Can Sophisticated Dispatching Strategy Acquired by Reinforcement Learning? - A Case Study in Dynamic Courier Dispatching System.
Yujie ChenYu QianYichen YaoZili WuRongqi LiYinzhi ZhouHaoyuan HuYinghui XuPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- scheduling problem
- dynamic routing
- manufacturing systems
- production scheduling
- test bed
- case study
- data structure
- learning algorithm
- flexible manufacturing systems
- function approximation
- search strategy
- least squares
- real world
- machine learning
- real time
- active learning
- supervised learning
- monte carlo
- learning process
- expert systems
- multi agent
- optimal strategy
- website
- temporal difference learning
- database