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.
copied = false, 2000);
">
@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},
}
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},
}