Abstract: Learning from demonstration is a powerful method for robotic skill acquisition. However, the significant expense of collecting such action-labeled robot data presents a major bottleneck.
Abstract: Class Incremental Learning (CIL) aims to enable models to learn new classes sequentially while retaining knowledge of previous ones. Although current methods have alleviated catastrophic ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback