Improvement of the Relaxation Procedure in Concurrent Q-Learning.

Kazunori Murakami Tomoko Ozeki

Published in: ICONIP (2) (2013)

Keyphrases

cooperative
reinforcement learning
hierarchical reinforcement learning
multi agent
learning algorithm
function approximation
multi agent reinforcement learning
dynamic programming
real time
image segmentation
artificial neural networks
mobile robot
stochastic approximation
concurrent execution