Gradient Method for Solving Multisystem Integrated Optimal Control Problem With Undetermined Terminal Time.
Yang LiWanchun ChenHao ZhouLiang YangPublished in: IEEE Syst. J. (2021)
Keyphrases
- optimal control
- gradient method
- actor critic
- control problems
- dynamic programming
- hamilton jacobi bellman
- control strategy
- convergence rate
- policy gradient
- reinforcement learning
- infinite horizon
- optimal control problems
- step size
- optimization methods
- negative matrix factorization
- optimization method
- evolutionary algorithm
- real time