ConceptAI & ML
Representation learning in deep RL
The use of variational autoencoders to learn disentangled latent state representations from complex state observations for reinforcement learning.
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.