The Dynamic Travelling Salesman Problem with Time-Dependent and Stochastic Travel Times: A Deep Reinforcement Learning Approach

37 Pages Posted: 27 Apr 2024

See all articles by Dawei Chen

Dawei Chen

affiliation not provided to SSRN

Christina Imdahl

Eindhoven University of Technology

David Lai

University of Southampton

T. van Woensel

Eindhoven University of Technology (TUE)

Abstract

We introduce a novel approach using deep reinforcement learning to tackle the Dynamic Traveling Salesman Problem with time-dependent and stochastic travel times (DTSP-TDS). The main goal is to dynamically plan the route with the shortest tour duration that visits all customers while considering the uncertainties and time-dependence of travel times. We employ a reinforcement learning approach to dynamically address the stochastic travel times to observe changing states and make decisions accordingly. Our reinforcement learning approach incorporates a Dynamic Graph Temporal Attention model with multi-head attention to dynamically extract information about stochastic travel times. Numerical studies with varying amounts of customers and time intervals are conducted to test its performance. Our proposed method outperforms other benchmarks regarding solution quality and solving time, including the Rolling horizon-based heuristics and other existing reinforcement learning approaches. In addition, we demonstrate our approach's robustness and generalization capabilities in solving the DTSP-TDS by comparing the performance of the algorithms for various problem configurations.

Keywords: Dynamic traveling salesman problem, Time-dependent and stochastic travel times, Deep reinforcement learning

Suggested Citation

Chen, Dawei and Imdahl, Christina and Lai, David and van Woensel, T., The Dynamic Travelling Salesman Problem with Time-Dependent and Stochastic Travel Times: A Deep Reinforcement Learning Approach. Available at SSRN: https://ssrn.com/abstract=4809480 or http://dx.doi.org/10.2139/ssrn.4809480

Dawei Chen (Contact Author)

affiliation not provided to SSRN ( email )

No Address Available

Christina Imdahl

Eindhoven University of Technology ( email )

PO Box 513
Eindhoven, 5600 MB
Netherlands

David Lai

University of Southampton ( email )

Southampton Business School
Southampton
United Kingdom

T. Van Woensel

Eindhoven University of Technology (TUE) ( email )

PO Box 513
Eindhoven, 5600 MB
Netherlands

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
28
Abstract Views
110
PlumX Metrics