Stochastic linear quadratic optimal control for model-free discrete-time systems based on Q-learning algorithm.
Tao WangHuaguang ZhangYanhong LuoPublished in: Neurocomputing (2018)
Keyphrases
- optimal control
- linear quadratic
- reinforcement learning
- optimal control problems
- model free
- rl algorithms
- learning algorithm
- closed loop
- dynamic programming
- vector valued
- reinforcement learning algorithms
- control strategy
- impedance control
- policy iteration
- infinite horizon
- dynamical systems
- function approximation
- feedback control
- machine learning
- probabilistic model
- neural network
- real time
- machine learning algorithms
- supervised learning
- temporal difference
- state space
- feature space
- data mining