Metraipolis › archive › dc_9eda7f4eff5d
Graph-Based Inference and Topology-Aware Multi-Agent Reinforcement Learning for Large-Scale Railway Network Management — arXiv:2609.30150
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30150
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T05:26:16.978Z
- SHA-256 of the archived text
0ff34ceee024fb6c50a43200c6e650bbe821a5da5295a25321cd2fbbed93ee24- Stable URL of this page
https://metraipolis.com/documento/dc_9eda7f4eff5d
How to cite
Graph-Based Inference and Topology-Aware Multi-Agent Reinforcement Learning for Large-Scale Railway Network Management — arXiv:2609.30150 — arXiv (en), https://arxiv.org/abs/2609.30150 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9eda7f4eff5d (Metraipolis archive dc_9eda7f4eff5d, sha256 0ff34ceee024fb6c50a43200c6e650bbe821a5da5295a25321cd2fbbed93ee24)
BibTeX
@misc{dc9eda7f4eff5d,
title = {Graph-Based Inference and Topology-Aware Multi-Agent Reinforcement Learning for Large-Scale Railway Network Management — arXiv:2609.30150},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30150},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9eda7f4eff5d; sha256 0ff34ceee024fb6c50a43200c6e650bbe821a5da5295a25321cd2fbbed93ee24},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30150. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern infrastructure asset management constitutes a complex sequential decision-making problem, characterized by long planning horizons and system-level interactions, such as spatial deterioration correlations and economies of scale. While deep reinforcement learning has shown promise in optimizing maintenance policies, scaling to real-world networks remains challenging. Centralized approaches become computationally intractable in large-scale systems, whereas decentralized approaches often fail to capture essential coordination mechanisms. To address these challenges, we propose a graph-based framework that integrates accurate environment modeling with scalable decision support. First, we employ a hierarchical Bayesian model leveraging a Gaussian Process on Graph kernel to infer a realistic, spatially correlated networked environment of railway maintenance planning from real-world data provided by the Swiss Federal Railways. Second, we introduce a topology-aware Multi-Agent Reinforcement Learning (MARL) framework by integrating graph neural networks and graph Transformers to optimize network-level policies. A central contribution of this work is the demonstration of scalability through zero-shot transfer learning: graph-based agents, trained only on small network portions, are successfully deployed in a zero-shot manner on large-scale unseen networks without any retraining. Numerical results indicate that the proposed method significantly outperforms optimized heuristics and standard MARL baselines, reducing computational training time while maintaining superior performance on large-scale networks. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.30150 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T04:50:39.512Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).