Confounding-robust Policy Evaluation In Infinite-horizon Reinforcement Learning

Abstract

Off-policy evaluation of sequential decision policies from observational data is necessary in applications of batch reinforcement learning such as education and healthcare. In such settings, however, unobserved variables confound observed actions, rendering exact evaluation of new policies impossible, i.e., unidentifiable. We develop a robust approach that estimates sharp bounds on the (unidentifiable) value of a given policy in an infinite-horizon problem given data from another policy with unobserved confounding, subject to a sensitivity model. We consider stationary or baseline unobserved confounding and compute bounds by optimizing over the set of all stationary state-occupancy ratios that agree with a new partially identified estimating equation and the sensitivity model. We prove convergence to the sharp bounds as we collect more confounded data. Although checking set membership is a linear program, the support function is given by a difficult nonconvex optimization problem. We d

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykallus2020confounding

Related papers

• Off-policy Evaluation In Infinite-horizon Reinforcement Learning With Latent Confounders (2020)0.00
• Robust Fitted-q-evaluation And Iteration Under Sequentially Exogenous Unobserved Confounders (2023)0.00
• Reinforcement Learning With Continuous Actions Under Unmeasured Confounding (2025)0.00
• Doubly Robust Interval Estimation For Optimal Policy Evaluation In Online Learning (2021)0.00
• Online Estimation And Inference For Robust Policy Evaluation In Reinforcement Learning (2023)2.26
• Black-box Off-policy Estimation For Infinite-horizon Reinforcement Learning (2020)0.00
• Proximal Reinforcement Learning: Efficient Off-policy Evaluation In Partially Observed Markov Decision Processes (2021)0.00
• Doubly Robust Off-policy Value And Gradient Estimation For Deterministic Policies (2020)0.00