A leader-following paradigm based deep reinforcement learning method for multi-agent cooperation games.
Feiye ZhangQingyu YangDou AnPublished in: Neural Networks (2022)
Keyphrases
- significant improvement
- reinforcement learning
- detection method
- dynamic programming
- cost function
- objective function
- pairwise
- machine learning
- edge detection
- computational cost
- experimental evaluation
- preprocessing
- neural network
- multi agent
- multiscale
- image sequences
- feature set
- clustering method
- segmentation method
- high precision