(A) Temporal sequence of activations in various neural maps (color, shape, object,
and action hubs) when the robot by random exploration stacks the mushroom on top of
the cylinder. The content encoded in the episodic memory network is the temporal
sequence of activity in the object, action, and value hubs, when the robot gains
experiences. (B) The complete temporal sequence of bottom-up activity in the
object-action hubs and rewards received when experience is acquired (Panel A) as
represented in the 50 × 20 episodic memory network. (C) The similar encoding of
episode 2 where the robot stacks the cylinder on top of the mushroom, receiving the
lesser reward (as the tallest stack was not built). Note that the activations in rows
1 and 3 are swapped in Panels B and C, reflecting the temporal sequence of activations
when experience is gained. Rewards received are based on the robot’s success in
building the tallest stack and changes dynamically with the situation. (D) The
behavior immediately after two episodes of experience are encoded. Bottom-up
perception of the mushroom activates the object hub and fills in partial information
in the episodic memory network, leading to recall of past experiences associated with
it. What is recalled filling in all missing information is a valuable inference that
it is more rewarding to stack mushroom-like objects on the top. The emphasis in the
preliminary example is that valuable action sequences are implicitly evident in the
episodic recall of past experiences.
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.