initial update

_publications/2020data.md

@@ -0,0 +1,16 @@
+---
+title: "Data Generation Method for Learning a Low-dimensional Safe Region in Safe Reinforcement Learning"
+collection: publications
+permalink: /publication/2020data
+authorlist: '<b>Zhehua Zhou</b>, Ozgur S Oguz, Yi Ren, Marion Leibold, Martin Buss'
+excerpt: 'In this work, we investigate how different training data will affect the safe reinforcement learning approach based on data-driven model order reduction.'
+date: 2021-09-10
+venue: 'ArXiv Preprint:2109.05077'
+# slidesurl: 'http://academicpages.github.io/files/slides1.pdf'
+paperurl: 'https://arxiv.org/abs/2109.05077'
+# citation: 'Your Name, You. (2009). &quot;Paper Title Number 1.&quot; <i>Journal 1</i>. 1(1).'
+pubtype: 'preprint'
+highlight: 'no'
+---
+
+Safe reinforcement learning aims to learn a control policy while ensuring that neither the system nor the environment gets damaged during the learning process. For implementing safe reinforcement learning on highly nonlinear and high-dimensional dynamical systems, one possible approach is to find a low-dimensional safe region via data-driven feature extraction methods, which provides safety estimates to the learning algorithm. As the reliability of the learned safety estimates is data-dependent, we investigate in this work how different training data will affect the safe reinforcement learning approach. By balancing between the learning performance and the risk of being unsafe, a data generation method that combines two sampling methods is proposed to generate representative training data. The performance of the method is demonstrated with a three-link inverted pendulum example.