DeepFreight: Integrating Deep Reinforcement Learning and Mixed Integer Programming for Multi-transfer Truck Freight Delivery
This addresses efficient fleet control for freight delivery companies facing rising demands and costs, though it appears incremental as it combines existing methods like QMIX and MILP.
The paper tackles the problem of multi-transfer freight delivery by proposing DeepFreight, which integrates deep reinforcement learning and mixed integer programming to optimize truck dispatch and package matching. The system achieves 100% delivery success while maintaining low delivery time and fuel consumption.
With the freight delivery demands and shipping costs increasing rapidly, intelligent control of fleets to enable efficient and cost-conscious solutions becomes an important problem. In this paper, we propose DeepFreight, a model-free deep-reinforcement-learning-based algorithm for multi-transfer freight delivery, which includes two closely-collaborative components: truck-dispatch and package-matching. Specifically, a deep multi-agent reinforcement learning framework called QMIX is leveraged to learn a dispatch policy, with which we can obtain the multi-step joint vehicle dispatch decisions for the fleet with respect to the delivery requests. Then an efficient multi-transfer matching algorithm is executed to assign the delivery requests to the trucks. Also, DeepFreight is integrated with a Mixed-Integer Linear Programming optimizer for further optimization. The evaluation results show that the proposed system is highly scalable and ensures a 100\% delivery success while maintaining low delivery-time and fuel consumption. The codes are available at https://github.com/LucasCJYSDL/DeepFreight.