Safe Reinforcement Learning Using Robust Action Governor
Abstract
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 an 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.
Cite
Text
Li et al. "Safe Reinforcement Learning Using Robust Action Governor." Proceedings of the 3rd Conference on Learning for Dynamics and Control, 2021.Markdown
[Li et al. "Safe Reinforcement Learning Using Robust Action Governor." Proceedings of the 3rd Conference on Learning for Dynamics and Control, 2021.](https://mlanthology.org/l4dc/2021/li2021l4dc-safe/)BibTeX
@inproceedings{li2021l4dc-safe,
title = {{Safe Reinforcement Learning Using Robust Action Governor}},
author = {Li, Yutong and Li, Nan and Tseng, H. Eric and Girard, Anouck and Filev, Dimitar and Kolmanovsky, Ilya},
booktitle = {Proceedings of the 3rd Conference on Learning for Dynamics and Control},
year = {2021},
pages = {1093-1104},
volume = {144},
url = {https://mlanthology.org/l4dc/2021/li2021l4dc-safe/}
}