Evaluating Reinforcement Learning Safety and Trustworthiness in Cyber-Physical Systems

• URL: http://arxiv.org/abs/2503.09388v1
• Date: Wed, 12 Mar 2025 13:33:07 GMT
• Title: Evaluating Reinforcement Learning Safety and Trustworthiness in Cyber-Physical Systems
• Authors: Katherine Dearstyne, Pedro, Alarcon Granadeno, Theodore Chambers, Jane Cleland-Huang,
• Abstract summary: We propose the SAFE-RL (Safety and Accountability Framework for evaluating Reinforcement Learning) for supporting the development, validation, and safe deployment of RL-based CPS.<n>We adopt a design science approach to construct the framework and demonstrate its use in three RL applications in small Uncrewed Aerial systems (sUAS)
• Score: 38.48645678884814
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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)

Related papers

• Assuring the Safety of Reinforcement Learning Components: AMLAS-RL [3.892872471787381]
  We adapt AMLAS to provide a framework for generating assurance arguments for an RL-enabled system.<n>We demonstrate AMLAS-RL using a running example of a wheeled vehicle tasked with reaching a target goal without collision.
  arXiv  Detail & Related papers  (2025-07-08T15:01:51Z)
• ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning [48.536695794883826]
  We present ActSafe, a novel model-based RL algorithm for safe and efficient exploration.<n>We show that ActSafe guarantees safety during learning while also obtaining a near-optimal policy in finite time.<n>In addition, we propose a practical variant of ActSafe that builds on latest model-based RL advancements.
  arXiv  Detail & Related papers  (2024-10-12T10:46:02Z)
• GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model [8.915288771953545]
  We introduce a novel Generalizable Safety enhancer (GenSafe) that is able to overcome the challenge of data insufficiency.<n>We evaluate GenSafe on multiple SRL approaches and benchmark problems.<n>Our proposed GenSafe not only offers a novel measure to augment existing SRL methods but also shows broad compatibility with various SRL algorithms.
  arXiv  Detail & Related papers  (2024-06-06T09:51:30Z)
• Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning [57.84059344739159]
  "Shielding" is a popular technique to enforce safety inReinforcement Learning (RL) We propose a new permissibility-based framework to deal with safety and shield construction.
  arXiv  Detail & Related papers  (2024-05-29T18:00:21Z)
• Approximate Model-Based Shielding for Safe Reinforcement Learning [83.55437924143615]
  We propose a principled look-ahead shielding algorithm for verifying the performance of learned RL policies. Our algorithm differs from other shielding approaches in that it does not require prior knowledge of the safety-relevant dynamics of the system. We demonstrate superior performance to other safety-aware approaches on a set of Atari games with state-dependent safety-labels.
  arXiv  Detail & Related papers  (2023-07-27T15:19:45Z)
• Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments [4.111899441919165]
  This study proposes a safe and sample-efficient reinforcement learning (RL) framework to address two major challenges. We use the safe set algorithm (SSA) to monitor and modify the nominal controls, and evaluate SSA+RL in a clustered dynamic environment. Our framework can achieve better safety performance compare to other safe RL methods during training and solve the task with substantially fewer episodes.
  arXiv  Detail & Related papers  (2023-03-24T20:29:17Z)
• Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks [70.76757529955577]
  This paper revisits prior work in this scope from the perspective of state-wise safe RL. We propose Unrolling Safety Layer (USL), a joint method that combines safety optimization and safety projection. To facilitate further research in this area, we reproduce related algorithms in a unified pipeline and incorporate them into SafeRL-Kit.
  arXiv  Detail & Related papers  (2022-12-12T06:30:17Z)
• Improving Robustness of Reinforcement Learning for Power System Control with Adversarial Training [71.7750435554693]
  We show that several state-of-the-art RL agents proposed for power system control are vulnerable to adversarial attacks. Specifically, we use an adversary Markov Decision Process to learn an attack policy, and demonstrate the potency of our attack. We propose to use adversarial training to increase the robustness of RL agent against attacks and avoid infeasible operational decisions.
  arXiv  Detail & Related papers  (2021-10-18T00:50:34Z)
• Constraints Satisfiability Driven Reinforcement Learning for Autonomous Cyber Defense [7.321728608775741]
  We present a new hybrid autonomous agent architecture that aims to optimize and verify defense policies of reinforcement learning (RL) We use constraints verification (using satisfiability modulo theory (SMT)) to steer the RL decision-making toward safe and effective actions. Our evaluation of the presented approach in a simulated CPS environment shows that the agent learns the optimal policy fast and defeats diversified attack strategies in 99% cases.
  arXiv  Detail & Related papers  (2021-04-19T01:08:30Z)
• Safe Reinforcement Learning Using Robust Action Governor [6.833157102376731]
  Reinforcement Learning (RL) is essentially a trial-and-error learning procedure which may cause unsafe behavior during the exploration-and-exploitation process. In this paper, we introduce a framework for safe RL that is based on integration of an RL algorithm with an add-on safety supervision module. We illustrate this proposed safe RL framework through an application to automotive adaptive cruise control.
  arXiv  Detail & Related papers  (2021-02-21T16:50:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.