mlsanityData to 14 Oct 2026

On the Definition of Robustness and Resilience of AI Agents for Real-time Congestion Management

arXiv 2504.13314 ↗First posted 17 Apr 2025cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The European Union's Artificial Intelligence (AI) Act defines robustness, resilience, and security requirements for high-risk sectors but lacks detailed methodologies for assessment. This paper introduces a novel framework for quantitatively evaluating the robustness and resilience of reinforcement learning agents in congestion management. Using the AI-friendly digital environment Grid2Op, perturbation agents simulate natural and adversarial disruptions by perturbing the input of AI systems without altering the actual state of the environment, enabling the assessment of AI performance under various scenarios. Robustness is measured through stability and reward impact metrics, while resilience quantifies recovery from performance degradation. The results demonstrate the framework's effectiveness in identifying vulnerabilities and improving AI robustness and resilience for critical applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 19 references that are in the map. First posted on arXiv 17 Apr 2025.

Builds on

8 of 19 references.

References · 8

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2020Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learningcited by 61
  4. 2021Learning to run a Power Network Challenge: a Retrospective Analysiscited by 55
  5. 2017Whatever Does Not Kill Deep Reinforcement Learning, Makes It Strongercited by 35
  6. 2019Verification of Neural Network Behaviour: Formal Guarantees for Power System Applicationscited by 26
  7. 2023Managing power grids through topology actions: A comparative study between advanced rule-based and reinforcement learning agentscited by 16
  8. 2021Understanding the Safety Requirements for Learning-based Power Systems Operationscited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Safe and Robust Reinforcement Learning: Principles and Practice
  2. 2026CCLab: Adversarial Testing of Learning- and Non-Learning-Based Congestion Controllers
  3. 2026Adaptive Utility driven Resource Orchestration for Resilient AI (AURORA-AI)
  4. 2025Quantitative Resilience Modeling for Autonomous Cyber Defense
  5. 2025Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
  6. 2025ARM-IRL: Adaptive Resilience Metric Quantification Using Inverse Reinforcement Learning
  7. 2026Robustness of Reinforcement Learning-Based Congestion Management in Low-Voltage Grids
  8. 2025Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning