Policy iteration for optimal control of weakly coupled nonlinear systems with completely unknown dynamics.
Chao LiDing WangDerong LiuHaibo HePublished in: ACC (2016)
Keyphrases
- optimal control
- policy iteration
- hamilton jacobi bellman
- nonlinear systems
- control law
- tracking error
- infinite horizon
- control problems
- lyapunov function
- control strategy
- dynamic programming
- reinforcement learning
- approximate dynamic programming
- adaptive control
- feedback control
- fuzzy controller
- average cost
- fuzzy systems
- brownian motion
- markov decision processes
- dynamical systems
- average reward
- actor critic
- model free
- stochastic control
- learning rate
- fuzzy model
- dynamic model
- fuzzy control
- function approximation
- neural network
- data mining