Knowledge transfer using local features
Conference Paper, Proceedings of IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL '07), pp. 26 - 31, April, 2007
Abstract
We present a method for reducing the effort required to compute policies for tasks based on solutions to previously solved tasks. The key idea is to use a learned intermediate policy based on local features to create an initial policy for the new task. In order to further improve this initial policy, we developed a form of generalized policy iteration. We achieve a substantial reduction in computation needed to find policies when previous experience is available.
BibTeX
@conference{Stolle-2007-17051,author = {Martin Stolle and Chris Atkeson},
title = {Knowledge transfer using local features},
booktitle = {Proceedings of IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL '07)},
year = {2007},
month = {April},
pages = {26 - 31},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.