Mathematics of Machine Learning
Toward the understanding of partial-monitoring games
Contextual Bandits with Similarity Information
Monte-Carlo Planning: Basic Principles and Recent Progress
Bandit Algorithms for Online Linear Optimization
From Bandits to Experts: On the Value of Side-Observations
Piecewise-Stationary Bandit Problems with Side Information
Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search
Some Recent Bandit Results
PAC-Bayesian Bounds and Aggregation