A-MADiff: Attention-Guided Multi-Agent DRL with Diffusion Policies for Memory-Aware Task Orchestration in Mobile AIGC Networks
A cooperative multi-agent orchestration framework, in which each edge node is equipped with a scheduling agent to route tasks to local ASPs or neighboring edge nodes, and an attention-guided centralized critic to estimate per-agent values from cross-agent states under GPU memory heterogeneity is proposed.
Chong-Zhi Wu, Zheng-Tao Li, Jia-Wen Kang et al.
· 0 citations