Reinforcement Learning (RL) is essentially a trial-and-error learning procedure which may cause unsafe behavior during the exploration-and-exploitation process. This hinders the application of RL to real-world control problems, especially to those for safety-critical systems. In this paper, we introduce a framework for safe RL that is based on integration of a RL algorithm with an add-on safety supervision module, called the Robust Action Governor (RAG), which exploits set-theoretic techniques and online optimization to manage safety-related requirements during learning. We illustrate this proposed safe RL framework through an application to automotive adaptive cruise control.
@article{arxiv.2102.10643,
title = {Safe Reinforcement Learning Using Robust Action Governor},
author = {Yutong Li and Nan Li and H. Eric Tseng and Anouck Girard and Dimitar Filev and Ilya Kolmanovsky},
journal= {arXiv preprint arXiv:2102.10643},
year = {2021}
}