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

arXiv: https://arxiv.org/abs/2506.23036 · HTML: https://mlsanity.com/paper/2506.23036/

## 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.

## Placed in

- Deep reinforcement learning methods / [Adversarial robustness and RL in finance](https://mlsanity.com/deeprl/adversarial-robustness-and-rl-in-finance/)

## Builds on (most cited first, 10 of 10)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [What's Hidden in a Randomly Weighted Neural Network?](https://mlsanity.com/paper/1911.13299/) (2019)
- [Antifragile Control Systems: The case of mobile robot trajectory tracking in the presence of uncertainty](https://mlsanity.com/paper/2302.05117/) (2023)
- [Fragility, Robustness and Antifragility in Deep Learning](https://mlsanity.com/paper/2312.09821/) (2023)

## 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.