Data Efficient Behavior Cloning for Fine Manipulation Via Continuity-Based Corrective Labels

We consider imitation learning with access only to expert demonstrations, whose real-world application is often limited by covariate shift due to compounding errors during execution. We investigate the effectiveness of the Continuity- based Corrective Labels for Imitation Learning (CCIL) frame- work in mitigating this issue for real-world fine manipulation tasks. CCIL generates corrective labels by learning a locally continuous dynamics model from demonstrations to guide the agent back toward expert states. Through extensive experiments on insertion and fine grasping tasks, we provide the first em- pirical validation that CCIL can significantly improve imitation learning performance despite discontinuities present in contact- rich manipulation. We find that: (1) real-world manipulation exhibits sufficient local smoothness to apply CCIL, (2) gener- ated corrective labels are most beneficial in low-data regimes, and (3) label filtering based on estimated dynamics model error enables performance gains. To effectively apply CCIL to robotic domains, we offer a practical instantiation of the framework and insights into design choices and hyperparameter selection. Our work demonstrates CCIL’s practicality for alleviating compounding errors in imitation learning on physical robots.