Feudal Graph Reinforcement Learning

no code implementations • 11 Apr 2023 • Tommaso Marzi, Arshjot Khehra, Andrea Cini, Cesare Alippi

In this work, we propose a novel methodology, named Feudal Graph Reinforcement Learning (FGRL), that addresses such challenges by relying on hierarchical RL and a pyramidal message-passing architecture.

Decision Making reinforcement-learning +2