Latent space policy search for robotics

Kevin Sebastian Luck, Gerhard Neumann, Erik Berger, Jan Peters, Heni Ben Amor

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

12 Scopus citations

Abstract

Learning motor skills for robots is a hard task. In particular, a high number of degrees-of-freedom in the robot can pose serious challenges to existing reinforcement learning methods, since it leads to a high-dimensional search space. However, complex robots are often intrinsically redundant systems and, therefore, can be controlled using a latent manifold of much smaller dimensionality. In this paper, we present a novel policy search method that performs efficient reinforcement learning by uncovering the low-dimensional latent space of actuator redundancies. In contrast to previous attempts at combining reinforcement learning and dimensionality reduction, our approach does not perform dimensionality reduction as a preprocessing step but naturally combines it with policy search. Our evaluations show that the new approach outperforms existing algorithms for learning motor skills with high-dimensional robots.

Original languageEnglish (US)
Title of host publicationIROS 2014 Conference Digest - IEEE/RSJ International Conference on Intelligent Robots and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1434-1440
Number of pages7
ISBN (Electronic)9781479969340
DOIs
StatePublished - Oct 31 2014
Event2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2014 - Chicago, United States
Duration: Sep 14 2014Sep 18 2014

Publication series

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

Other

Other2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2014
CountryUnited States
CityChicago
Period9/14/149/18/14

ASJC Scopus subject areas

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

Fingerprint Dive into the research topics of 'Latent space policy search for robotics'. Together they form a unique fingerprint.

  • Cite this

    Luck, K. S., Neumann, G., Berger, E., Peters, J., & Amor, H. B. (2014). Latent space policy search for robotics. In IROS 2014 Conference Digest - IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 1434-1440). [6942745] (IEEE International Conference on Intelligent Robots and Systems). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IROS.2014.6942745