Me

W. Bradley Knox

PhD student, Department of Computer Sciences
University of Texas at Austin
bradknox*AT*cs.utexas.edu





My main research interest is in allowing an agent to learn from positive and negative reinforcement by a human trainer. My ICDL 2008 paper below on the TAMER framework describes my first steps toward this goal. More broadly, I'm interested in learning agents, reinforcement learning, and general machine learning.

Awards

2008 NSF Graduate Research Fellowship
2008 David Bruton, Jr. Graduate School Fellowship

Research Competitions

Robocup @Home League (home assistant robotics)
2007: 2nd place -- Austin Villa @Home Website
Robocup Coach League (opponent modeling)
2006: 2nd place
2005: Champion -- Austin Villa 2005 Coach Website

Publications

  • W. Bradley Knox and Peter Stone. TAMER: Training an Agent Manually via Evaluative Reinforcement. In IEEE 7th International Conference on Development and Learning, August 2008.
    ICDL-2008
    Details     BibTeX     Download: [pdf] (1.1MB)  [ps] (12.8MB) 


  • Juhyun Lee, W. Bradley Knox, and Peter Stone. Inter-Classifier Feedback for Human-Robot Interaction in a Domestic Setting. Journal of Physical Agents, 2(2):41–50, July 2008. Special Issue on Human Interaction with Domestic Robots
    Available from journal's web page.
    Details    BibTeX    Download: [pdf] (2.4MB)  [ps] (3.4MB) 


  • W. Bradley Knox, Juhyun Lee, and Peter Stone. Domestic Interaction on a Segway Base. Proceedings of the Robocup-2008 Symposium.
    Robocup 2008 Symposium
    Download: [pdf]  


  • W. Bradley Knox, Juhyun Lee, and Peter Stone. Person Recognition on a Segway Robot: A Video of UT Austin Villa Robocup@Home 2007 Finals Demonstration. 2008 IEEE International Conference on Robotics and Automation.
    ICRA 2008
    Abstract    Project Home Page     Download: [mpeg] (10.5MB)  


  • Gregory Kuhlmann, William B. Knox, and Peter Stone. Know Thine Enemy: A Champion RoboCup Coach Agent. In Proceedings of the Twenty-First National Conference on Artificial Intelligence, pp. 1463–68, July 2006.
    AAAI 2006
    Details     BibTeX     Download: [pdf] (126.0kB)   [ps] (286.1kB)  











  • ROBOTS!!