Reinforcement learning is a powerful technique for developing new robot behaviors. However, typical lack of safety guarantees constitutes a hurdle for its practical application on real robots. To address this issue, safe reinforcement learning aims to incorporate safety considerations, enabling faster transfer to real robots and facilitating lifelong learning. One promising approach within safe reinforcement learning is the use of control barrier functions. These functions provide a framework to ensure that the system remains in a safe state during the learning process. However, synthesizing control barrier functions is not straightforward and often requires ample domain knowledge. This challenge motivates the exploration of data-driven methods for automatically defining control barrier functions, which is highly appealing. We conduct a comprehensive review of the existing literature on safe reinforcement learning using control barrier functions. Additionally, we investigate various techniques for automatically learning the Control Barrier Functions, aiming to enhance the safety and efficacy of Reinforcement Learning in practical robot applications.
consectetur adipiscing elit. Aenean varius, massa in blandit hendrerit, nunc diam semper risus, eget vestibulum mi est ac diam. Maecenas sed sagittis justo. Class aptent taciti sociosqu ad litora torquent per conubia nostra, per inceptos himenaeos. Pellentesque malesuada suscipit e x a dignissim. Curabitur vitae tincidunt tellus. Sed faucibus lorem metus, ac finibus odio maximus auctor. Phasellus accumsan li
consectetur adipiscing elit. Aenean varius, massa in blandit hendrerit, nunc diam semper risus, eget vestibulum mi est ac diam. Maecenas sed sagittis justo. Class aptent taciti sociosqu ad litora torquent per conubia nostra, per inceptos himenaeos. Pellentesque malesuada suscipit e x a dignissim. Curabitur vitae tincidunt tellus. Sed faucibus lorem metus, ac finibus odio maximus auctor. Phasellus accumsan li
bla bla
bla bla
@misc{guerrier2024learningcontrolbarrierfunctions,
title = {Learning Control Barrier Functions and their application in Reinforcement Learning: A Survey},
author = {Maeva Guerrier and Hassan Fouad and Giovanni Beltrame}
year = {2024},
eprint = {2404.16879},
archivePrefix = {arXiv},
primaryClass = {cs.LG},
url = {https://arxiv.org/abs/2404.16879},
}