mlsanityData to 14 Oct 2026

Parameter Stress Analysis in Reinforcement Learning: Applying Synaptic Filtering to Policy Networks

arXiv 2506.23036 ↗First posted 28 Jun 2025cs.LG cs.SY eess.SYcited by 0

On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance

Abstract (arXiv)

This paper explores reinforcement learning (RL) policy robustness by systematically analyzing network parameters under internal and external stresses. textcolorblackWe apply synaptic filtering methods using high-pass, low-pass, and pulse-wave filters from citeppravin2024fragility, as an internal stress by selectively perturbing parameters, while adversarial attacks apply external stress through modified agent observations. This dual approach enables the classification of parameters as textitfragile, textitrobust, or textitantifragile, based on their influence on policy performance in clean and adversarial settings. Parameter scores are defined to quantify these characteristics, and the framework is validated on proximal policy optimization (PPO)-trained agents in Mujoco continuous control environments. The results highlight the presence of antifragile parameters that enhance policy performance under stress, demonstrating the potential of targeted filtering techniques to improve RL policy adaptability. These insights provide a foundation for future advancements in the design of robust and antifragile RL systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods. Builds on 10 of its 13 references that are in the map. First posted on arXiv 28 Jun 2025.

Builds on

10 of 13 references.

References · 10

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2016Adversarial examples in the physical worldcited by 1,769
  5. 2016OpenAI Gymcited by 1,736
  6. 2019Importance Estimation for Neural Network Pruningcited by 541
  7. 2017Adversarial Attacks on Neural Network Policiescited by 320
  8. 2019What's Hidden in a Randomly Weighted Neural Network?cited by 237
  9. 2023Antifragile Control Systems: The case of mobile robot trajectory tracking in the presence of uncertaintycited by 2
  10. 2023Fragility, Robustness and Antifragility in Deep Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Robust Policy Optimization via Adversarial Importance Sampling
  2. 2024Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
  3. 2026Robust Adversarial Policy Optimization Under Dynamics Uncertainty
  4. 2024On the Perturbed States for Transformed Input-robust Reinforcement Learning
  5. 2025Policy Disruption in Reinforcement Learning:Adversarial Attack with Large Language Models and Critical State Identification
  6. 2024Safe and Robust Reinforcement Learning: Principles and Practice
  7. 2026Taming the Adversary: A Cost-to-Disturbance Ratio Approach to Adversarial Reinforcement Learning
  8. 2024Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model