Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation.
Anas BarakatPascal BianchiJulien LehmannPublished in: AISTATS (2022)
Keyphrases
- function approximation
- actor critic
- reinforcement learning
- learning algorithm
- model free
- cost function
- dynamic programming
- temporal difference
- function approximators
- policy gradient
- reinforcement learning algorithms
- policy iteration
- gradient method
- temporal difference learning
- optimal solution
- radial basis function
- convergence rate
- neuro fuzzy
- search space
- average reward
- natural actor critic