Reinforcement Learning for Solving the Vehicle Routing Problem
Fuzhou University Reinforcement Learning for Solving the Vehicle Routing Problem 32nd Conference on Neural Information Processing Systems 2018 2023-11-10
1.摘要
1. 使 VRP VRP Google OR
2.引言
2. VRP VRP ; 线 使 VRP 使 RL
2.引言
2. Bello Pointer Network VRP VRP 0 RNN embedding RNN RNN embedding
3.模型概述
3.  
3.模型概述
3. RNN RNN embedding RNN VRP
3.模型概述
3. a t decoding t RNN decoder
3.模型概述
3.    
3.模型概述
3. AC i actor next ii critic reward
4.实验
4. [0,1]*[0,1] {1,…,9} 0 decoder embedding decoder i greedy ii Beam Search BS
4.实验
4.
5.结论
5. VRP VRP 使
谢谢!
Fuzhou University