Sign inSign in
ConceptAI & ML

Replay buffer

A memory component inside a DQN agent that stores past experiences (state, action, reward, next state) for training.
as Parham Panahi defines itAlberta Machine Intelligence Institute (Amii)
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

    A mechanism in reinforcement learning used to store past transitions and draw uncorrelated samples from them to mitigate the correlation problem in online Q-learning.
    • 8:19Foundational concepts in deep reinforcement learning, likely

Lectures that assume it

3

Connections

15

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.