Sign inSign in
ConceptAI & ML

Distributional shift

The problem where the distribution of states encountered during test time differs from the distribution of states seen in the training data.
as Sergey Levine defines itUC BerkeleyThe wording closest to all 7 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

2

Each in their own terms, from the easiest level.

  • Sergey Levine

    UC Berkeley · Undergraduate

    • 7:59Fundamental concepts in deep reinforcement learning
    • 2:26Offline Reinforcement Learning II
    • 2:24Exploration of advanced topics in deep reinforcement learning
    • 7:56Model-Based Reinforcement Learning with Policies
    • 12:35RL with Sequence Models & Language Models, Part 3
  • Sara Beery

    MIT · Graduate

    The mismatch between anticipated conditions or training data distributions and the actual deployment environment.
    • 10:07Generalization: Out-of-Distribution (OOD)

Lectures that assume it

1

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.