The paper derives the semiparametric efficiency bound for off-policy evaluation in MDPs and introduces a doubly robust, cross-fitted estimator (DRL) that achieves it.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes
The paper derives the semiparametric efficiency bound for off-policy evaluation in MDPs and introduces a doubly robust, cross-fitted estimator (DRL) that achieves it.