Invariant Causal Imitation Learning For Generalizable Policies

Abstract

Consider learning an imitation policy on the basis of demonstrated behavior from multiple environments, with an eye towards deployment in an unseen environment. Since the observable features from each setting may be different, directly learning individual policies as mappings from features to actions is prone to spurious correlations -- and may not generalize well. However, the expert's policy is often a function of a shared latent structure underlying those observable features that is invariant across settings. By leveraging data from multiple environments, we propose Invariant Causal Imitation Learning (ICIL), a novel technique in which we learn a feature representation that is invariant across domains, on the basis of which we learn an imitation policy that matches expert behavior. To cope with transition dynamics mismatch, ICIL learns a shared representation of causal features (for all training environments), that is disentangled from the specific representations of noise variables

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybica2023invariant

Related papers

• Causal Imitation Learning Under Temporally Correlated Noise (2022)0.00
• Causal Imitation Learning Under Expert-observable And Expert-unobservable Confounding (2025)0.00
• Causal Confusion In Imitation Learning (2019)0.00
• Confounded Causal Imitation Learning With Instrumental Variables (2025)0.00
• Causal Imitation Learning Under Measurement Error And Distribution Shift (2026)0.00
• Fully General Online Imitation Learning (2021)0.00
• Causal Imitation Learning With Unobserved Confounders (2022)0.00
• Robust Imitation Learning Against Variations In Environment Dynamics (2022)0.00