A reinforcement learning method for multi-AGV scheduling in manufacturing.
Tianfang XuePeng ZengHaibin YuPublished in: ICIT (2018)
Keyphrases
- reinforcement learning
- synthetic data
- high precision
- computational cost
- objective function
- high accuracy
- detection method
- significant improvement
- dynamic programming
- experimental evaluation
- neural network
- preprocessing
- classification accuracy
- support vector machine
- clustering method
- computational complexity
- data sets
- image segmentation
- resource allocation
- classification method