Xiaoke Zhang

Off-Policy Evaluation for Episodic Partially Observable Markov Decision Processes under Non-Parametric Models

We study the problem of off-policy evaluation (OPE) for episodic Partially Observable Markov Decision Processes (POMDPs) with continuous states. Motivated by the recently proposed proximal causal inference framework, we develop a non-parametric identification result for estimating the policy value v…