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.
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
1Connections
2The lectures that define it or assume it, and the concepts next to it.