Reward-DAgger: Robot-Gated Interactive Imitation Learning with General-Purpose Progress-Based Reward Models

Excerpt

arXiv:2610.04054v1 Announce Type: cross Abstract: Recent advances in robot learning have enabled generalist control policies capable of completing a wide range of tasks. However, their performance degrades when deployed in unseen environments, making it critical to detect failures and teach recovery behaviors. Existing runtime monitoring methods often require task- and policy-specific training or hyperparameter tuning, limiting cross-task deployment and introducing additional overhead during ite