Efficient data reuse in value function approximation

Hachiya, H; Akiyama T, Sugiyama, M; Peters, J

doi:10.1109/ADPRL.2009.4927519

DetailsSummary

Efficient data reuse in value function approximation

Hachiya, H., Akiyama T, Sugiyama, M., & Peters, J. (2009). Efficient data reuse in value function approximation. Proceedings of the 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (IEEE ADPRL 2009), 8-15.

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C4EB-A Version Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C4EC-8

Genre: Conference Paper

Files

show Files

Locators

show

Creators

show

hide

Creators:
Hachiya, H¹, Author
Akiyama T, Sugiyama, M, Author
Peters, J^{1, 2}, Author

Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795
2Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647

Content

show

hide

Free keywords: -

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. The usefulness of the proposed approach is demonstrated through simulated swing-up inverted-pendulum problem.

Details

show

hide

Language(s):

Dates: Date issued: 2009-05

Publication Status: Issued

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: URI: http://www.ieee-ssci.org/index.php?q=node/3
DOI: 10.1109/ADPRL.2009.4927519
BibTex Citekey: 5771

Degree: -

Event

show

hide

Title: 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning

Place of Event: Nashville, TN, USA

Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show

hide

Title: Proceedings of the 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (IEEE ADPRL 2009)

Source Genre: Journal

Creator(s):

Affiliations:

Publ. Info: Piscataway, NJ, USA : IEEE Service Center

Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 8 - 15 Identifier: -