SIA OpenIR  > 机器人学研究室
Nonlinear inverse reinforcement learning with mutual information and guassian process
Li DC(李德才); He YQ(何玉庆); Gu F(谷丰)
Department机器人学研究室
Conference Name2014 International Conference on Robotics and Biomimetics (ROBIO 2014)
Conference DateDecember 5-10, 2014
Conference PlaceBali, Indonesia
Source Publication2014 International Conference on Robotics and Biomimetics (ROBIO 2014)
PublisherIEEE
Publication PlacePiscataway, NJ, USA
2014
Pages1445-1450
Indexed ByEI ; CPCI(ISTP)
EI Accession number20152100876978
WOS IDWOS:000380399500240
Contribution Rank1
ISBN978-1-4799-7396-5
AbstractIn this paper, a mutual information (MI) and Extreme Learning Machine (ELM) based inverse reinforcement learning (IRL) algorithm, which termed as MEIRL, is proposed to construct nonlinear reward function. The basic idea of MIIRL is that, similar to GPIRL, the reward function is learned by using Gaussian process and the importance of each feature is obtained by using automatic relevance determination (ARD). Then mutual information is employed to evaluate the impact of each feature to the reward function, based on which extreme learning machine is introduced along with an adaptive model construction procedure to choose the optimal subset of features and the performance of the original GPIRL algorithm is enhanced as well. Furthermore, to demonstrate the effectiveness of MEIRL, a simulation called highway driving is constructed. The simulation results show that MEIRL is comparable with the state of art IRL algorithms in terms of generalization capability, but more efficient while the number of features is large.
Language英语
Citation statistics
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/15412
Collection机器人学研究室
Corresponding AuthorLi DC(李德才)
AffiliationShenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
Recommended Citation
GB/T 7714
Li DC,He YQ,Gu F. Nonlinear inverse reinforcement learning with mutual information and guassian process[C]. Piscataway, NJ, USA:IEEE,2014:1445-1450.
Files in This Item: Download All
File Name/Size DocType Version Access License
Nonlinear inverse re(1569KB)会议论文 开放获取ODC PDDLView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li DC(李德才)]'s Articles
[He YQ(何玉庆)]'s Articles
[Gu F(谷丰)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li DC(李德才)]'s Articles
[He YQ(何玉庆)]'s Articles
[Gu F(谷丰)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li DC(李德才)]'s Articles
[He YQ(何玉庆)]'s Articles
[Gu F(谷丰)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Nonlinear inverse reinforcement learning with mutual information and guassian process.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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