RL-STPA: Adapting System-Theoretic Hazard Analysis for Safety-Critical Reinforcement Learning

• URL: http://arxiv.org/abs/2604.15201v1
• Date: Thu, 16 Apr 2026 16:27:42 GMT
• Title: RL-STPA: Adapting System-Theoretic Hazard Analysis for Safety-Critical Reinforcement Learning
• Abstract summary: This paper introduces Reinforcement Learning System-Theoretic Process Analysis (RL-STPA)<n> RL-STPA adapts conventional hazard analysis to address RL's unique challenges through three key contributions.<n>We demonstrate RL-STPA in the safety-critical test case of autonomous drone navigation and landing.
• Score: 0.8291942198324129
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As reinforcement learning (RL) deployments expand into safety-critical domains, existing evaluation methods fail to systematically identify hazards arising from the black-box nature of neural network enabled policies and distributional shift between training and deployment. This paper introduces Reinforcement Learning System-Theoretic Process Analysis (RL-STPA), a framework that adapts conventional STPA's systematic hazard analysis to address RL's unique challenges through three key contributions: hierarchical subtask decomposition using both temporal phase analysis and domain expertise to capture emergent behaviors, coverage-guided perturbation testing that explores the sensitivity of state-action spaces, and iterative checkpoints that feed identified hazards back into training through reward shaping and curriculum design. We demonstrate RL-STPA in the safety-critical test case of autonomous drone navigation and landing, revealing potential loss scenarios that can be missed by standard RL evaluations. The proposed framework provides practitioners with a toolkit for systematic hazard analysis, quantitative metrics for safety coverage assessment, and actionable guidelines for establishing operational safety bounds. While RL-STPA cannot provide formal guarantees for arbitrary neural policies, it offers a practical methodology for systematically evaluating and improving RL safety and robustness in safety-critical applications where exhaustive verification methods remain intractable.

Related papers

• Sampling-Based Safe Reinforcement Learning [30.21184523512902]
  We propose a model-based reinforcement learning algorithm that maintains safety throughout the learning process.<n>This formulation approximates an intractable worst-case optimization over uncertain dynamics.<n>Under regularity conditions, we derive high-probability guarantees of safety throughout learning and a finite-time sample complexity bound for recovering a near-optimal policy.
  arXiv  Detail & Related papers  (2026-05-19T07:21:53Z)
• Safe Continual Reinforcement Learning in Non-stationary Environments [2.8757268399458855]
  Reinforcement learning (RL) offers a compelling data-driven paradigm for synthesizing controllers for complex systems when accurate physical models are unavailable.<n>Most existing control-oriented RL methods assume stationarity and, therefore, struggle in real-world non-stationary deployments.<n>We study safe continual reinforcement learning algorithms that can adapt over the system's lifetime while preserving safety.
  arXiv  Detail & Related papers  (2026-04-21T17:58:32Z)
• 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)
• Control Synthesis of Cyber-Physical Systems for Real-Time Specifications through Causation-Guided Reinforcement Learning [3.608670495432032]
  Signal temporal logic (STL) has emerged as a powerful formalism of expressing real-time constraints.<n> reinforcement learning (RL) has become an important method for solving control synthesis problems in unknown environments.<n>We propose an online reward generation method guided by the online causation monitoring of STL.
  arXiv  Detail & Related papers  (2025-10-09T02:49:28Z)
• 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)
• Systematic Hazard Analysis for Frontier AI using STPA [0.0]
  frontier AI companies currently do not describe in detail any structured approach to identifying and analysing hazards.<n>A (Systems-Theoretic Process Analysis) is a systematic methodology for identifying how complex systems can become unsafe, leading to hazards.<n>We evaluateA's ability to broaden the scope, improve traceability and strengthen the robustness of safety assurance for frontier AI systems.
  arXiv  Detail & Related papers  (2025-06-02T15:28:34Z)
• Safe and Robust Reinforcement Learning: Principles and Practice [0.0]
  Reinforcement Learning has shown remarkable success in solving relatively complex tasks. The deployment of RL systems in real-world scenarios poses significant challenges related to safety and robustness. This paper explores the main dimensions of the safe and robust RL landscape, encompassing algorithmic, ethical, and practical considerations.
  arXiv  Detail & Related papers  (2024-03-27T13:14:29Z)
• Analyzing Adversarial Inputs in Deep Reinforcement Learning [53.3760591018817]
  We present a comprehensive analysis of the characterization of adversarial inputs, through the lens of formal verification. We introduce a novel metric, the Adversarial Rate, to classify models based on their susceptibility to such perturbations. Our analysis empirically demonstrates how adversarial inputs can affect the safety of a given DRL system with respect to such perturbations.
  arXiv  Detail & Related papers  (2024-02-07T21:58:40Z)
• 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)
• Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems [17.679681019347065]
  Deep Reinforcement Learning (DRL) has achieved impressive performance in robotics and autonomous systems (RAS) A key challenge to its deployment in real-life operations is the presence of spuriously unsafe DRL policies. This paper proposes a novel quantitative reliability assessment framework for DRL-controlled RAS.
  arXiv  Detail & Related papers  (2022-10-26T19:25:46Z)
• Safe Reinforcement Learning via Confidence-Based Filters [78.39359694273575]
  We develop a control-theoretic approach for certifying state safety constraints for nominal policies learned via standard reinforcement learning techniques. We provide formal safety guarantees, and empirically demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2022-07-04T11:43:23Z)
• Benchmarking Safe Deep Reinforcement Learning in Aquatic Navigation [78.17108227614928]
  We propose a benchmark environment for Safe Reinforcement Learning focusing on aquatic navigation. We consider a value-based and policy-gradient Deep Reinforcement Learning (DRL) We also propose a verification strategy that checks the behavior of the trained models over a set of desired properties.
  arXiv  Detail & Related papers  (2021-12-16T16:53:56Z)

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.