Search
Close
  • About Us
    • Governance
    • Our Team
    • Labs
    • Open positions
    • Alumni
  • Research
    • Wearable robotics
      • ReGait++
      • Third Arm
    • Rescue Robotics
      • Flying Robots
      • Legged robots
      • Collaboration, Learning and Tests
    • Educational robotics
      • Cellulo
      • Thymio
    • Publications
    • Resources
  • Education
    • How to get into robotics
      • How our professors got into robotics
      • How our researchers got started
    • Robotics for kids
      • Activities for Kids
      • R2t2 Mars Mission
    • Graduate Programs in Robotics
    • Resources
  • Tech Transfer
    • Researchers expertise
    • Spin-Offs
    • Swiss Robotics Day
    • Swiss Robotics Ecosystem
    • Resources
  • Equal Opportunities
    • Robotics for Girls
    • Master students
    • Young Researchers
    • Building Equality
    • Women in Robotics
    • Resources
  • Awards & Programs
    • Spin-Fund
    • PhD/Postdoc exchange program
    • Award for Career Development
    • Award for Women Master Students
    • Swiss Robotics Masters Award
    • Award for Scientific Visibility
    • Women keynote speakers
    • Best Paper Award
  • Outreach
    • Drone Days
    • Cybathlon
    • Swiss Robotics Industry Days
    • Other Outreach Events
  • Contact
Menu
  • About Us
    • Governance
    • Our Team
    • Labs
    • Open positions
    • Alumni
  • Research
    • Wearable robotics
      • ReGait++
      • Third Arm
    • Rescue Robotics
      • Flying Robots
      • Legged robots
      • Collaboration, Learning and Tests
    • Educational robotics
      • Cellulo
      • Thymio
    • Publications
    • Resources
  • Education
    • How to get into robotics
      • How our professors got into robotics
      • How our researchers got started
    • Robotics for kids
      • Activities for Kids
      • R2t2 Mars Mission
    • Graduate Programs in Robotics
    • Resources
  • Tech Transfer
    • Researchers expertise
    • Spin-Offs
    • Swiss Robotics Day
    • Swiss Robotics Ecosystem
    • Resources
  • Equal Opportunities
    • Robotics for Girls
    • Master students
    • Young Researchers
    • Building Equality
    • Women in Robotics
    • Resources
  • Awards & Programs
    • Spin-Fund
    • PhD/Postdoc exchange program
    • Award for Career Development
    • Award for Women Master Students
    • Swiss Robotics Masters Award
    • Award for Scientific Visibility
    • Women keynote speakers
    • Best Paper Award
  • Outreach
    • Drone Days
    • Cybathlon
    • Swiss Robotics Industry Days
    • Other Outreach Events
  • Contact
Search
Close
  • About Us
    • Governance
    • Our team
    • Labs
    • Open positions
    • Alumni
  • Research
    • Wearable Robotics
      • ReGait++
      • Third Arm
    • Rescue Robotics
      • Flying robots
      • Legged robots
      • Collaborations, learning and tests
    • Educational Robotics
      • Cellulo
      • Thymio
    • Publications
    • Resources
  • Education
    • How to get into robotics
      • How our professors got into robotics
      • How our researchers got started
    • Robotics for kids
      • Activities for kids
      • R2t2 Mars mission
    • Graduate programs in robotics
    • Resources
  • Tech Transfer
    • Researchers expertise
    • Spin-Offs
    • Swiss Robotics Day
    • Swiss Robotics Ecosystem
    • Resources
  • Equal Opportunities
    • Robotics for girls
    • Master students
    • Young researchers
    • Building equality
    • Women in Robotics
    • Resources
  • Awards & Programs
    • Spin-Fund
    • PhD/Postdoc Exchange Program
    • Award for Career Development
    • Award for Women Master Students
    • Award for Scientific Visibility
    • Women keynote speakers
    • Best Paper Awards
  • Outreach
    • Drone Days
    • Cybathlon
    • Swiss Robotics Industry Days
    • Other Outreach Events
Menu
  • About Us
    • Governance
    • Our team
    • Labs
    • Open positions
    • Alumni
  • Research
    • Wearable Robotics
      • ReGait++
      • Third Arm
    • Rescue Robotics
      • Flying robots
      • Legged robots
      • Collaborations, learning and tests
    • Educational Robotics
      • Cellulo
      • Thymio
    • Publications
    • Resources
  • Education
    • How to get into robotics
      • How our professors got into robotics
      • How our researchers got started
    • Robotics for kids
      • Activities for kids
      • R2t2 Mars mission
    • Graduate programs in robotics
    • Resources
  • Tech Transfer
    • Researchers expertise
    • Spin-Offs
    • Swiss Robotics Day
    • Swiss Robotics Ecosystem
    • Resources
  • Equal Opportunities
    • Robotics for girls
    • Master students
    • Young researchers
    • Building equality
    • Women in Robotics
    • Resources
  • Awards & Programs
    • Spin-Fund
    • PhD/Postdoc Exchange Program
    • Award for Career Development
    • Award for Women Master Students
    • Award for Scientific Visibility
    • Women keynote speakers
    • Best Paper Awards
  • Outreach
    • Drone Days
    • Cybathlon
    • Swiss Robotics Industry Days
    • Other Outreach Events

Transfer in Inverse Reinforcement Learning for Multiple Strategies

Publication date:

Authors:

  • Presented at: IEEE/RSJ International Conference on Intelligent Robots and Systems, Tokyo, Japan, November 3-8, 2013
  • Accepted in: IEEE/RSJ International Conference on Intelligent Robots and Systems, 2013
  • Publication date: 2013

We consider the problem of incrementally learning different strategies of performing a complex sequential task from multiple demonstrations of an expert or a set of experts. While the task is the same, each expert differs in his/her way of performing it. We assume that this variety across experts’ demonstration is due to the fact that each expert/strategy is driven by a different reward function, where reward function is expressed as a linear combination of a set of known features. Consequently, we can learn all the expert strategies by forming a convex set of optimal deterministic policies, from which one can match any unseen expert strategy drawn from this set. Instead of learning from scratch every optimal policy in this set, the learner transfers knowledge from the set of learned policies to bootstrap its search for new optimal policy. We demonstrate our approach on a simulated mini-golf task where the 7 degrees of freedom Barrett WAM robot arm learns to sequentially putt on different holes in accordance with the playing strategies of the expert.

    Reference

    • Detailed record: https://infoscience.epfl.ch/record/187590?ln=en
    • EPFL-CONF-187590
    • doi:10.1109/IROS.2013.6696817
    Reference
    Read the paper
    • Intranet
    • News
    • Events
    • Contact
    Menu
    • Intranet
    • News
    • Events
    • Contact
    • Journalists and media
    • News bulletin archive
    • Newsletter archive
    Menu
    • Journalists and media
    • News bulletin archive
    • Newsletter archive
    Subscribe to our newsletter
    Twitter
    Linkedin
    Youtube
    Facebook
    Partners

    Leading house

    epfl_white

    Co-Leading house

    eth_white
    unizuerich_white
    idsia_white
    unibe_all_white
    empa-all-white
    unibasel_white

    Copyright © 2021 NCCR Robotics. All rights reserved.