ConceptAI & ML
Posterior sampling
An exploration strategy where the agent samples a latent variable from its posterior belief and acts optimally under that sampled belief.
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
1Sergey Levine
Connections
6The lectures that define it or assume it, and the concepts next to it.