Sign inSign in
ConceptAI & ML

Causality in policy gradients

The principle that the policy at time t′t' cannot affect the reward at time tt when t<t′t < t', which allows discarding past rewards from the policy gradient sum to reduce variance.
Watch it explained

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

1

    Connections

    3

    The lectures that define it or assume it, and the concepts next to it.

    1 lecturer. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.