Altmetric

Gaussian Processes for Data-Efficient Learning in Robotics and Control

File Description SizeFormat 
pami_final.pdfAccepted version1.39 MBAdobe PDFDownload
Title: Gaussian Processes for Data-Efficient Learning in Robotics and Control
Author(s): Deisenroth, MP
Fox, D
Rasmussen, CE
Item Type: Journal Article
Abstract: © 1979-2012 IEEE.Autonomous learning has been a promising direction in control and robotics for more than a decade since data-driven learning allows to reduce the amount of engineering knowledge, which is otherwise required. However, autonomous reinforcement learning (RL) approaches typically require many interactions with the system to learn controllers, which is a practical limitation in real systems, such as robots, where many interactions can be impractical and time consuming. To address this problem, current learning approaches typically require task-specific knowledge in form of expert demonstrations, realistic simulators, pre-shaped policies, or specific knowledge about the underlying dynamics. In this paper, we follow a different approach and speed up learning by extracting more information from data. In particular, we learn a probabilistic, non-parametric Gaussian process transition model of the system. By explicitly incorporating model uncertainty into long-term planning and controller learning our approach reduces the effects of model errors, a key problem in model-based learning. Compared to state-of-the art RL our model-based policy search method achieves an unprecedented speed of learning. We demonstrate its applicability to autonomous learning in real robot and control tasks.
Publication Date: 1-Feb-2014
URI: http://hdl.handle.net/10044/1/12277
DOI: http://dx.doi.org/10.1109/TPAMI.2013.218
ISSN: 0162-8828
Publisher: IEEE
Start Page: 408
End Page: 423
Journal / Book Title: IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume: 37
Issue: 2
Copyright Statement: © 2013 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
Publication Status: Accepted
Appears in Collections:Computing



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

Creative Commons