Sign inSign in
ConceptAI & ML

Baseline

A value subtracted from the cumulative future reward to reduce variance in the policy gradient estimator.
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 · Graduate

    A quantity subtracted from the reward in policy gradients (such as the average reward) to center the rewards and reduce estimator variance without introducing bias.
    • 5:37Policy Gradients II: Variance Reduction, Baselines & Reward-to-Go Causality

Lectures that assume it

4

Connections

13

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.