ConceptAI & ML
Bayesian upper confidence bounds
An approach that uses Bayes law to compute a posterior distribution over action values and adds a multiple of the posterior standard deviation to estimate an upper confidence bound.
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.