ConceptAI & ML
Reward learning
Learning the feature weights of a reward function from expert demonstrations so that optimization or search recovers the demonstrated behavior.
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
2Each in their own terms, from the easiest level.
Brian Christian
Reward learning requires a computational model of human behavior.
Connections
6The lectures that define it or assume it, and the concepts next to it.