Sign inSign in
ConceptAI & ML

Offline reinforcement learning

The task of learning a policy from a fixed historical dataset of interactions without interacting further with the environment.
as Andrea Zanette defines itUC BerkeleyThe wording closest to all 5 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

5

Each in their own terms, from the easiest level.

  • Emma Brunskill

    Stanford University · Undergraduate

    Offline RL means learning a good decision policy from a fixed dataset without interacting further with the environment.
    • 34:11Introduction to Reinforcement Learning (CS234, 2024, Lecture 1)
  • Ashish Vaswani, Lucas Beyer & William Fedus

    Stanford University · Graduate

    A form of reinforcement learning where the agent learns from a pre-collected dataset of interactions rather than through active trial-and-error.
    • 4:30Decision Transformer: Reinforcement Learning via Sequence Modeling
  • Sergey Levine

    UC Berkeley · Graduate

    Developing reinforcement learning methods that can reuse previously collected data sets to create a data-driven RL framework without active online interaction.
    • 4:15Offline Reinforcement Learning
  • Aviral Kumar

    UC Berkeley · Graduate

    Learning optimized policies to maximize reward using existing static interaction data without online trial and interaction with the environment.
    • 0:49Guest Lecture: Aviral Kumar (UC Berkeley CS 285)

Lectures that assume it

1

Connections

15

The lectures that define it or assume it, and the concepts next to it.

5 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.