让智能体自主学习动态交互关系，提升复杂网络下的协作效率。
Bayesian Ego-graph Inference for Networked Multi-Agent Reinforcement Learning
- 每个智能体基于局部邻域采样子图，用随机掩码决定通信与决策。
- 在167个智能体的交通控制任务中，性能超越主流MARL方法。
- 适合需要自适应协作的分布式系统，如智能交通、无人机群组。
在联网多智能体强化学习（Networked-MARL）中，去中心化智能体需在局部可观测性和固定物理图结构限制下行动。现有方法常假设邻域静态，难以适应动态或异构环境。虽集中式框架可学习动态图，但依赖全局状态和中心化架构，在真实去中心化系统中不切实际。本文提出一种基于随机图的策略，各智能体在其局部物理邻域上采样子图进行决策。在此基础上，引入去中心化的贝叶斯框架BayesG，通过贝叶斯变分推断学习稀疏且上下文感知的交互结构。每个智能体操作于其自身为中心的节点图（ego-graph），并采样潜在通信掩码以指导消息传递与策略计算。变分分布与策略通过证据下界（ELBO）目标端到端联合训练，使智能体同步学习交互拓扑与决策策略。BayesG在包含最多167个智能体的大规模交通控制任务中表现优于强基线，验证了其卓越的可扩展性、效率与性能。
原文摘要 · Abstract (English)
In networked multi-agent reinforcement learning (Networked-MARL), decentralized agents must act under local observability and constrained communication over fixed physical graphs. Existing methods often assume static neighborhoods, limiting adaptability to dynamic or heterogeneous environments. While centralized frameworks can learn dynamic graphs, their reliance on global state access and centralized infrastructure is impractical in real-world decentralized systems. We propose a stochastic graph-based policy for Networked-MARL, where each agent conditions its decision on a sampled subgraph over its local physical neighborhood. Building on this formulation, we introduce BayesG, a decentralized actor-framework that learns sparse, context-aware interaction structures via Bayesian variational inference. Each agent operates over an ego-graph and samples a latent communication mask to guide message passing and policy computation. The variational distribution is trained end-to-end alongside the policy using an evidence lower bound (ELBO) objective, enabling agents to jointly learn both interaction topology and decision-making strategies. BayesG outperforms strong MARL baselines on large-scale traffic control tasks with up to 167 agents, demonstrating superior scalability, efficiency, and performance.
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。