APER-DDQN: UAV Precise Airdrop Method Based on Deep Reinforcement Learning.
Yan OuyangXinqing WangRuizhe HuHonghui XuPublished in: IEEE Access (2022)
Keyphrases
- reinforcement learning
- highly accurate
- multiresolution
- detection method
- experimental evaluation
- high precision
- pairwise
- synthetic data
- classification accuracy
- computational complexity
- preprocessing
- similarity measure
- mathematical model
- image sequences
- high accuracy
- computational cost
- path planning
- function approximation
- support vector machine svm
- unsupervised learning
- supervised learning
- probabilistic model
- neural network
- dynamic programming
- cost function
- objective function
- machine learning