Value Iteration Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear Systems.
Qinglai WeiDerong LiuHanquan LinPublished in: IEEE Trans. Cybern. (2016)
Keyphrases
- optimal control
- dynamic programming
- nonlinear systems
- control law
- adaptive control
- optimal control problems
- adaptive fuzzy
- lyapunov function
- feedback control
- adaptive neural
- infinite horizon
- tracking error
- stability analysis
- linear quadratic
- control problems
- dead zone
- state space
- markov decision processes
- control theory
- hamilton jacobi bellman
- optimal policy
- policy iteration
- approximate dynamic programming
- fuzzy model
- brownian motion
- reinforcement learning
- learning rate
- linear programming
- lyapunov stability
- fuzzy controller
- control strategy
- actor critic
- sliding mode
- stochastic control
- nonlinear equations
- nonlinear functions
- partially observable markov decision processes
- evolutionary algorithm
- machine learning