Global Convergence of the ODE Limit for Online Actor-Critic Algorithms in Reinforcement Learning.

Ziheng Wang Justin A. Sirignano

Published in: CoRR (2021)

Keyphrases

global convergence
reinforcement learning
convergence analysis
actor critic
learning algorithm
optimization methods
policy iteration
convergence rate
approximate dynamic programming
function approximation
global optimum
model free
multi agent
optimization problems