Lecture Notes on Multi-Armed Bandits
Lecture1: Introduction
Lecture2: Explore-Then-Commit Algorithm
Lecture3: Concentration Inequalities
Lecture4: Successive Elimination Algorithm
Lecture5: The UCB Algorithm
Lecture6: Regret Lower Bounds
Lecture7: Relative Entropy
Lecture8: Divergence Decomposition
Lecture9: Minimax Bound for 2-armed Bernoulli Bandits
Lecture10: Minimax Bound for K-armed Bernoulli Bandits