ConceptAI & ML
Meta-overfitting
A vulnerability where a meta-trained model performs poorly when the task at test time lies outside the distribution of training tasks.
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.
Meta-RL1Training tasks1
Lecturers
1Connections
1The lectures that define it or assume it, and the concepts next to it.