites W2034786972 @default.
- W130805539 cites W2064675550 @default.
- W130805539 cites W2091565802 @default.
- W130805539 cites W2111935653 @default.
- W130805539 cites W2112036188 @default.
- W130805539 cites W2133130433 @default.
- W130805539 cites W2144357723 @default.
- W130805539 cites W2154997814 @default.
- W130805539 cites W2166160300 @default.
- W130805539 doi "https://doi.org/10.1007/978-3-642-22887-2_4" @default.
- W130805539 hasPublicationYear "2011" @default.
- W130805539 type Work @default.
- W130805539 sameAs 130805539 @default.
- W130805539 citedByCount "13" @default.
- W130805539 countsByYear W1308055392012 @default.
- W130805539 countsByYear W1308055392013 @default.
- W130805539 countsByYear W1308055392014 @default.
- W130805539 countsByYear W1308055392015 @default.
- W130805539 countsByYear W1308055392016 @default.
- W130805539 countsByYear W1308055392017 @default.
- W130805539 crossrefType "book-chapter" @default.
- W130805539 hasAuthorship W130805539A5034551188 @default.
- W130805539 hasAuthorship W130805539A5059050556 @default.
- W130805539 hasAuthorship W130805539A5071172037 @default.
- W130805539 hasAuthorship W130805539A5088043381 @default.
- W130805539 hasConcept C105795698 @default.
- W130805539 hasConcept C106189395 @default.
- W130805539 hasConcept C119857082 @default.
- W130805539 hasConcept C121332964 @default.
- W130805539 hasConcept C127413603 @default.
- W130805539 hasConcept C131097465 @default.
- W130805539 hasConcept C154945302 @default.
- W130805539 hasConcept C159423971 @default.
- W130805539 hasConcept C159886148 @default.
- W130805539 hasConcept C160633673 @default.
- W130805539 hasConcept C163836022 @default.
- W130805539 hasConcept C17098449 @default.
- W130805539 hasConcept C199360897 @default.
- W130805539 hasConcept C202444582 @default.
- W130805539 hasConcept C2777027219 @default.
- W130805539 hasConcept C2780791683 @default.
- W130805539 hasConcept C32848918 @default.
- W130805539 hasConcept C33923547 @default.
- W130805539 hasConcept C41008148 @default.
- W130805539 hasConcept C50644808 @default.
- W130805539 hasConcept C53442348 @default.
- W130805539 hasConcept C62520636 @default.
- W130805539 hasConcept C78519656 @default.
- W130805539 hasConcept C97541855 @default.
- W130805539 hasConcept C98763669 @default.
- W130805539 hasConceptScore W130805539C105795698 @default.
- W130805539 hasConceptScore W130805539C106189395 @default.
- W130805539 hasConceptScore W130805539C119857082 @default.
- W130805539 hasConceptScore W130805539C121332964 @default.
- W130805539 hasConceptScore W130805539C127413603 @default.
- W130805539 hasConceptScore W130805539C131097465 @default.
- W130805539 hasConceptScore W130805539C154945302 @default.
- W130805539 hasConceptScore W130805539C159423971 @default.
- W130805539 hasConceptScore W130805539C159886148 @default.
- W130805539 hasConceptScore W130805539C160633673 @default.
- W130805539 hasConceptScore W130805539C163836022 @default.
- W130805539 hasConceptScore W130805539C17098449 @default.
- W130805539 hasConceptScore W130805539C199360897 @default.
- W130805539 hasConceptScore W130805539C202444582 @default.
- W130805539 hasConceptScore W130805539C2777027219 @default.
- W130805539 hasConceptScore W130805539C2780791683 @default.
- W130805539 hasConceptScore W130805539C32848918 @default.
- W130805539 hasConceptScore W130805539C33923547 @default.
- W130805539 hasConceptScore W130805539C41008148 @default.
- W130805539 hasConceptScore W130805539C50644808 @default.
- W130805539 hasConceptScore W130805539C53442348 @default.
- W130805539 hasConceptScore W130805539C62520636 @default.
- W130805539 hasConceptScore W130805539C78519656 @default.
- W130805539 hasConceptScore W130805539C97541855 @default.
- W130805539 hasConceptScore W130805539C98763669 @default.
- W130805539 hasLocation W1308055391 @default.
- W130805539 hasOpenAccess W130805539 @default.
- W130805539 hasPrimaryLocation W1308055391 @default.
- W130805539 hasRelatedWork W130805539 @default.
- W130805539 hasRelatedWork W1563041104 @default.
- W130805539 hasRelatedWork W2140069345 @default.
- W130805539 hasRelatedWork W2146763310 @default.
- W130805539 hasRelatedWork W2173087131 @default.
- W130805539 hasRelatedWork W2347690758 @default.