Multiple Actor-Critic Structures for Continuous-Time Optimal Control Using Input-Output Data.
Ruizhuo SongFrank L. LewisQinglai WeiHuaguang ZhangZhong-Ping JiangDaniel S. LevinePublished in: IEEE Trans. Neural Networks Learn. Syst. (2015)
Keyphrases
- optimal control
- actor critic
- control problems
- dynamic programming
- feedback control
- control strategy
- optimal control problems
- reinforcement learning
- policy gradient
- control law
- infinite horizon
- lyapunov function
- function approximation
- dynamic environments
- policy iteration
- cost function
- objective function
- neural network