Combination of an actor/critic algorithm with goal-directed reasoning.

Hideaki Itoh Kazuyuki Aihara

Published in: Artif. Life Robotics (2001)

Keyphrases

goal directed
learning algorithm
search space
cost function
np hard
dynamic programming
optimal solution
convergence rate
neural network
simulated annealing
machine learning
evolutionary algorithm
least squares
linear programming
mathematical model
convergence proof