We present a new family of deep neural network-based dynamic systems. The presented dynamics are globally stable and can be conditioned with an arbitrary context state. We show how these dynamics can be used as structured robot policies. Global stability is one of the most important and straightforward inductive biases as it allows us to impose reasonable behaviors outside the region of the demonstrations.
@article{arxiv.2012.06224,
title = {Structured Policy Representation: Imposing Stability in arbitrarily conditioned dynamic systems},
author = {Julen Urain and Davide Tateo and Tianyu Ren and Jan Peters},
journal= {arXiv preprint arXiv:2012.06224},
year = {2020}
}
Comments
Presented in NeurIPS 2020, 3rd Robot Learning Workshop. Stability, Few-Shot Learning, Deep Dynamic Systems