让防御智能体学会通信，协同应对网络攻击威胁。
Learning to Communicate in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence
- 设计可通信的多智能体强化学习框架，提升协作能力。
- 在模拟环境中学习到的策略接近人类专家响应水平。
- 同时优化防御策略与低开销通信消息，兼顾效率与效果。
在部分可观测环境下的合作多智能体强化学习中，传统方法通常允许智能体独立行动，可能限制策略的协同效果。通过共享已知或可疑的正在进行的威胁信息，有效通信可提升网络战场中的决策质量。本文提出一种游戏设计，使防御智能体在网络安全操作研究平台（Cyber Operations Research Gym）中，通过适配后的可微分智能体间学习算法，学习通信与防御即时网络威胁。所学战术策略接近人类专家在事件响应中的表现。此外，智能体在学习防御策略的同时，也学会了成本最低的通信消息。
原文摘要 · Abstract (English)
Popular methods in cooperative Multi-Agent Reinforcement Learning with partially observable environments typically allow agents to act independently during execution, which may limit the coordinated effect of the trained policies. However, by sharing information such as known or suspected ongoing threats, effective communication can lead to improved decision-making in the cyber battle space. We propose a game design where defender agents learn to communicate and defend against imminent cyber threats by playing training games in the Cyber Operations Research Gym, using the Differentiable Inter Agent Learning algorithm adapted to the cyber operational environment. The tactical policies learned by these autonomous agents are akin to those of human experts during incident responses to avert cyber threats. In addition, the agents simultaneously learn minimal cost communication messages while learning their defence tactical policies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。