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

Youbang Sun Tao Liu P. R. Kumar Shahin Shahrampour

Published in: CoRR (2024)

Keyphrases

policy gradient
control system
game theoretic
convergence rate
reinforcement learning algorithms
actor critic
neural network
reinforcement learning
nash equilibria
function approximators
approximation methods
imperfect information