Evaluating Reinforcement Learning Safety and Trustworthiness in Cyber-Physical Systems

2025-03-12 · Katherine Dearstyne, Pedro, Alarcon Granadeno, Theodore Chambers, Jane Cleland-Huang

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)

📄 PDF Abstract BibTeX arXiv:2503.09388

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

ADOPT Please enter a description about the method here

Trustworthiness for an Ultra-Wideband Localization Service

2024-08-10 · Philipp Peterseil, Bernhard Etzlinger, Jan Horáček, Roya Khanzadeh 외

Trustworthiness assessment is an essential step to assure that interdependent systems perform critical functions as anticipated, even under adverse conditions. In this paper, a holistic trustworthiness assessment framewo…

Synchronous Signal Temporal Logic for Decidable Verification of Cyber-Physical Systems

2026-03-26 · Partha Roop, Sobhan Chatterjee, Avinash Malik, Nathan Allen 외 arxiv

Many Cyber Physical System (CPS) work in a safety-critical environment, where correct execution, reliability and trustworthiness are essential. Signal Temporal Logic (STL) provides a formal framework for checking safety-…

Ontology-Based Reasoning about the Trustworthiness of Cyber-Physical Systems

2018-03-20 · Marcello Balduccini, Edward Griffor, Michael Huth, Claire Vishik 외

It has been challenging for the technical and regulatory communities to formulate requirements for trustworthiness of the cyber-physical systems (CPS) due to the complexity of the issues associated with their design, dep…

Constraints Satisfiability Driven Reinforcement Learning for Autonomous Cyber Defense

2021-04-19 · Ashutosh Dutta, Ehab Al-Shaer, Samrat Chatterjee

With the increasing system complexity and attack sophistication, the necessity of autonomous cyber defense becomes vivid for cyber and cyber-physical systems (CPSs). Many existing frameworks in the current state-of-the-a…

Decision Making reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets

2026-07-09 · Shilin Ou, Yifan Xu, Luyao Zhang arxiv

As agentic AI systems are increasingly applied to cyber-physical environments, their evaluation requires assessment of both task performance and trustworthiness. In decentralized energy markets, autonomous agents may imp…