ConceptAI & ML
Bootstrap estimate
An estimate that uses the previous fitted value function combined with the current reward to approximate the target value, lowering variance at the cost of higher bias.
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
1Connections
3The lectures that define it or assume it, and the concepts next to it.