LGSYFeb 21, 2021

Safe Reinforcement Learning Using Robust Action Governor

arXiv:2102.10643v232 citations
AI Analysis

This addresses safety-critical control problems for real-world applications like automotive systems, but it is incremental as it builds on existing set-theoretic and optimization techniques.

The paper tackles the problem of unsafe behavior in reinforcement learning during exploration by introducing a framework that integrates RL with a Robust Action Governor (RAG) module to manage safety requirements, demonstrated through an application to automotive adaptive cruise control.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes