Global Convergence of Policy Gradient Algorithms for Indefinite Least Squares Stationary Optimal Control.

Jingjing Bu Mehran Mesbahi

Published in: CoRR (2020)

Keyphrases

optimal control
global convergence
least squares
policy gradient
convergence rate
optimization methods
reinforcement learning
policy iteration
dynamic programming
control strategy
learning algorithm
convergence speed
neural network
optimization problems