ConceptAI & ML
Causality in policy gradients
The principle that the policy at time cannot affect the reward at time when , which allows discarding past rewards from the policy gradient sum to reduce variance.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
1Connections
3The lectures that define it or assume it, and the concepts next to it.