ConceptAI & ML
Off-policy reinforcement learning
Reinforcement learning methods that utilize datasets from past interactions or offline data to train agents rather than requiring interactive rollout data.
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.
Data sets1Reinforcement learning1
Lecturers
1Connections
2The lectures that define it or assume it, and the concepts next to it.