![]() |
@article{DBLP:journals/ml/Gosavi04,
author = {Abhijit Gosavi},
title = {A Reinforcement Learning Algorithm Based on Policy Iteration
for Average Reward: Empirical Results with Yield Management
and Convergence Analysis},
journal = {Machine Learning},
volume = {55},
number = {1},
year = {2004},
pages = {5-29},
ee = {http://dx.doi.org/10.1023/B:MACH.0000019802.64038.6c},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
Copyright © 2005-12-08 by Michael Ley (ley@uni-trier.de)