Stable value iteration for two-player zero-sum game of discrete-time nonlinear systems based on adaptive dynamic programming.
Ruizhuo SongLiao ZhuPublished in: Neurocomputing (2019)
Keyphrases
- nonlinear systems
- dynamic programming
- adaptive control
- adaptive fuzzy
- adaptive neural
- markov decision processes
- stability analysis
- dead zone
- tracking control
- state space
- fuzzy model
- tracking error
- fuzzy control
- lyapunov function
- fuzzy controller
- fuzzy systems
- control law
- finite state
- optimal policy
- adaptive neural control
- learning rate
- linear programming
- infinite horizon
- reinforcement learning
- feedback control
- control method
- markov chain
- genetic algorithm
- optimal control
- pattern recognition
- autonomous robots
- control algorithm
- decision making