Parallel Cross Entropy Policy Gradient Adaptive Dynamic Programming for Optimal Tracking Control of Discrete-Time Nonlinear Systems.
Jiahui XuJingcheng WangJun RaoYanjiu ZhongShunyu WuQifang SunPublished in: IEEE Trans. Syst. Man Cybern. Syst. (2024)
Keyphrases
- tracking control
- nonlinear systems
- dynamic programming
- cross entropy
- adaptive control
- optimal control
- adaptive neural
- control law
- policy gradient
- reinforcement learning
- fuzzy model
- fuzzy systems
- tracking error
- fuzzy control
- learning rate
- fuzzy controller
- control method
- state space
- lyapunov function
- maximum likelihood
- markov decision processes
- nonlinear functions
- finite state
- input output
- rough sets
- control system