Sign inSign in
ConceptAI & ML

Reward learning

Learning the feature weights of a reward function from expert demonstrations so that optimization or search recovers the demonstrated behavior.
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.

Lecturers

2

Each in their own terms, from the easiest level.

  • Brian Christian

    UC Berkeley · Graduate

    Reward learning requires a computational model of human behavior.
    • 53:05What Humans Want: Models of Preference and Reward in Minds and Machines

Connections

6

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.