Sign inSign in
ConceptAI & ML

Policy improvement

The process of updating a policy by performing a one-step look-ahead using the values obtained from policy evaluation.
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.

Policy evaluation2Bellman equation1Greedy action selection1One-step look-ahead1Policy1Value function1

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

    Creating a better policy by acting greedily with respect to the value function of the current policy.
    • 31:00Planning by Dynamic Programming — Policy & Value Iteration

Lectures that assume it

2

Connections

11

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.