English

Learning body-affordances to simplify action spaces

Artificial Intelligence 2017-08-16 v1 Robotics

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.

Keywords

Cite

@article{arxiv.1708.04391,
  title  = {Learning body-affordances to simplify action spaces},
  author = {Nicholas Guttenberg and Martin Biehl and Ryota Kanai},
  journal= {arXiv preprint arXiv:1708.04391},
  year   = {2017}
}

Comments

4 pages, 4 figures

R2 v1 2026-06-22T21:14:50.087Z