Faster Rates for Policy Learning

Understand

This article improves the existing proven rates of regret decay in optimal policy estimation.

• We give a margin-free result showing that the regret decay for estimating a within-class optimal policy is second-order for empirical risk minimizers over Donsker classes, with regret decaying at a faster rate than the standard error of an efficient estimator of the value of an optimal policy.
• We also give a result from the classification literature that shows that faster regret decay is possible via plug-in estimation provided a margin condition holds.
• Four examples are considered.