Global Convergence of Policy Gradient Algorithms for Indefinite Least Squares Stationary Optimal Control.
Jingjing BuMehran MesbahiPublished in: IEEE Control. Syst. Lett. (2020)
Keyphrases
- optimal control
- global convergence
- least squares
- policy gradient
- policy iteration
- actor critic
- convergence rate
- control problems
- infinite horizon
- optimization methods
- optimization problems
- dynamic programming
- reinforcement learning
- learning algorithm
- convergence speed
- real time
- cost function
- artificial neural networks