• Sorted by Date • Classified by Publication Type •
Matthijs Snel and Shimon Whiteson. Multi-Task Reinforcement Learning: Shaping and Feature Selection. In EWRL 2011: Proceedings of the Ninth European Workshop on Reinforcement Learning, September 2011.
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced source tasks to speed up learning on a new target task. Earlier work has not clearly motivated choices for the shaping function. This paper discusses and empirically compares several alternatives, and demonstrates that the most intuitive one may not always be the best option. In addition, we extend previous work on identifying good representations for the value and shaping functions, and show that selecting the right representation results in improved generalization over tasks.
@InProceedings{snel:ewrl11,
author = "Matthijs Snel and Shimon Whiteson",
title = "Multi-Task Reinforcement Learning: Shaping and Feature Selection",
booktitle = "EWRL 2011: Proceedings of the Ninth European Workshop on Reinforcement Learning",
month = "September",
year = 2011,
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Mar 07, 2012 15:56:00