Model-Free Optimal Tracking Design With Evolving Control Strategies via Q-Learning.
Ding WangHaiming HuangMingming ZhaoPublished in: IEEE Trans. Circuits Syst. II Express Briefs (2024)
Keyphrases
- model free
- control strategies
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- real time
- reinforcement learning methods
- control system
- traffic management
- state space
- mathematical model
- control strategy
- policy iteration
- average reward
- genetic algorithm
- supervised learning
- temporal difference
- multi agent