Inverse reinforcement learning with leveraged Gaussian processes

Kyungjae Lee, Sungjoon Choi, Songhwai Oh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

In this paper, we propose a novel inverse reinforcement learning algorithm with leveraged Gaussian processes that can learn from both positive and negative demonstrations. While most existing inverse reinforcement learning (IRL) methods suffer from the lack of information near low reward regions, the proposed method alleviates this issue by incorporating (negative) demonstrations of what not to do. To mathematically formulate negative demonstrations, we introduce a novel generative model which can generate both positive and negative demonstrations using a parameter, called proficiency. Moreover, since we represent a reward function using a leveraged Gaussian process which can model a nonlinear function, the proposed method can effectively estimate the structure of a nonlinear reward function.

Original languageEnglish
Title of host publicationIROS 2016 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3907-3912
Number of pages6
ISBN (Electronic)9781509037629
DOIs
Publication statusPublished - 2016 Nov 28
Externally publishedYes
Event2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2016 - Daejeon, Korea, Republic of
Duration: 2016 Oct 92016 Oct 14

Publication series

NameIEEE International Conference on Intelligent Robots and Systems
Volume2016-November
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Other

Other2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2016
Country/TerritoryKorea, Republic of
CityDaejeon
Period16/10/916/10/14

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Inverse reinforcement learning with leveraged Gaussian processes'. Together they form a unique fingerprint.

Cite this