Mathematics of Machine Learning
Monte-Carlo Planning: Basic Principles and Recent Progress
Finding a most biased coin with fewest flips
Hybrid Stochastic-Adversarial On-Line Learning
Exploration vs. Exploitation Challenge
Bayesian Numerical Analysis
On the Complexity of A/B Testing
A simple multi-armed bandit algorithm with optimal variation-bounded regret
Online Learning with Predictable Sequences
Forced-Exploration Based Algortihms for Playing in Stochastic Linear Bandits