Sign inSign in
ConceptAI & ML

Least squares policy iteration

An algorithm that combines policy evaluation via least squares Q-learning with greedy policy improvement for control.
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

2

Each in their own terms, from the easiest level.

  • Sergey Levine

    UC Berkeley · Graduate

    An offline reinforcement learning method that replaces LSTD with LSTDQ to learn Q-functions using previously collected data.
    • 16:55Offline Reinforcement Learning (CS 285, Lecture 15, Part 3)

Connections

6

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.