# Structured Policy Representation: Imposing Stability in arbitrarily conditioned dynamic systems

arXiv: https://arxiv.org/abs/2012.06224 · HTML: https://mlsanity.com/paper/2012.06224/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2020.

## Built on by (most cited first, 1 of 1)

- [Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes](https://mlsanity.com/paper/2209.07696/) (2022)

## Abstract (arXiv)

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.