LeanBandits
1
Introduction
2
Iterative stochastic algorithms
▶
2.1
Ionescu-Tulcea theorem
▶
Case of a composition-product
2.2
Independence and Markov property
3
Stochastic multi-armed bandits
▶
3.1
Algorithm, bandit and probability space
3.2
Alternative model
3.3
Regret and other bandit quantities
4
Concentration inequalities
5
Bandit algorithms
▶
5.1
Explore-Then-Commit
5.2
UCB
6
Practical Algorithms
7
Sampling
8
Bibliography
Dependency graph
7 Sampling