Learning to Optimize via Information-Directed Sampling

Daniel Russo; Benjamin Van Roy

doi:10.1287/opre.2017.1663

Learning to Optimize via Information-Directed Sampling

Daniel Russo¹; Benjamin Van Roy²

¹ Graduate School of Business, Columbia University, New York, New York 10027 · ² Stanford University, Stanford, California 94305;

Operations Research 2018

We propose information-directed sampling—a new approach to online optimization problems in which a decision maker must balance between exploration and exploitation while learning from partial feedback. Each action is sampled in a manner that minimizes the ratio between squared expected single-period regret and a measure of information gain: the mutual information between the optimal action and the next observation. We establish an expected regret bound for information-directed sampling that applies across a very general class of models and scales with the entropy of the optimal action distribution. We illustrate through simple analytic examples how information-directed sampling accounts for kinds of information that alternative approaches do not adequately address and that this can lead to dramatic performance gains. For the widely studied Bernoulli, Gaussian, and linear bandit problems, we demonstrate state-of-the-art simulation performance. The electronic companion is available at https://doi.org/10.1287/opre.2017.1663 .

DOI: 10.1287/opre.2017.1663
Volume: 66 (1)
Pages: 230-252
Language: en
Export: BibTeX
Sources: crossref