CP-Gen and DR-PPI are two estimators that aim to provide valid confidence intervals for off-policy evaluation with synthetic auxiliary data, with asymptotic guarantees for DR-PPI and empirical coverage for both.
Assumption 4(Common support).π e(a|s)>0→π b(a|s)>0,∀s∈S,∀a∈A
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
PERRY: Policy Evaluation with Confidence Intervals using Auxiliary Data
CP-Gen and DR-PPI are two estimators that aim to provide valid confidence intervals for off-policy evaluation with synthetic auxiliary data, with asymptotic guarantees for DR-PPI and empirical coverage for both.