LeanBandits
1
Introduction
2
Stochastic multi-armed bandits
▶
2.1
Bandit model and probability space
2.2
Regret and other bandit quantities
2.3
Alternative model
3
Concentration inequalities
4
Bandit algorithms
▶
4.1
Explore-Then-Commit
4.2
UCB
5
Practical Algorithms
6
Sampling
Dependency graph
6 Sampling