Learning-Rate Adjusting Q-Learning for Two-Person Two-Action Symmetric Games.

Koichi Moriyama

Published in: KES-AMSTA (2009)

Keyphrases

learning rate
convergence rate
extensive form games
learning algorithm
error function
adaptive learning rate
hidden layer
convergence speed
rapid convergence
game theory
nash equilibria
weight vector
action selection
activation function
nash equilibrium
step size
multilayer neural networks