Safe Reinforcement Learning Using Robust Action Governor
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.