Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning
Machine Learning
2024-12-10 v1 Machine Learning
Abstract
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.
Cite
@article{arxiv.2412.05783,
title = {Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning},
author = {Shuguang Yu and Shuxing Fang and Ruixin Peng and Zhengling Qi and Fan Zhou and Chengchun Shi},
journal= {arXiv preprint arXiv:2412.05783},
year = {2024}
}