Model-Free Optimal Tracking Control via Critic-Only Q-Learning.
Biao LuoDerong LiuTingwen HuangDing WangPublished in: IEEE Trans. Neural Networks Learn. Syst. (2016)
Keyphrases
- model free
- reinforcement learning algorithms
- tracking control
- function approximation
- temporal difference
- reinforcement learning
- average reward
- policy iteration
- nonlinear systems
- temporal difference learning
- optimal control
- dynamic programming
- control law
- machine learning
- reinforcement learning methods
- neural network
- real time
- pattern recognition
- data mining
- stochastic games
- policy evaluation