Integrated Reinforcement Learning and Optimization for Railway Timetable Rescheduling

Reference

H. Zhang, X. Liu, D. Sun, A. Dabiri, and B. De Schutter, "Integrated reinforcement learning and optimization for railway timetable rescheduling," Proceedings of the 17th IFAC Symposium on Control in Transportation Systems (CTS 2024), Ayia Napa, Cyprus, pp. 310-315, July 2024.

Abstract

The railway timetable rescheduling problem is regarded as an efficient way to handle disturbances. Typically, it is tackled using a mixed integer linear programming (MILP) formulation. In this paper, an algorithm that combines both reinforcement learning and optimization is proposed to solve the railway timetable rescheduling problem. Specifically, a value-based reinforcement learning algorithm is implemented to determine the independent integer variables of the MILP problem. Then, the values of all the integer variables can be derived from these independent integer variables. With the solution for the integer variables, the MILP problem can be transformed into a linear programming problem, which can be solved efficiently. The simulation results show that the proposed method can reduce passenger delays compared with the baseline, while also reducing the solution time.

Publisher page

• Access full text  

Downloads

• PDF of corresponding technical report (928 KB)

BibTeX

@inproceedings{ZhaLu:24-009,
   author    = {Zhang, Hengkai and Liu, Xiaoyu and Sun, Dingshan and Dabiri,
                Azita and De Schutter, Bart},
   title     = {Integrated Reinforcement Learning and Optimization for Railway
                Timetable Rescheduling},
   booktitle = {Proceedings of the 17th IFAC Symposium on Control in
                Transportation Systems (CTS 2024)},
   address   = {Ayia Napa, Cyprus},
   pages     = {310--315},
   month     = jul,
   year      = {2024}
   }

• Download BibTeX entry