• Sorted by Date • Classified by Publication Type •
Shimon Whiteson, Brian Tanner, Matthew E. Taylor, and Peter Stone. Generalized Domains for Empirical Evaluations in Reinforcement Learning. In ICML 2009: Proceedings of the Twenty-Sixth International Conference on Machine Learning: Workshop on Evaluation Methods for Machine Learning, June 2009.
Many empirical results in reinforcement learning are based on a very small set of environments. These results often represent the best algorithm parameters that were found after an ad-hoc tuning or fitting process. We argue that presenting tuned scores from a small set of environments leads to method overfitting, wherein results may not generalize to similar environments. To address this problem, we advocate empirical evaluations using generalized domains: parameterized problem generators that explicitly encode variations in the environment to which the learner should be robust. We argue that evaluating across a set of these generated problems offers a more meaningful evaluation of reinforcement learning algorithms.
@InProceedings{whiteson:icml09,
author = "Shimon Whiteson and Brian Tanner and Matthew E. Taylor and Peter Stone",
title = "Generalized Domains for Empirical Evaluations in Reinforcement Learning",
booktitle = "ICML 2009: Proceedings of the Twenty-Sixth International
Conference on Machine Learning: Workshop on Evaluation Methods for Machine Learning",
month = "June",
year = 2009,
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Mar 07, 2012 15:56:00