General value iteration based reinforcement learning for solving optimal tracking control problem of continuous-time affine nonlinear systems.
Geyang XiaoHuaguang ZhangYanhong LuoQiuxia QuPublished in: Neurocomputing (2017)
Keyphrases
- tracking control
- nonlinear systems
- optimal control
- control law
- reinforcement learning
- adaptive control
- dynamic programming
- state space
- adaptive neural
- controller design
- markov decision processes
- fuzzy systems
- learning rate
- fuzzy model
- fuzzy controller
- fuzzy control
- nonlinear functions
- adaptive fuzzy
- lyapunov function
- optimal policy
- machine learning
- tracking error
- markov decision process
- inverted pendulum
- learning algorithm
- average reward
- neural network
- control algorithm
- control strategy
- genetic programming
- policy iteration
- closed loop
- takagi sugeno
- genetic algorithm