CASIA OpenIR  > 精密感知与控制研究中心  > 人工智能与机器学习
Finite Sample Analysis of LSTD with Random Projections and Eligibility Traces
Li HF(李海芳)1; Yingce Xia2; Wensheng Zhang1
2018-04
Conference Namethe Twenty-Seventh International Joint Conference on Artificial Intelligence
Conference DateJuly 13-19 2018
Conference PlaceStockholm, Sweden
PublisherProceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18)
Abstract

Policy evaluation with linear function approximation is an important problem in reinforcement learning. When facing high-dimensional feature spaces, such a problem becomes extremely hard considering the computation efficiency and quality of approximations. We propose a new algorithm, LSTD(λ)-RP, which leverages random projection techniques and takes eligibility traces into consideration to tackle the above two challenges. We carry out theoretical analysis of LSTD(λ)-RP, and provide meaningful upper bounds of the estimation error, approximation error and total generalization error. These results demonstrate that LSTD(λ)-RP can benefit from random projection and eligibility traces strategies, and LSTD(λ)-RP can achieve better performances than prior LSTDRP and LSTD(λ) algorithms.

Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/26084
Collection精密感知与控制研究中心_人工智能与机器学习
Corresponding AuthorLi HF(李海芳)
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.University of Science and Technology of China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Li HF,Yingce Xia,Wensheng Zhang. Finite Sample Analysis of LSTD with Random Projections and Eligibility Traces[C]:Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18),2018.
Files in This Item: Download All
File Name/Size DocType Version Access License
LSTD.pdf(173KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li HF(李海芳)]'s Articles
[Yingce Xia]'s Articles
[Wensheng Zhang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li HF(李海芳)]'s Articles
[Yingce Xia]'s Articles
[Wensheng Zhang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li HF(李海芳)]'s Articles
[Yingce Xia]'s Articles
[Wensheng Zhang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: LSTD.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.