Dual policy iteration-reinforcement learning to optimize the detection quality of passive remote sensing device.
Rui GuoZhonghao FuPublished in: Signal Process. (2023)
Keyphrases
- remote sensing
- policy iteration
- reinforcement learning
- change detection
- markov decision processes
- model free
- optimal policy
- remote sensing images
- policy evaluation
- multispectral
- temporal difference
- high resolution
- hyperspectral
- remote sensing imagery
- fixed point
- remote sensing data
- image processing
- least squares
- high spatial resolution
- optimal control
- markov decision process
- satellite images
- high quality
- reinforcement learning algorithms
- hyperspectral imagery
- satellite data
- image analysis
- infinite horizon
- average reward
- multi spectral images
- land cover
- finite state
- function approximation
- target detection
- actor critic
- learning algorithm
- false alarms
- state space
- earth observation
- hyperspectral images
- convergence rate
- markov decision problems
- monte carlo
- dynamic programming
- pattern recognition
- automatic image registration
- function approximators
- remote sensed images