de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Journal Article

Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons83950

Hachiya,  H
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons84135

Peters,  J
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society;

Locator
There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Hachiya, H., Akiyama T, Sugiyama, M., & Peters, J. (2009). Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning. Neural Networks, 22(10), 1399-1410. doi:10.1016/j.neunet.2009.01.002.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-C1B6-7
Abstract
Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a policy that is different from the currently optimized policy. A common approach is to use importance sampling techniques for compensating for the bias of value function estimators caused by the difference between the data-sampling policy and the target policy. However, existing off-policy methods often do not take the variance of the value function estimators explicitly into account and therefore their performance tends to be unstable. To cope with this problem, we propose using an adaptive importance sampling technique which allows us to actively control the trade-off between bias and variance. We further provide a method for optimally determining the trade-off parameter based on a variant of cross-validation. We demonstrate the usefulness of the proposed approach through simulations.