Sign inSign in
ConceptAI & ML

Temporal difference learning

A learning method that updates value estimates incrementally based on each observed transition rather than waiting for the end of an episode.
as Pieter Abbeel 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.

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

    Methods that learn directly from experience in a model-free manner by updating guesses towards other guesses using incomplete episodes.
    • 34:20Model-Free Prediction — Monte Carlo, TD(0) & TD(λ)
  • Russ Tedrake

    MIT · Undergraduate

    A reinforcement learning method that learns from bootstrapping off the current estimate of the value function.
    • 32:16Dynamic Programming III

Lectures that assume it

6

Connections

18

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.