English

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.

Keywords

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}
}
R2 v1 2026-06-28T20:26:46.635Z