discrete-event simulation

A deep reinforcement learning approach for the asynchronous dynamic vehicle dispatching problem

How can we assign vehicles to requests in real time, the instant a call arrives or a vehicle becomes free? We model this asynchronous dispatching problem as a semi-Markov decision process and solve it by combining discrete-event simulation with deep reinforcement learning, validated on real New York City taxi data.

A deep reinforcement learning approach for the asynchronous dynamic vehicle dispatching problem

This paper addresses the asynchronous dynamic vehicle dispatching problem (DVDP), in which vehicle assignments must be made in real time as requests arise or vehicles become available. Unlike traditional synchronous dispatching, the asynchronous DVDP …