Login / Signup

Linear Convergence of Independent Natural Policy Gradient in Games With Entropy Regularization.

Youbang SunTao LiuP. R. KumarShahin Shahrampour
Published in: IEEE Control. Syst. Lett. (2024)
Keyphrases
  • policy gradient
  • neural network
  • reinforcement learning
  • actor critic
  • nash equilibria
  • convergence rate
  • function approximators
  • sufficient conditions