• Focuses on sample complexity and algorithms for online learning and decision-making. Prediction of individual sequences, online regression, and online density estimation. Multi-armed and contextual bandits. Decision-making with structured observations and the decision-estimation coefficient. Frequentist and Bayesian approaches. Reinforcement learning: tabular methods and function approximation. Behavioral and neural mechanisms of reinforcement learning.

• Textbook Information

There is no information available for this course.