2021/04/30 by Hadi Jahanshahi, Aysun Bozanta, Mücahit Çevik +7 · 60 citations
Business, Management and Accounting · Computer Science · Engineering · Mathematics · #Artificial intelligence #Business #Computer science #Engineering #Marketing #Markov decision process #Markov process #Mathematics #Operations research #Optimization and Search Problems #Order (exchange) #Process (computing) #Reinforcement learning #Service (business) #Set (abstract data type) #Statistics #Supply Chain and Inventory Management #Transportation and Mobility Innovations #Variety (cybernetics) #cs.AI #cs.LG #math.OC
paper · pdf · doi:10.1016/j.knosys.2022.108489
published in Knowledge-Based Systems 243, 108489 (Elsevier BV) · Keywords: meal delivery, courier assignment, reinforcement learning, DQN, DDQN
arxiv created 2022/02/23 · openalex publication_date 2022/02/25 · arxiv updated 2022/03/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
We consider a meal delivery service fulfilling dynamic customer requests given a set of couriers over the course of a day. A courier's duty is to pick-up an order from a restaurant and deliver it to a customer. We model this service as a Markov decision process and use deep reinforcement learning as the solution approach. We experiment with the resulting policies on synthetic and real-world datasets and compare those with the baseline policies. We also examine the courier utilization for different numbers of couriers. In our analysis, we specifically focus on the impact of the limited available resources in the meal delivery problem. Furthermore, we investigate the effect of intelligent order rejection and re-positioning of the couriers. Our numerical experiments show that, by incorporating the geographical locations of the restaurants, customers, and the depot, our model significantly improves the overall service quality as characterized by the expected total reward and the delivery times. Our results present valuable insights on both the courier assignment process and the optimal number of couriers for different order frequencies on a given day. The proposed model also shows a robust performance under a variety of scenarios for real-world implementation.