Graph-Based Inference and Topology-Aware Multi-Agent Reinforcement Learning for Large-Scale Railway Network Management
A graph-based framework that integrates accurate environment modeling with scalable decision support is proposed that significantly outperforms optimized heuristics and standard MARL baselines, reducing computational training time while maintaining superior performance on large-scale networks.
G. Arcieri, Gregory Duthé, Christopher P. Muller et al.
· 0 citations