Knowledge Transfer Using Local Features

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… (More)

9 Figures and Tables

Cite this paper

@article{Stolle2007KnowledgeTU, title={Knowledge Transfer Using Local Features}, author={M. Stolle and C. G. Atkeson}, journal={2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning}, year={2007}, pages={26-31} }