Article

SCRIM: Quantifying State Criticality in Imitation Learning

The authors propose SCRIM, a state criticality measure that uses an adversarial perturbation policy and a value critic to estimate the worst-case degradation in downstream value caused by small perturbations to expert actions, scoring each demonstration state. These scores can be used to reweight behavior-cloning losses or to select compact, high-value subsets of demonstrations, reducing training data while maintaining performance. The method is evaluated on a variety of simulated and real robot manipulation tasks, and the paper was accepted to CoRL 2026.

Part of the event: SCRIM: Quantifying State Criticality in Imitation Learning

This page provides a summary and source link only.