Solving the distal reward problem with rare correlations
In the course of trial-and-error learning, the results of actions, manifested as rewards or punishments, occur often seconds after the actions that caused them. How can a reward be associated with an earlier action when the neural activity that caused that action is no longer present in the network?...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Default Article |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/2134/16992 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|