Adaptive Optimal Control via Q-Learning for Itô Fuzzy Stochastic Nonlinear Continuous-Time Systems With Stackelberg Game.
Zhongyang MingHuaguang ZhangYing YanLiu YangPublished in: IEEE Trans. Fuzzy Syst. (2024)
Keyphrases
- optimal control
- optimal control problems
- class of nonlinear systems
- reinforcement learning
- linear quadratic
- dynamic programming
- feedback control
- lyapunov function
- brownian motion
- control problems
- control strategy
- infinite horizon
- actor critic
- learning algorithm
- cooperative
- function approximation
- optimal policy
- decision making
- lyapunov stability
- continuous stirred tank reactor
- mathematical model
- state space
- stochastic control
- stackelberg game
- real time