ConceptAI & ML
Model-based reinforcement learning stability
The stability issues in model-based reinforcement learning arising because models are fitted iteratively using collected data and policies can exploit inaccuracies in the learned model.
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.