How to perfect a chocolate souffle and other important problems.
When learning to achieve a goal through a complex series of actions, humans often group several actions into a subroutine and evaluate whether the subroutine achieved a specific subgoal. A new study reports brain responses consistent with such "hierarchical reinforcement learning."
| Main Authors: | , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
2011
|