Reusing motor commands to learn object interaction

Abstract

We propose the Reuse algorithm, that exploit data produced during the exploration of an first environment to efficiently bootstrap the exploration of second, different but related environment. The effect of the Reuse algorithm is to produce a high diversity of effects early during exploration. The algorithm only constrains the environments to share the same motor space, and makes no assumptions about learning algorithms or sensory modalities. We illustrate our algorithm on a 6-joints robotic arm interacting with a virtual object, and show that our algorithm is robust to dissimilar environments, and significantly improves the early exploration of similar ones.