HiGFRL: Hierarchical Graph Fusion-Driven Reinforcement Learning for Dependency-Aware Task Scheduling in Heterogeneous Cloud
This work proposes HiGFRL, a Hierarchical Graph Fusion-Driven Reinforcement Learning framework, which designs a fusion-driven dual-network architecture to optimize RL decision-making and incorporates a topology-prior-guided hybrid reward mechanism that distills static topological priors into the learning process to acc...
Tiangang Li, Shi Ying, Xiangbo Tian
· 0 citations