Token-based deep reinforcement learning for Heterogeneous VRP with Service Time Constraints.
Yujun WangXiaopeng HongYabin WangJunzhou ZhaoGuanghui SunBaoxing QinPublished in: Knowl. Based Syst. (2024)
Keyphrases
- reinforcement learning
- loosely coupled
- constraint satisfaction
- optimal control
- dynamic programming
- state space
- function approximation
- vehicle routing problem with time windows
- web services
- reinforcement learning algorithms
- constrained optimization
- multi agent
- service oriented
- constraint programming
- global constraints
- optimal policy
- management system
- multi domain