Gradient method using pseudospectral collocation scheme for two-stage optimal control with an unspecified switching time.
Liang YangJin YangXiaoming LiuWanchun ChenHao ZhouPublished in: Int. J. Control (2021)
Keyphrases
- optimal control
- gradient method
- actor critic
- control problems
- dynamic programming
- reinforcement learning
- convergence rate
- control strategy
- optimal control problems
- policy gradient
- feedback control
- negative matrix factorization
- step size
- infinite horizon
- co occurrence
- real time
- optimization methods
- face recognition
- neural network