Multi-agent simulation-Adaptive dynamic programming based reinforcement learning for evaluating joint delivery systems in relation to the different locations of urban consolidation centres

This research applied Multi-agent Simulation-Adaptive Dynamic Programming based Reinforcement Learning (MAS-ADP based RL) to evaluate Joint Delivery Systems (JDS) in relation to different locations of Urban Consolidation Centres in Yokohama, Japan. The MAS-ADP based RL is capable of replicating the potential actions of modeled agents in an uncertain environment accurately. The application of MAS-ADP based RL in this research shows that the location of UCC influences the behavior of freight carriers and the UCC operator in the JDS. Therefore, it is essential to conduct a feasibility study of UCC location to support JDS using MAS-ADP based RL to get better evaluation outcomes.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01741642
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Apr 22 2020 4:09PM