ConceptAI & ML
Reinforcement learning characteristics
Reinforcement learning differs from other machine learning paradigms because it lacks a supervisor and relies solely on a reward signal, feedback is delayed rather than instantaneous, time and sequential data matter, and the agent's actions actively affect the data it receives.
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.