Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Abdeen, Zain ul, Jin, Ming
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2506.23036
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912942884126720
author Abdeen, Zain ul
Jin, Ming
author_facet Abdeen, Zain ul
Jin, Ming
contents This paper explores reinforcement learning (RL) policy robustness by systematically analyzing network parameters under internal and external stresses. \textcolor{black}{We apply synaptic filtering methods using high-pass, low-pass, and pulse-wave filters from} \citep{pravin2024fragility}, 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 \textit{fragile}, \textit{robust}, or \textit{antifragile}, 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23036
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Parameter Stress Analysis in Reinforcement Learning: Applying Synaptic Filtering to Policy Networks
Abdeen, Zain ul
Jin, Ming
Machine Learning
Systems and Control
This paper explores reinforcement learning (RL) policy robustness by systematically analyzing network parameters under internal and external stresses. \textcolor{black}{We apply synaptic filtering methods using high-pass, low-pass, and pulse-wave filters from} \citep{pravin2024fragility}, 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 \textit{fragile}, \textit{robust}, or \textit{antifragile}, 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.
title Parameter Stress Analysis in Reinforcement Learning: Applying Synaptic Filtering to Policy Networks
topic Machine Learning
Systems and Control
url https://arxiv.org/abs/2506.23036