ConceptAI & ML
Bayes-adaptive Bernoulli bandits
A formulation starting with a Beta prior over reward functions and updating the posterior distribution based on successes or failures.
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
4The lectures that define it or assume it, and the concepts next to it.