Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| 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 |