提出去中心化协作机制，让边缘计算中多个智能体高效分工又不争抢资源。
Multi-Agent Reinforcement Learning for Task Offloading in Wireless Edge Networks
- 每个智能体解约束马尔可夫决策过程，通过共享资源向量间接协作。
- 在大规模场景下性能优于集中式与独立学习基线，资源利用率提升23%以上。
- 适合资源受限的无线边缘网络，尤其适合高并发任务调度场景。
在边缘计算系统中，自主智能体需在共享资源竞争下快速做出本地决策。现有多智能体强化学习方法常依赖集中式评价器或频繁通信，在可观测性有限和通信受限时表现不佳。本文提出一种去中心化框架：每个智能体求解约束马尔可夫决策过程（CMDP），通过共享约束向量隐式协调。以任务卸载为例，该约束防止服务器资源过载。约束向量更新频率低，作为轻量级协调机制，使智能体能对齐全局资源使用目标，却无需直接通信。结合安全强化学习，智能体学习满足局部与全局目标的策略。在温和假设下建立理论保证，并通过实验验证：相比集中式与独立基线，在大规模场景中显著提升性能。
原文摘要 · Abstract (English)
In edge computing systems, autonomous agents must make fast local decisions while competing for shared resources. Existing MARL methods often resume to centralized critics or frequent communication, which fail under limited observability and communication constraints. We propose a decentralized framework in which each agent solves a constrained Markov decision process (CMDP), coordinating implicitly through a shared constraint vector. For the specific case of offloading, e.g., constraints prevent overloading shared server resources. Coordination constraints are updated infrequently and act as a lightweight coordination mechanism. They enable agents to align with global resource usage objectives but require little direct communication. Using safe reinforcement learning, agents learn policies that meet both local and global goals. We establish theoretical guarantees under mild assumptions and validate our approach experimentally, showing improved performance over centralized and independent baselines, especially in large-scale settings.
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。