ConceptAI & ML
Bandit problem
A problem where you must choose between multiple actions with unknown, stochastic immediate rewards to find the best one through trial and error.
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.
Reward1Stochastic outcomes1
Lecturers
1Connections
2The lectures that define it or assume it, and the concepts next to it.