Part of Advances in Neural Information Processing Systems 37 (NeurIPS 2024) Main Conference Track
Shuguang Yu, Shuxing Fang, Ruixin Peng, Zhengling Qi, Fan Zhou, Chengchun Shi
This paper studies off-policy evaluation (OPE) in the presence of unmeasured confounders. Inspired by the two-way fixed effects regression model widely used in the panel data literature, we propose a two-way unmeasured confounding assumption to model the system dynamics in causal reinforcement learning and develop a two-way deconfounder algorithm that devises a neural tensor network to simultaneously learn both the unmeasured confounders and the system dynamics, based on which a model-based estimator can be constructed for consistent policy value estimation. We illustrate the effectiveness of the proposed estimator through theoretical results and numerical experiments.