FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897698970> ?p ?o ?g. }

• W2897698970 abstract "Abstract The successor representation (SR) is a candidate principle for generalization in reinforcement learning, computational accounts of memory, and the structure of neural representations in the hippocampus. Given a sequence of states, the SR learns a predictive representation for every given state that encodes how often, on average, each upcoming state is expected to be visited, even if it is multiple steps ahead. A discount or scale parameter determines how many steps into the future SR’s generalizations reach, enabling rapid value computation, subgoal discovery, and flexible decision-making in large trees. However, SR with a single scale could discard information for predicting both the sequential order of and the distance between states, which are common problems in navigation for animals and artificial agents. Here we propose a solution: an ensemble of SRs with multiple scales. We show that the derivative of multi-scale SR can reconstruct both the sequence of expected future states and estimate distance to goal. This derivative can be computed linearly: we show that a multi-scale SR ensemble is the Laplace transform of future states, and the inverse of this Laplace transform is a biologically plausible linear estimation of the derivative. Multi-scale SR and its derivative could lead to a common principle for how the medial temporal lobe supports both map-based and vector-based navigation." @default.
• W2897698970 created "2018-10-26" @default.
• W2897698970 creator A5059293348 @default.
• W2897698970 creator A5085169868 @default.
• W2897698970 date "2018-10-22" @default.
• W2897698970 modified "2023-10-01" @default.
• W2897698970 title "Predicting the Future with Multi-scale Successor Representations" @default.
• W2897698970 cites W1540763494 @default.
• W2897698970 cites W1572294349 @default.
• W2897698970 cites W1888004466 @default.
• W2897698970 cites W1941769416 @default.
• W2897698970 cites W1965585960 @default.
• W2897698970 cites W1973031475 @default.
• W2897698970 cites W1973478411 @default.
• W2897698970 cites W1975958074 @default.
• W2897698970 cites W1983813797 @default.
• W2897698970 cites W2000214310 @default.
• W2897698970 cites W2002935439 @default.
• W2897698970 cites W2003370853 @default.
• W2897698970 cites W2006760951 @default.
• W2897698970 cites W2009513819 @default.
• W2897698970 cites W2011074553 @default.
• W2897698970 cites W2011868317 @default.
• W2897698970 cites W2016723506 @default.
• W2897698970 cites W2043615441 @default.
• W2897698970 cites W2052918792 @default.
• W2897698970 cites W2056354534 @default.
• W2897698970 cites W2062531735 @default.
• W2897698970 cites W2064790617 @default.
• W2897698970 cites W2076546217 @default.
• W2897698970 cites W2080994882 @default.
• W2897698970 cites W2096970998 @default.
• W2897698970 cites W2101782048 @default.
• W2897698970 cites W2122373385 @default.
• W2897698970 cites W2133105703 @default.
• W2897698970 cites W2137234026 @default.
• W2897698970 cites W2145889472 @default.
• W2897698970 cites W2147351968 @default.
• W2897698970 cites W2156530149 @default.
• W2897698970 cites W2172122397 @default.
• W2897698970 cites W2520200855 @default.
• W2897698970 cites W2557342183 @default.
• W2897698970 cites W2577983519 @default.
• W2897698970 cites W2599683001 @default.
• W2897698970 cites W2609154042 @default.
• W2897698970 cites W2766795651 @default.
• W2897698970 cites W2782639658 @default.
• W2897698970 cites W2799577095 @default.
• W2897698970 cites W2800261909 @default.
• W2897698970 cites W2809440348 @default.
• W2897698970 cites W2811470308 @default.
• W2897698970 cites W2883512183 @default.
• W2897698970 cites W2883690703 @default.
• W2897698970 cites W2889422159 @default.
• W2897698970 cites W2950347959 @default.
• W2897698970 cites W2951066214 @default.
• W2897698970 cites W2953319434 @default.
• W2897698970 cites W3100082343 @default.
• W2897698970 cites W3101539900 @default.
• W2897698970 cites W4236786787 @default.
• W2897698970 doi "https://doi.org/10.1101/449470" @default.
• W2897698970 hasPublicationYear "2018" @default.
• W2897698970 type Work @default.
• W2897698970 sameAs 2897698970 @default.
• W2897698970 citedByCount "29" @default.
• W2897698970 countsByYear W28976989702017 @default.
• W2897698970 countsByYear W28976989702018 @default.
• W2897698970 countsByYear W28976989702019 @default.
• W2897698970 countsByYear W28976989702020 @default.
• W2897698970 countsByYear W28976989702021 @default.
• W2897698970 countsByYear W28976989702022 @default.
• W2897698970 countsByYear W28976989702023 @default.
• W2897698970 crossrefType "posted-content" @default.
• W2897698970 hasAuthorship W2897698970A5059293348 @default.
• W2897698970 hasAuthorship W2897698970A5085169868 @default.
• W2897698970 hasBestOaLocation W28976989701 @default.
• W2897698970 hasConcept C11413529 @default.
• W2897698970 hasConcept C134306372 @default.
• W2897698970 hasConcept C154945302 @default.
• W2897698970 hasConcept C177148314 @default.
• W2897698970 hasConcept C17744445 @default.
• W2897698970 hasConcept C199539241 @default.
• W2897698970 hasConcept C205649164 @default.
• W2897698970 hasConcept C2776359362 @default.
• W2897698970 hasConcept C2778112365 @default.
• W2897698970 hasConcept C2778755073 @default.
• W2897698970 hasConcept C33923547 @default.
• W2897698970 hasConcept C41008148 @default.
• W2897698970 hasConcept C54355233 @default.
• W2897698970 hasConcept C58640448 @default.
• W2897698970 hasConcept C60455284 @default.
• W2897698970 hasConcept C75306776 @default.
• W2897698970 hasConcept C86803240 @default.
• W2897698970 hasConcept C94625758 @default.
• W2897698970 hasConcept C97937538 @default.
• W2897698970 hasConceptScore W2897698970C11413529 @default.
• W2897698970 hasConceptScore W2897698970C134306372 @default.
• W2897698970 hasConceptScore W2897698970C154945302 @default.
• W2897698970 hasConceptScore W2897698970C177148314 @default.
• W2897698970 hasConceptScore W2897698970C17744445 @default.

• next