On Finite-Time Convergence of Actor-Critic Algorithm.

Shuang Qiu Zhuoran Yang Jieping Ye Zhaoran Wang

Published in: IEEE J. Sel. Areas Inf. Theory (2021)

Keyphrases

convergence proof
learning algorithm
np hard
convergence rate
optimal solution
computational complexity
k means
optimization algorithm
objective function
search space
dynamic programming
least squares
simulated annealing
mathematical model
recursive least squares