Metro Train Timetable Rescheduling Based on Q-learning Approach.
Boyi SuZhikai WangShuai SuTao TangPublished in: ITSC (2020)
Keyphrases
- reinforcement learning
- cooperative
- state space
- learning algorithm
- function approximation
- optimal policy
- multi agent
- learning rate
- shop floor
- timetabling problem
- reinforcement learning algorithms
- action selection
- neural network
- stochastic approximation
- dynamic programming
- feasible solution
- multiagent learning
- multi agent reinforcement learning
- project scheduling
- bucket brigade
- examination timetabling