ConceptAI & ML
Domain randomization
A data augmentation technique where simulation environments are randomized to bridge the gap between simulation and reality.
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.
Sergey Levine
Intentionally adding more randomness to a source training domain to increase policy robustness to variability in physical or visual parameters.
Connections
5The lectures that define it or assume it, and the concepts next to it.