On the Linear convergence of Natural Policy Gradient Algorithm.

Sajad Khodadadian Prakirt Raj Jhunjhunwala Sushil Mahavir Varma Siva Theja Maguluri

Published in: CoRR (2021)

Keyphrases

cost function
convergence rate
learning algorithm
computational complexity
dynamic programming
path planning
neural network
worst case
gradient method
policy gradient
gradient ascent