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.
@article{arxiv.2109.05077,
title = {Data Generation Method for Learning a Low-dimensional Safe Region in Safe Reinforcement Learning},
author = {Zhehua Zhou and Ozgur S. Oguz and Yi Ren and Marion Leibold and Martin Buss},
journal= {arXiv preprint arXiv:2109.05077},
year = {2021}
}