Deep Reinforcement Learning for Crowdshipping Last-Mile Delivery with Endogenous Uncertainty

The Future of Last - Mile Delivery

Stochastic last-mile delivery problems with time constraints

When a package is shipped, the customer often requires the delivery to be made within a particular time window or by a deadline. However, meeting such time requirements is difficult, and delivery companies may not always know ahead of time which customers will need a delivery. In this thesis, we present models and solution approaches for two stochastic last-mile delivery problems in which custo...

Transshipment Networks for Last-Mile Delivery in Congested Urban Areas1

This paper introduces the concept of transshipment networks, a collection of strategically located transshipment platforms, for efficient and flexible last-mile delivery in congested urban areas. By implementing transshipment platforms, logistics operators can select the locations, light-freight vehicle types and operating schedules that best fit specific distribution strategies, and, simultane...

Minimizing waiting time in last mile delivery for smart city

Customers consider a reliable and on-time last mile delivery in Omni-channel business as important as price and good’s quality. We focus on minimizing the waiting time for customers and carriers in last mile delivery. We model the problem as an optimization problem and develop Genetic Algorithm to solve it.

Naive Reinforcement Learning with Endogenous

This article considers a simple model of reinforcement learning. All behavior change derives from the reinforcing or deterring effect of instantaneous payoff experiences. Payoff experiences are reinforcing or deterring depending on whether the payoff exceeds an aspiration level or falls short of it. Over time, the aspiration level is adjusted toward the actually experienced payoffs. This articl...