Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation.
Semih CayciNiao HeR. SrikantPublished in: SIAM J. Optim. (2024)
Keyphrases
- function approximation
- policy gradient
- function approximators
- reinforcement learning
- actor critic
- reinforcement learning algorithms
- model free
- policy search
- learning tasks
- radial basis function
- convergence rate
- temporal difference
- approximation methods
- temporal difference learning
- neural network
- convergence speed
- transfer learning
- least squares
- support vector
- machine learning