为强化学习在物理系统中的安全评估提供可验证框架
Evaluating Reinforcement Learning Safety and Trustworthiness in Cyber-Physical Systems
- 构建SAFE-RL框架，通过设计科学方法支撑RL系统的开发与验证
- 在小型无人机系统中验证框架，实现对3个RL应用的安全评估
- 适合关注RL系统安全落地的研究者与工程人员
网络物理系统（CPS）常采用强化学习（RL）技术以动态适应环境并优化性能，但构建RL组件的安全论证仍具挑战。为此，我们提出SAFE-RL（用于评估强化学习的安全与问责框架），支持基于RL的CPS的开发、验证与安全部署。采用设计科学方法构建该框架，并在三个小型无人飞行器（sUAS）的RL应用中演示其使用效果。
原文摘要 · Abstract (English)
Cyber-Physical Systems (CPS) often leverage Reinforcement Learning (RL) techniques to adapt dynamically to changing environments and optimize performance. However, it is challenging to construct safety cases for RL components. We therefore propose the SAFE-RL (Safety and Accountability Framework for Evaluating Reinforcement Learning) for supporting the development, validation, and safe deployment of RL-based CPS. We adopt a design science approach to construct the framework and demonstrate its use in three RL applications in small Uncrewed Aerial systems (sUAS)
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。