**摘要**
With sophisticated cyber-attacks becoming increasingly prevalent, modern networks require intelligent autonomous cyber-defense agents trained via Reinforcement Learning (RL). These agents employ neurosymbolic approaches such as behavior trees with learning-enabled components (LECs) to learn, reason, adapt, and implement security rules while maintaining critical operations. However, these autonomou
👤 作者: Ankita Samaddar, Sandeep Neema, Daniel Balasubramanian, Xenofon Koutsoukos

---
🔗 **[Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents](https://arxiv.org/abs/2606.18223v1)**

> Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-06-17 14:00