FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2800142021> ?p ?o ?g. }

• W2800142021 endingPage "433" @default.
• W2800142021 startingPage "429" @default.
• W2800142021 abstract "Deep neural networks have achieved impressive successes in fields ranging from object recognition to complex games such as Go1,2. Navigation, however, remains a substantial challenge for artificial agents, with deep neural networks trained by reinforcement learning3-5 failing to rival the proficiency of mammalian spatial behaviour, which is underpinned by grid cells in the entorhinal cortex 6 . Grid cells are thought to provide a multi-scale periodic representation that functions as a metric for coding space7,8 and is critical for integrating self-motion (path integration)6,7,9 and planning direct trajectories to goals (vector-based navigation)7,10,11. Here we set out to leverage the computational functions of grid cells to develop a deep reinforcement learning agent with mammal-like navigational abilities. We first trained a recurrent network to perform path integration, leading to the emergence of representations resembling grid cells, as well as other entorhinal cell types 12 . We then showed that this representation provided an effective basis for an agent to locate goals in challenging, unfamiliar, and changeable environments-optimizing the primary objective of navigation through deep reinforcement learning. The performance of agents endowed with grid-like representations surpassed that of an expert human and comparison agents, with the metric quantities necessary for vector-based navigation derived from grid-like units within the network. Furthermore, grid-like representations enabled agents to conduct shortcut behaviours reminiscent of those performed by mammals. Our findings show that emergent grid-like representations furnish agents with a Euclidean spatial metric and associated vector operations, providing a foundation for proficient navigation. As such, our results support neuroscientific theories that see grid cells as critical for vector-based navigation7,10,11, demonstrating that the latter can be combined with path-based strategies to support navigation in challenging environments." @default.
• W2800142021 created "2018-05-17" @default.
• W2800142021 creator A5003252073 @default.
• W2800142021 creator A5005349213 @default.
• W2800142021 creator A5010900024 @default.
• W2800142021 creator A5012250683 @default.
• W2800142021 creator A5013028446 @default.
• W2800142021 creator A5018323141 @default.
• W2800142021 creator A5018388854 @default.
• W2800142021 creator A5019679953 @default.
• W2800142021 creator A5026582515 @default.
• W2800142021 creator A5029480918 @default.
• W2800142021 creator A5030688126 @default.
• W2800142021 creator A5043910056 @default.
• W2800142021 creator A5046090328 @default.
• W2800142021 creator A5048371195 @default.
• W2800142021 creator A5048551460 @default.
• W2800142021 creator A5049230082 @default.
• W2800142021 creator A5050109164 @default.
• W2800142021 creator A5054065284 @default.
• W2800142021 creator A5062883663 @default.
• W2800142021 creator A5063890110 @default.
• W2800142021 creator A5066294254 @default.
• W2800142021 creator A5071223804 @default.
• W2800142021 creator A5079415139 @default.
• W2800142021 creator A5086282819 @default.
• W2800142021 creator A5090334330 @default.
• W2800142021 creator A5090341705 @default.
• W2800142021 date "2018-05-01" @default.
• W2800142021 modified "2023-10-09" @default.
• W2800142021 title "Vector-based navigation using grid-like representations in artificial agents" @default.
• W2800142021 cites W1512234833 @default.
• W2800142021 cites W1540763494 @default.
• W2800142021 cites W1950640079 @default.
• W2800142021 cites W1968023011 @default.
• W2800142021 cites W1970792572 @default.
• W2800142021 cites W1976596954 @default.
• W2800142021 cites W1979533714 @default.
• W2800142021 cites W1997692559 @default.
• W2800142021 cites W2008936540 @default.
• W2800142021 cites W2014792483 @default.
• W2800142021 cites W2030805642 @default.
• W2800142021 cites W2042492924 @default.
• W2800142021 cites W2048921595 @default.
• W2800142021 cites W2064675550 @default.
• W2800142021 cites W2067026281 @default.
• W2800142021 cites W2075376711 @default.
• W2800142021 cites W2080994882 @default.
• W2800142021 cites W2081197259 @default.
• W2800142021 cites W2084588382 @default.
• W2800142021 cites W2092580449 @default.
• W2800142021 cites W2108501592 @default.
• W2800142021 cites W2111051539 @default.
• W2800142021 cites W2112669647 @default.
• W2800142021 cites W2121881115 @default.
• W2800142021 cites W2126378748 @default.
• W2800142021 cites W2135065060 @default.
• W2800142021 cites W2141763580 @default.
• W2800142021 cites W2143864104 @default.
• W2800142021 cites W2145339207 @default.
• W2800142021 cites W2146013506 @default.
• W2800142021 cites W2253328753 @default.
• W2800142021 cites W2257979135 @default.
• W2800142021 cites W2530887700 @default.
• W2800142021 cites W2577983519 @default.
• W2800142021 cites W2786340785 @default.
• W2800142021 cites W2919115771 @default.
• W2800142021 doi "https://doi.org/10.1038/s41586-018-0102-6" @default.
• W2800142021 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29743670" @default.
• W2800142021 hasPublicationYear "2018" @default.
• W2800142021 type Work @default.
• W2800142021 sameAs 2800142021 @default.
• W2800142021 citedByCount "422" @default.
• W2800142021 countsByYear W28001420212017 @default.
• W2800142021 countsByYear W28001420212018 @default.
• W2800142021 countsByYear W28001420212019 @default.
• W2800142021 countsByYear W28001420212020 @default.
• W2800142021 countsByYear W28001420212021 @default.
• W2800142021 countsByYear W28001420212022 @default.
• W2800142021 countsByYear W28001420212023 @default.
• W2800142021 crossrefType "journal-article" @default.
• W2800142021 hasAuthorship W2800142021A5003252073 @default.
• W2800142021 hasAuthorship W2800142021A5005349213 @default.
• W2800142021 hasAuthorship W2800142021A5010900024 @default.
• W2800142021 hasAuthorship W2800142021A5012250683 @default.
• W2800142021 hasAuthorship W2800142021A5013028446 @default.
• W2800142021 hasAuthorship W2800142021A5018323141 @default.
• W2800142021 hasAuthorship W2800142021A5018388854 @default.
• W2800142021 hasAuthorship W2800142021A5019679953 @default.
• W2800142021 hasAuthorship W2800142021A5026582515 @default.
• W2800142021 hasAuthorship W2800142021A5029480918 @default.
• W2800142021 hasAuthorship W2800142021A5030688126 @default.
• W2800142021 hasAuthorship W2800142021A5043910056 @default.
• W2800142021 hasAuthorship W2800142021A5046090328 @default.
• W2800142021 hasAuthorship W2800142021A5048371195 @default.
• W2800142021 hasAuthorship W2800142021A5048551460 @default.
• W2800142021 hasAuthorship W2800142021A5049230082 @default.
• W2800142021 hasAuthorship W2800142021A5050109164 @default.

• next