Sign inSign in
ConceptAI & ML

High variance in policy gradient

Policy gradient estimators have very high variance with finite sample sizes, meaning different random samples yield very different gradient values.
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.

Lecturers

1

    Connections

    3

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

    Concepts2

    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.