Actor-Critic or Critic-Actor? A Tale of Two Time Scales.
Shalabh BhatnagarVivek S. BorkarSoumyajit GuinPublished in: IEEE Control. Syst. Lett. (2023)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- optimal control
- approximate dynamic programming
- temporal difference
- neuro fuzzy
- gradient method
- reinforcement learning algorithms
- policy iteration
- function approximation
- natural actor critic
- markov decision processes
- step size
- model free
- evaluation function
- control strategy
- average reward
- linear programming
- least squares
- state space
- dynamic programming
- multi agent systems