Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation.
Anas BarakatPascal BianchiJulien LehmannPublished in: CoRR (2021)
Keyphrases
- function approximation
- actor critic
- reinforcement learning
- learning algorithm
- dynamic programming
- model free
- function approximators
- monte carlo
- natural actor critic
- temporal difference
- cost function
- neural network
- linear programming
- finite state
- state space
- artificial neural networks
- temporal difference learning
- policy gradient
- optimal solution
- genetic algorithm