Transient Reward Approximation for Grids, Crowds, and Viruses

Ernst Moritz Hahn Holger Hermanns Ralf Wimmer Bernd Becker

Published in: CoRR (2012)

Keyphrases

reinforcement learning
steady state
error bounds
queueing networks
closed form
neural network
long run
learning algorithm
bayesian networks
approximation algorithms
continuous functions
approximation methods
error tolerance