Sign inSign in
ConceptAI & ML

Policy gradient theorem

A theorem expressing the policy gradient of a value function as a weighted average of Q-functions.
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

2

Each in their own terms, from the easiest level.

  • David Silver

    Google DeepMind · Undergraduate

    A theorem that generalizes the likelihood ratio approach to multi-step MDPs, expressing the policy gradient as an expectation of the score function multiplied by the action-value function.
    • 46:35Policy Gradient Methods

Lectures that assume it

2

Connections

14

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

2 lecturers. 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.