Open access
Jul 2026
Hierarchical Mean-Field Theory-based Off-Policy GRPO for Federated Edge Learning in Resource-Constrained Edge Computing
A novel algorithm named Group Relative Policy Optimization Based on Hierarchical Mean-Field Theory (OGRPO-HMF) is proposed, which can jointly optimize the local training of nodes and the global model aggregation of servers to comprehensively enhance the efficiency and performance of FEL.
Bing Ai, Yu Sun, Jun Wang et al.
· Cognitive Computation · 0 citations