The paper introduces PACOPP, a rejection-sampling plus conformal prediction algorithm that gives probably approximately correct coverage guarantees for off-policy reward prediction intervals in contextual bandits.
Accountable off-policy evaluation with kernel B ellman statistics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PAC Off-Policy Prediction of Contextual Bandits
The paper introduces PACOPP, a rejection-sampling plus conformal prediction algorithm that gives probably approximately correct coverage guarantees for off-policy reward prediction intervals in contextual bandits.