ConceptAI & ML
One-step MDPs
A simplified class of Markov Decision Processes where an episode starts in a state, the agent takes a single action, receives a reward, and the episode immediately terminates.
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.