Causal Imitation Learning Under Measurement Error And Distribution Shift

Abstract

We study offline imitation learning (IL) when part of the decision-relevant state is observed only through noisy measurements and the distribution may change between training and deployment. Such settings induce spurious state-action correlations, so standard behavioral cloning (BC) -- whether conditioning on raw measurements or ignoring them -- can converge to systematically biased policies under distribution shift. We propose a general framework for IL under measurement error, inspired by explicitly modeling the causal relationships among the variables, yielding a target that retains a causal interpretation and is robust to distribution shift. Building on ideas from proximal causal inference, we introduce \texttt\{CausIL\}, which treats noisy state observations as proxy variables, and we provide identification conditions under which the target policy is recoverable from demonstrations without rewards or interactive expert queries. We develop estimators for both discrete and continuou

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybo2026causal

Related papers

• Feedback In Imitation Learning: The Three Regimes Of Covariate Shift (2021)0.00
• Causal Imitation Learning Under Temporally Correlated Noise (2022)0.00
• Mitigating Covariate Shift In Imitation Learning Via Offline Data Without Great Coverage (2021)0.00
• Causal Imitation Learning Under Expert-observable And Expert-unobservable Confounding (2025)0.00
• Causal Confusion In Imitation Learning (2019)0.00
• Offline Imitation Learning With Suboptimal Demonstrations Via Relaxed Distribution Matching (2023)6.77
• Invariant Causal Imitation Learning For Generalizable Policies (2023)0.00
• Confounded Causal Imitation Learning With Instrumental Variables (2025)0.00