A Dynamical Systems Framework for Reinforcement Learning Safety and Robustness Verification

• URL: http://arxiv.org/abs/2508.15588v1
• Date: Thu, 21 Aug 2025 14:00:26 GMT
• Title: A Dynamical Systems Framework for Reinforcement Learning Safety and Robustness Verification
• Authors: Ahmed Nasir, Abdelhafid Zenati,
• Abstract summary: This paper introduces a novel framework that addresses the lack of formal methods for verifying the robustness and safety of learned policies.<n>By leveraging tools from dynamical systems theory, we identify and visualize Lagrangian Coherent Structures (LCS) that act as the hidden "skeleton" governing the system's behavior.<n>We show that this framework provides a comprehensive and interpretable assessment of policy behavior, successfully identifying critical flaws in policies that appear successful based on reward alone.
• Score: 1.104960878651584
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The application of reinforcement learning to safety-critical systems is limited by the lack of formal methods for verifying the robustness and safety of learned policies. This paper introduces a novel framework that addresses this gap by analyzing the combination of an RL agent and its environment as a discrete-time autonomous dynamical system. By leveraging tools from dynamical systems theory, specifically the Finite-Time Lyapunov Exponent (FTLE), we identify and visualize Lagrangian Coherent Structures (LCS) that act as the hidden "skeleton" governing the system's behavior. We demonstrate that repelling LCS function as safety barriers around unsafe regions, while attracting LCS reveal the system's convergence properties and potential failure modes, such as unintended "trap" states. To move beyond qualitative visualization, we introduce a suite of quantitative metrics, Mean Boundary Repulsion (MBR), Aggregated Spurious Attractor Strength (ASAS), and Temporally-Aware Spurious Attractor Strength (TASAS), to formally measure a policy's safety margin and robustness. We further provide a method for deriving local stability guarantees and extend the analysis to handle model uncertainty. Through experiments in both discrete and continuous control environments, we show that this framework provides a comprehensive and interpretable assessment of policy behavior, successfully identifying critical flaws in policies that appear successful based on reward alone.

Related papers

• Safe and Robust Domains of Attraction for Discrete-Time Systems: A Set-Based Characterization and Certifiable Neural Network Estimation [6.2834380315226825]
  Analyzing nonlinear systems with attracting robust invariant sets (RISs) requires estimating their domains of attraction (DOAs)<n>We propose a novel framework for the accurate estimation of safe (state-constrained) and robust DOAs for discrete-time nonlinear uncertain systems.
  arXiv  Detail & Related papers  (2026-03-03T15:26:06Z)
• Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models [57.006252510102506]
  Reinforcement learning (RL) is a powerful framework for optimal decision-making and control but often lacks provable guarantees for safety-critical applications.<n>We introduce a novel recovery-based shielding framework that enables safe RL with a provable safety lower bound for unknown and non-linear continuous dynamical systems.
  arXiv  Detail & Related papers  (2026-02-12T22:03:35Z)
• Kernel-Based Learning of Safety Barriers [0.9367224590861915]
  Rapid integration of AI algorithms in safety-critical applications is raising concerns about the ability to meet stringent safety standards.<n>Traditional tools for formal safety verification struggle with the black-box nature of AI-driven systems.<n>We present a data-driven approach for safety verification and synthesis of black-box systems with discrete-time dynamics.
  arXiv  Detail & Related papers  (2026-01-17T10:42:35Z)
• Safely Learning Controlled Stochastic Dynamics [61.82896036131116]
  We introduce a method that ensures safe exploration and efficient estimation of system dynamics.<n>After training, the learned model enables predictions of the system's dynamics and permits safety verification of any given control.<n>We provide theoretical guarantees for safety and derive adaptive learning rates that improve with increasing Sobolev regularity of the true dynamics.
  arXiv  Detail & Related papers  (2025-06-03T11:17:07Z)
• Investigating Robustness in Cyber-Physical Systems: Specification-Centric Analysis in the face of System Deviations [8.8690305802668]
  A critical attribute of cyber-physical systems (CPS) is robustness, denoting its capacity to operate safely. This paper proposes a novel specification-based robustness, which characterizes the effectiveness of a controller in meeting a specified system requirement. We present an innovative two-layer simulation-based analysis framework designed to identify subtle robustness violations.
  arXiv  Detail & Related papers  (2023-11-13T16:44:43Z)
• Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions [60.26921219698514]
  We introduce a model-uncertainty-aware reformulation of CBF-based safety-critical controllers. We then present the pointwise feasibility conditions of the resulting safety controller. We use these conditions to devise an event-triggered online data collection strategy.
  arXiv  Detail & Related papers  (2022-08-23T05:02:09Z)
• KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Dynamical Systems [66.9461097311667]
  We propose a model-based reinforcement learning framework with formal stability guarantees. The proposed method learns the system dynamics up to a confidence interval using feature representation. We show that KCRL is guaranteed to learn a stabilizing policy in a finite number of interactions with the underlying unknown system.
  arXiv  Detail & Related papers  (2022-06-03T17:27:04Z)
• Joint Differentiable Optimization and Verification for Certified Reinforcement Learning [91.93635157885055]
  In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties. We propose a framework that jointly conducts reinforcement learning and formal verification.
  arXiv  Detail & Related papers  (2022-01-28T16:53:56Z)
• Adversarially Robust Stability Certificates can be Sample-Efficient [14.658040519472646]
  We consider learning adversarially robust stability certificates for unknown nonlinear dynamical systems. We show that the statistical cost of learning an adversarial stability certificate is equivalent, up to constant factors, to that of learning a nominal stability certificate.
  arXiv  Detail & Related papers  (2021-12-20T17:23:31Z)
• Closing the Closed-Loop Distribution Shift in Safe Imitation Learning [80.05727171757454]
  We treat safe optimization-based control strategies as experts in an imitation learning problem. We train a learned policy that can be cheaply evaluated at run-time and that provably satisfies the same safety guarantees as the expert.
  arXiv  Detail & Related papers  (2021-02-18T05:11:41Z)
• Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach [2.741266294612776]
  We propose a model-free safety specification method that learns the maximal probability of safe operation. Our approach constructs a Lyapunov function with respect to a safe policy to restrain each policy improvement stage. It yields a sequence of safe policies that determine the range of safe operation, called the safe set.
  arXiv  Detail & Related papers  (2020-02-24T09:20:03Z)

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.