Policy Optimization Adaptive Dynamic Programming for Optimal Control of Input-Affine Discrete-Time Nonlinear Systems.
Mingduo LinBo ZhaoPublished in: IEEE Trans. Syst. Man Cybern. Syst. (2023)
Keyphrases
- optimal control
- nonlinear systems
- optimal control problems
- control law
- dynamic programming
- dead zone
- adaptive control
- tracking error
- infinite horizon
- lyapunov function
- adaptive fuzzy
- optimal policy
- actor critic
- adaptive neural
- stability analysis
- control problems
- feedback control
- control strategy
- control theory
- nonlinear functions
- reinforcement learning
- stochastic control
- average cost
- linear programming
- fuzzy systems
- policy gradient
- linear quadratic
- lyapunov stability
- state space
- approximate dynamic programming
- hamilton jacobi bellman
- control method
- fuzzy control
- brownian motion
- policy iteration
- markov decision problems
- partially observable markov decision processes
- nonlinear equations
- machine learning
- production planning
- markov decision processes
- control algorithm
- neural network
- closed loop
- fuzzy model
- sliding mode
- fuzzy controller
- learning rate