摘要：This work aims to study off-policy evaluation (OPE) under scenarios where two key reinforcement learning (RL) assumptions – temporal stationarity and individual homogeneity are both violated. To handle the “double inhomogeneities”, we propose a class of latent factor models for the reward and observation transition functions, under which we develop a general OPE framework that consists of both model-based and model-free approaches. It contributes to a deeper understanding of OPE in environments, where standard RL assumptions are not met, and provides several practical approaches in these settings. We establish the theoretical properties of the proposed value estimators and empirically show that our approach outperforms competing methods that ignore either temporal nonstationarity or individual heterogeneity. Finally, we illustrate our method on a data set from the Medical Information Mart for Intensive Care.

个人简介：Dr. Zeyu Bian is a Postdoctoral Research Associate at Miami Herbert Business School. He earned his PhD in Biostatistics from McGill University in 2022. His research interests include statistical reinforcement learning, dynamic treatment regimens and causal inference.