Reinforcement learning approach for optimal control of multiple electric locomotives in a heavy-haul freight train: A Double-Switch-Q-network architecture.
Huiyue TangYuan WangXiang LiuXiaoyun FengPublished in: Knowl. Based Syst. (2020)
Keyphrases
- optimal control
- network architecture
- reinforcement learning
- control problems
- dynamic programming
- artificial neural
- infinite horizon
- feedback control
- risk sensitive
- neural network
- class of nonlinear systems
- control strategy
- brownian motion
- network design
- optimal control problems
- control law
- neural network model
- learning algorithm
- model free
- rl algorithms
- adaptive control
- linear programming