Sign inSign in
ConceptAI & ML

Policy iteration

An algorithm that alternates between evaluating the advantage function for a policy and updating the policy to greedily select actions with highest advantage.
as Sergey Levine defines itUC BerkeleyThe wording closest to all 5 definitions
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

3

Each in their own terms, from the easiest level.

  • David Silver

    Google DeepMind · Undergraduate

    An iterative process alternating between policy evaluation and policy improvement that converges to the optimal policy.
    • 32:21Planning by Dynamic Programming — Policy & Value Iteration
  • Pieter Abbeel

    UC Berkeley · Undergraduate

    An algorithm that alternates between evaluating a fixed policy and improving it using one-step look-ahead until the policy converges.
    • 53:35Markov Decision Processes (MDPs) Part 2/2
  • Sergey Levine

    UC Berkeley · Graduate

    • 6:38Deep Reinforcement Learning
    • 5:02Foundational concepts in deep reinforcement learning

Lectures that assume it

4

Connections

19

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

3 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.