An Actor-Critic Algorithm With Second-Order Actor and Critic.

Jing Wang Ioannis Ch. Paschalidis

Published in: IEEE Trans. Autom. Control. (2017)

Keyphrases

actor critic
learning algorithm
policy gradient
objective function
computational complexity
search space
mathematical model
optimal solution
np hard
optimization algorithm
monte carlo
neural network
cost function
linear programming
policy iteration
gradient method