Learning body-affordances to simplify action spaces

TL;DR

This paper introduces a method for discovering and interpolating high-level body-affordances in embodied agents, simplifying complex control tasks by creating low-dimensional, abstract action interfaces based on sensor space embeddings.

Contribution

The proposed approach offers a simpler, more implementable way to learn body-affordances that span the sensor space, aiding in high-dimensional control tasks.

Findings

Successfully learns body-affordances that cover sensor space

Enables interpolation between high-level actions

Simplifies control of complex embodied agents

Abstract

Controlling embodied agents with many actuated degrees of freedom is a challenging task. We propose a method that can discover and interpolate between context dependent high-level actions or body-affordances. These provide an abstract, low-dimensional interface indexing high-dimensional and time- extended action policies. Our method is related to recent ap- proaches in the machine learning literature but is conceptually simpler and easier to implement. More specifically our method requires the choice of a n-dimensional target sensor space that is endowed with a distance metric. The method then learns an also n-dimensional embedding of possibly reactive body-affordances that spread as far as possible throughout the target sensor space.