Policy Iteration for Multiplicative Noise Output Feedback Control.
Benjamin GravellMatilde GargianiJohn LygerosTyler H. SummersPublished in: CoRR (2022)
Keyphrases
- feedback control
- policy iteration
- optimal control
- multiplicative noise
- markov decision processes
- infinite horizon
- additive noise
- closed loop
- reinforcement learning
- fixed point
- adaptive control
- dynamic programming
- image denoising
- optimal policy
- synthetic aperture radar
- model free
- noise reduction
- sar images
- noisy images
- least squares
- markov decision process
- spatial domain
- temporal difference
- control strategy
- denoising
- speckle noise
- total variation
- finite state
- denoising algorithm
- ultrasound images
- learning algorithm
- control law
- real time
- imaging systems
- convergence rate
- image reconstruction
- markov chain
- hidden markov models
- objective function