Finding and transferring policies using stored behaviors


We present several algorithms that aim to advance the state-of-the-art in reinforcement learning and planning algorithms. One key idea is to transfer knowledge across problems by representing it using local features. This idea is used to speed up a dynamic programming based generalized policy iteration. We then present a control approach that uses a library… (More)
DOI: 10.1007/s10514-010-9191-2


Cite this paper

@article{Stolle2010FindingAT, title={Finding and transferring policies using stored behaviors}, author={Martin Stolle and Christopher G. Atkeson}, journal={Auton. Robots}, year={2010}, volume={29}, pages={169-200} }