DATA SCALING LAWS IN IMITATION LEARNING FORROBOTIC MANIPULATION

发表时间：24 Oct 2024

论文链接：https://readpaper.com/pdf-annotate/note?pdfId=2550555330677924608&noteId=2609088511190122752

作者单位：Tsinghua University（清华高阳组）

Motivation：Data scaling has revolutionized fields like natural language processing and computer vision, providing models with remarkable generalization capabilities. 想要研究具身的 scaling law。

解决方法：In this paper, we investigate whether similar data scaling laws exist in robotics, particularly in robotic manipulation, and whether appropriate data scaling can yield single-task robot policies that can be deployed zero-shot for any object within the same category in any environment.

实现方式：By collecting data across numerous environments and objects, we study how a policy's generalization perfor