# Learning a Low-dimensional Representation of a Safe Region for Safe Reinforcement Learning on Dynamical Systems

arXiv: https://arxiv.org/abs/2010.09555 · HTML: https://mlsanity.com/paper/2010.09555/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2020.

## Built on by (most cited first, 6 of 6)

- [Opinion-Guided Reinforcement Learning](https://mlsanity.com/paper/2405.17287/) (2024)
- [Towards Fast Safe Online Reinforcement Learning via Policy Finetuning](https://mlsanity.com/paper/2412.04426/) (2024)
- [Data Generation Method for Learning a Low-dimensional Safe Region in Safe Reinforcement Learning](https://mlsanity.com/paper/2109.05077/) (2021)
- [GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model](https://mlsanity.com/paper/2406.03912/) (2024)
- [MORTAR: A Model-based Runtime Action Repair Framework for AI-enabled Cyber-Physical Systems](https://mlsanity.com/paper/2408.03892/) (2024)
- [AttentionSwarm: Reinforcement Learning with Attention Control Barier Function for Crazyflie Drones in Dynamic Environments](https://mlsanity.com/paper/2503.07376/) (2025)

## Abstract (arXiv)

For safely applying reinforcement learning algorithms on high-dimensional nonlinear dynamical systems, a simplified system model is used to formulate a safe reinforcement learning framework. Based on the simplified system model, a low-dimensional representation of the safe region is identified and is used to provide safety estimates for learning algorithms. However, finding a satisfying simplified system model for complex dynamical systems usually requires a considerable amount of effort. To overcome this limitation, we propose in this work a general data-driven approach that is able to efficiently learn a low-dimensional representation of the safe region. Through an online adaptation method, the low-dimensional representation is updated by using the feedback data such that more accurate safety estimates are obtained. The performance of the proposed approach for identifying the low-dimensional representation of the safe region is demonstrated with a quadcopter example. The results show that, compared to previous work, a more reliable and representative low-dimensional representation of the safe region is derived, which then extends the applicability of the safe reinforcement learning framework.