Sign inSign in
ConceptAI & ML

Inverse reinforcement learning

A problem where the goal is to recover an unknown reward function given observed behavior of an agent.
as Brian Christian defines itUC BerkeleyThe wording closest to all 6 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

2

Each in their own terms, from the easiest level.

  • Sergey Levine

    UC Berkeley · Undergraduate

    Learning reward functions from examples or observed behavior.
    • 3:09Control as Inference, Part 1
    • 7:35Inverse Reinforcement Learning, Part 1
    • 10:13Inverse Reinforcement Learning, Part 4
    • 12:03Sequential Decision-Making: Policy Gradients vs. Value-Based Architectures
    • 25:31Challenges and Open Problems in Deep Reinforcement Learning (CS 285, Lecture 23, Part 1)

Lectures that assume it

1

Connections

17

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.