Sign inSign in
ConceptAI & ML

Preference-based reward learning

A method to train reward functions by modeling the probability that a human prefers one generated answer over another using the exponential ratio of their rewards.
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.

Maximum entropy inverse RL1Reward model1

Lecturers

1

    Connections

    2

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

    Concept1

    1 lecturer. 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.