ConceptAI & ML
Data augmentation in imitation learning
A technique that adds synthetic or auxiliary data illustrating corrective actions to help the policy recover from out-of-distribution states.
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.