On the Convergence Rates of Policy Gradient Methods.
Lin XiaoPublished in: J. Mach. Learn. Res. (2022)
Keyphrases
- convergence rate
- policy gradient methods
- natural actor critic
- gradient method
- policy gradient
- step size
- actor critic
- convergence speed
- learning rate
- robot arm
- function approximation
- simulated annealing
- optimal control
- reinforcement learning algorithms
- neural network
- objective function
- reinforcement learning
- machine learning