Sign inSign in
ConceptAI & ML

Experience replay

A technique in reinforcement learning where the agent stores its experiences in a memory buffer and samples random batches from it to train the network, breaking the correlation between consecutive samples.
as Fei-Fei Li, Justin Johnson & Serena Yeung defines itStanford UniversityThe 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 · Graduate

    A technique where past experience transitions are stored in a memory buffer and sampled randomly to perform stochastic gradient descent updates.
    • 1:17:27Value Function Approximation & Deep Q-Networks (DQN)
  • Parham Panahi

    Alberta Machine Intelligence Institute (Amii) · Graduate

    Storing raw past experiences in a memory buffer and sampling from them repeatedly to train a reinforcement learning agent.
    • 5:52Endpoint Replay: Compressing the Recency Buffer in Deep Reinforcement Learning

Connections

8

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.