Automatic,Weight Learning for Multiple Data Sources when Learning from Demonstration

Brenna D. Argall, Brett Browning, Manuela Veloso

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

9 Scopus citations

Abstract

Traditional approaches to programming robots are generally inaccessible to non-robotics-experts. A promising exception is the Learning from Demonstration paradigm. Here a policy mapping world observations to action selection is learned, by generalizing from task demonstrations by a teacher. Most Learning from Demonstration work to date considers data from a single teacher. In this paper, we consider the incorporation of demonstrations from multiple teachers. In particular, we contribute an algorithm that handles multiple data sources, and additionally reasons about reliability differences between them. For example, multiple teachers could be inequally proficient at performing the demonstrated task. We introduce Demonstration Weight Learning (DWL) as a Learning from Demonstration algorithm that explicitly represents multiple data sources and learns to select between them, based on their observed reliability and according to an adaptive expert learning inspired approach. We present a first implementation of DWL within a simulated robot domain. Data sources are shown to differ in reliability, and weighting is found impact task execution success. Furthermore, DWL is shown to produce appropriate data source weights that improve policy performance.

Original languageEnglish (US)
Title of host publication2009 IEEE International Conference on Robotics and Automation, ICRA '09
Pages226-231
Number of pages6
DOIs
StatePublished - Nov 2 2009
Event2009 IEEE International Conference on Robotics and Automation, ICRA '09 - Kobe, Japan
Duration: May 12 2009May 17 2009

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729

Other

Other2009 IEEE International Conference on Robotics and Automation, ICRA '09
CountryJapan
CityKobe
Period5/12/095/17/09

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Automatic,Weight Learning for Multiple Data Sources when Learning from Demonstration'. Together they form a unique fingerprint.

  • Cite this

    Argall, B. D., Browning, B., & Veloso, M. (2009). Automatic,Weight Learning for Multiple Data Sources when Learning from Demonstration. In 2009 IEEE International Conference on Robotics and Automation, ICRA '09 (pp. 226-231). [5152668] (Proceedings - IEEE International Conference on Robotics and Automation). https://doi.org/10.1109/ROBOT.2009.5152668