DeepFreight: A Model-free Deep-reinforcement-learning-based Algorithm for Multi-transfer Freight Delivery

Authors

  • Jiayu Chen Purdue University
  • Abhishek K. Umrawal Purdue University
  • Tian Lan The George Washington University
  • Vaneet Aggarwal Purdue University

Keywords:

Multi-agent Planning And Learning, Applications That Involve A Combination Of Learning With Planning Or Scheduling, Reinforcement Learning Using Planning (model-based, Bayesian, Deep, Etc.), Planning Applied To Automating Machine Learning Systems

Abstract

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 shows that the proposed system is highly scalable and ensures a 100% delivery success while maintaining low delivery-time and fuel consumption.

Downloads

Published

2021-05-17

How to Cite

Chen, J., Umrawal, A. K., Lan, T., & Aggarwal, V. (2021). DeepFreight: A Model-free Deep-reinforcement-learning-based Algorithm for Multi-transfer Freight Delivery. Proceedings of the International Conference on Automated Planning and Scheduling, 31(1), 510-518. Retrieved from https://ojs.aaai.org/index.php/ICAPS/article/view/15998