Conformal Off-Policy Prediction in Contextual Bandits

Understand

Most off-policy evaluation methods for contextual bandits have focused on the expected outcome of a policy, which is estimated via methods that at best provide only asymptotic guarantees.

• However, in many applications, the expectation may not be the best measure of performance as it does not capture the variability of the outcome.
• In addition, particularly in safety-critical settings, stronger guarantees than asymptotic correctness may be required.
• To address these limitations, we consider a novel application of conformal prediction to contextual bandits.