An Opponent-Aware Reinforcement Learning Method for Team-to-Team Multi-Vehicle Pursuit via Maximizing Mutual Information Indicator.
Qinwen WangXinhang LiZheng YuanYiying YangChen XuLin ZhangPublished in: CoRR (2022)
Keyphrases
- mutual information
- reinforcement learning
- similarity measure
- detection method
- significant improvement
- computational cost
- machine learning
- information theoretic
- preprocessing
- dynamic programming
- high accuracy
- robot soccer
- multiagent systems
- clustering method
- edge detection
- image registration
- classification accuracy
- image analysis
- computational complexity
- video sequences
- learning algorithm