Safe Reinforcement Learning Using Robust Action Governor

2021-02-21 · Yutong Li, Nan Li, H. Eric Tseng, Anouck Girard, Dimitar Filev, Ilya Kolmanovsky

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.

📄 PDF Abstract BibTeX arXiv:2102.10643

Code (0)

등록된 구현이 없습니다.

Tasks

RAG reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Safe Reinforcement Learning

Robust Action Governor for Uncertain Piecewise Affine Systems with Non-convex Constraints and Safe Reinforcement Learning

2022-07-17 · Yutong Li, Nan Li, H. Eric Tseng, Anouck Girard 외

The action governor is an add-on scheme to a nominal control loop that monitors and adjusts the control actions to enforce safety specifications expressed as pointwise-in-time state and control constraints. In this paper…

RAG Reinforcement Learning (RL)Safe Reinforcement Learning

Safe Control and Learning Using the Generalized Action Governor

2022-11-22 · Nan Li, Yutong Li, Ilya Kolmanovsky, Anouck Girard 외

This article introduces a general framework for safe control and learning based on the generalized action governor (AG). The AG is a supervisory scheme for augmenting a nominal closed-loop system with the ability of stri…

reinforcement-learning Reinforcement Learning (RL)

Towards Verifiably Ethical Robot Behaviour

2015-04-14 · Louise A. Dennis, Michael Fisher, Alan F. T. Winfield

Ensuring that autonomous systems work ethically is both complex and difficult. However, the idea of having an additional `governor' that assesses options the system has, and prunes them to select the most ethical choices…

Decision Making

Control Barrier Function for Linearizable Systems with High Relative Degrees from Signal Temporal Logics: A Reference Governor Approach

2023-09-15 · Kaier Liang, Mingyu Cai, Cristian-Ioan Vasile

This paper considers the safety-critical navigation problem with Signal Temporal Logic (STL) tasks. We developed an explicit reference governor-guided control barrier function (ERG-guided CBF) method that enables the app…

TumorBoard: Evidence-Grounded Multi-Agent Decision Support for Longitudinal Neuro-Oncology

2026-08-04 · Yantong Liu, Zheyu Zhang, Runpeng Liu, Mu Xitang 외 arxiv

Neuro-oncology decisions require coordinated interpretation of serial MRI, pathology, molecular markers, treatment history, performance status, and evolving guidelines. We present TumorBoard, a multi-agent decision-suppo…