You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector

Excerpt

arXiv:2603.15757v4 Announce Type: replace-cross Abstract: Generative robot policies trained on demonstrations using behavior cloning often learn actions that are sub-optimal or misaligned with respect to the downstream task. Policy improvement approaches aim to bridge this gap and improve the cumulative reward with minimal interventions on the pre-trained policy. However, an impediment to their practical deployment is the requirement of cumbersome hyperparameter tuning specific to model or task