Primal-Dual Value Function Approximation for Stochastic Dynamic Intermodal Transportation with Eco-Labels

Eco-labels are a way to benchmark transportation shipments with respect to their environmental impact. In contrast to an eco-labeling of consumer products, emissions in transportation depend on several operational factors like the mode of transportation (e.g., train or truck) or a vehicle’s current and potential future capacity utilization when new orders are added for consolidation. Thus, satisfying eco-labels and doing this cost efficiently is a challenging task when dynamically routing orders in an intermodal network. In this paper, the authors model the problem as a multiobjective sequential decision process and propose a reinforcement learning method: value function approximation (VFA). VFAs frequently simulate trajectories of the problem and store observed values (violated eco-labels and costs) for states aggregated to a set of features. The observations are used for improved decision making in the next trajectory. For our problem, the authors face two additional challenges when applying a VFA, the multiple objectives and the “delayed” realization of eco-label satisfaction due to future consolidation. For the first, the authors propose different feature sets dependent on the objective function’s focus: costs or eco-labels. For the latter, the authors propose enhancing the suboptimal decision making and observed pessimistic primal values within the VFA trajectories with optimistic dual decision making when all information of a trajectory is known ex post. This enhancement is a general methodological contribution to the literature of approximate dynamic programming and will likely improve learning for other problems as well. The authors show the advantages of both components in a comprehensive study for intermodal transport via trains and trucks in Europe.

• Record URL:
  • https://doi.org/10.1287/trsc.2022.1164
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/1767714
• Supplemental Notes:
  • Abstracts reprinted with permission of INFORMS (Institute for Operations Research and the Management Sciences, http://www.informs.org).
• Authors:
  • Heinold, Arne
  • Meisel, Frank
  • Ulmer, Marlin W
• Publication Date: 2023-11

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: 1452-1472
• Serial:
  • Transportation Science
  • Volume: 57
  • Issue Number: 6
  • Publisher: Institute for Operations Research and the Management Sciences (INFORMS)
  • ISSN: 0041-1655
  • Serial URL: http://transci.journal.informs.org/

Subject/Index Terms

• TRT Terms: Classification; Costs; Dynamic programming; Environmental impacts; Freight trains; Intermodal transportation; Pollutants; Shipments; Stochastic processes; Trucks
• Subject Areas: Environment; Freight Transportation; Motor Carriers; Operations and Traffic Management; Planning and Forecasting; Railroads;

Filing Info

• Accession Number: 01902559
• Record Type: Publication
• Files: TRIS
• Created Date: Dec 18 2023 8:46AM