Solving the train dispatching problem via deep reinforcement learning

Every day, railways experience disturbances and disruptions, both on the network and the fleet side, that affect the stability of rail traffic. Induced delays propagate through the network, which leads to a mismatch in demand and offer for goods and passengers, and, in turn, to a loss in service quality. In these cases, it is the duty of human traffic controllers, the so-called dispatchers, to do their best to minimize the impact on traffic. However, dispatchers inevitably have a limited depth of perception of the knock-on effect of their decisions, particularly how they affect areas of the network that are outside their direct control. In recent years, much work in Decision Science has been devoted to developing methods to solve the problem automatically and support the dispatchers in this challenging task. This paper investigates Machine Learning-based methods for tackling this problem, proposing two different Deep Q-Learning methods(Decentralized and Centralized). Numerical results show the superiority of these techniques respect to the classical linear Q-Learning based on matrices. Moreover the Centralized approach is compared with a MILP formulation showing interesting results. The experiments are inspired on data provided by a U.S. class 1 railroad.

• Record URL:
  • https://doi.org/10.1016/j.jrtpm.2023.100394
• Record URL:
  • http://www.sciencedirect.com/science/article/pii/S2210970623000264
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/22109706
• Supplemental Notes:
  • © 2023 Elsevier Ltd. All rights reserved. Abstract reprinted with permission of Elsevier.
• Authors:
  • Agasucci, Valerio
  • Grani, Giorgio
  • 0000-0001-6049-0062
  • Lamorgese, Leonardo
• Publication Date: 2023-6

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: 100394
• Serial:
  • Journal of Rail Transport Planning & Management
  • Volume: 26
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 2210-9706
  • Serial URL: http://www.sciencedirect.com/science/journal/22109706

Subject/Index Terms

• TRT Terms: Dispatching; Machine learning; Mixed integer programming; Railroad transportation
• Subject Areas: Operations and Traffic Management; Planning and Forecasting; Railroads;

Filing Info

• Accession Number: 01889601
• Record Type: Publication
• Files: TRIS
• Created Date: Aug 3 2023 11:39AM