Sign inSign in
ConceptAI & ML

Trust region

A region around the current point where the local quadratic approximation is trusted to be accurate.
as Sergey Levine defines itUC BerkeleyThe wording closest to all 3 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.

Optimization2Local approximation1Optimization constraints1Optimization variables1Quadratic approximation1Taylor expansion1

Opens up

Concepts that name this one as a prerequisite.

Lecturers

2

Each in their own terms, from the easiest level.

  • Sergey Levine

    UC Berkeley · Undergraduate

    • 2:31Exploration of advanced topics in deep reinforcement learning
  • Stephen Boyd

    Stanford University · Graduate

    A subset of the domain containing the current estimate over which a local approximation of the problem is trusted to be accurate.
    • 9:08Sequential Convex Programming

Lectures that assume it

1

Connections

8

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.