This chapter presents a multi‐agent simulation model that replicates the behavior of stakeholders, including shippers, freight carriers, administrators, customers and Urban Consolidation Centre (UCC) operators, who are involved in city logistics using reinforcement learning. It applies these multi‐agent models to realistic road networks in Osaka and Motomachi, Japan, for evaluating the effects of implementing a combination of city logistics policy measures, including joint delivery systems, green route policy and parking management. The results indicate that a combination of policy measures can achieve a well‐balanced performance of policy measures in terms of profits and costs for freight carriers and shippers as well as the reduction of negative environmental impacts. Social cost‐benefit analyses can monetarize the environmental and social costs, which will be useful to assess the net benefits of city logistics policy measures. Further research is needed to validate the results of multi‐agent simulation with real data from the implementation of city logistics measures.
Multi‐agent Simulation with Reinforcement Learning for Evaluating a Combination of City Logistics Policy Measures
City Logistics 2 ; 165-177
2018-05-30
13 pages
Article/Chapter (Book)
Electronic Resource
English
Multi-agent Reinforcement Learning-Based UAS Control for Logistics Environments
Springer Verlag | 2022
|Multi-agent system with Policy Gradient Reinforcement Learning for RoboCup Soccer Simulator
BASE | 2014
|DECENTRALIZED POLICY GRADIENT DESCENT AND ASCENT FOR SAFE MULTI-AGENT REINFORCEMENT LEARNING
European Patent Office | 2023
|