Navigating with grid-like representations in artificial agents
Originally shared by Ward Plunet
Navigating with grid-like representations in artificial agents
Most animals, including humans, are able to flexibly navigate the world they live in – exploring new areas, returning quickly to remembered places, and taking shortcuts. Indeed, these abilities feel so easy and natural that it is not immediately obvious how complex the underlying processes really are. In contrast, spatial navigation remains a substantial challenge for artificial agents whose abilities are far outstripped by those of mammals....In our most recent paper published in Nature, we developed an artificial agent to test the theory that grid cells support vector-based navigation, in keeping with our overarching philosophy that algorithms used for AI can meaningfully approximate elements of the brain.
https://deepmind.com/blog/grid-cells/
Navigating with grid-like representations in artificial agents
Most animals, including humans, are able to flexibly navigate the world they live in – exploring new areas, returning quickly to remembered places, and taking shortcuts. Indeed, these abilities feel so easy and natural that it is not immediately obvious how complex the underlying processes really are. In contrast, spatial navigation remains a substantial challenge for artificial agents whose abilities are far outstripped by those of mammals....In our most recent paper published in Nature, we developed an artificial agent to test the theory that grid cells support vector-based navigation, in keeping with our overarching philosophy that algorithms used for AI can meaningfully approximate elements of the brain.
https://deepmind.com/blog/grid-cells/
Comments
Post a Comment