Adjustable Iterative Q-Learning Schemes for Model-Free Optimal Tracking Control.
Junfei QiaoMingming ZhaoDing WangMingming HaPublished in: IEEE Trans. Syst. Man Cybern. Syst. (2024)
Keyphrases
- model free
- tracking control
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- policy iteration
- nonlinear systems
- average reward
- temporal difference
- policy evaluation
- control law
- rl algorithms
- learning tasks
- dynamic programming
- neural network
- optimal control
- linear combination
- fuzzy sets
- fuzzy logic
- adaptive neural
- machine learning