High-speed, model-free adaptive control using parallel synchronous detection.
Dimitrios N. LoizosPaul-Peter SotiriadisGert CauwenberghsPublished in: SBCCI (2007)
Keyphrases
- adaptive control
- model free
- reinforcement learning
- high speed
- reinforcement learning algorithms
- feedback control
- nonlinear systems
- control method
- function approximation
- control law
- policy iteration
- temporal difference
- dynamic environments
- adaptive controller
- state space
- variable structure
- chaotic systems
- markov decision processes
- neural network
- policy evaluation
- autonomous control
- active learning
- transfer learning