W. Bradley Knox
Ph.D. Alumni
Brad, an NSF Graduate Research Fellow, researches how to design agents that can be taught interactively by human reward—somewhat like animal training. The TAMER framework is the result of his efforts. After giving a lot of demos of a trainable Tetris agent, he kept getting called "The Tetris Guy." After defending, Brad joined Cynthia Breazeal's group at the MIT Media Lab as a postdoc, working on the personalization side of an educational robots project. In his free time, Brad runs in "barefoot" sandals, eats tasty trailer food, and tries out his robot training techniques on his dog.
Homepage:
http://media.mit.edu/~bradknox/
Publications
     [Expand to show all 18][Minimize]
Reward (Mis)design for autonomous driving 2023
W. Bradley Knox, Alessandro Allievi, Holger Banzhaf, Felix Schmitt, and Peter Stone, Artificial Intelligence, Vol. 316 (2023).
The EMPATHIC Framework for Task Learning from Implicit Human Feedback 2020
Yuchen Cui, Qiping Zhang, Alessandro Allievi, Peter Stone, Scott Niekum, and W. Bradley Knox, In Proceedings of the 4th Conference on Robot Learning (CoRL 2020), Cambridge MA, USA, November 2020.
Framing reinforcement learning from human reward: Reward positivity, temporal discounting, episodicity, and performance 2015
W. Bradley Knox and Peter Stone, Artificial Intelligence, Vol. 225 (2015).
Learning Non-Myopically from Human-Generated Reward 2013
W. Bradley Knox and Peter Stone, In In Proceedings of the International Conference on Intelligent User Interfaces (IUI), March 2013.
Training a Robot via Human Feedback: A Case Study 2013
W. Bradley Knox, Peter Stone, and Cynthia Breazeal, In Social Robotics, October 2013.
How Humans Teach Agents: A New Experimental Perspective 2012
W. Bradley Knox, Brian D. Glass, Bradley C. Love, W. Todd Maddox, and Peter Stone, International Journal of Social Robotics, Vol. 4 (2012), pp. 409-421. Springer Netherlands.
Learning from feedback on actions past and intended 2012
W. Bradley Knox, Cynthia Breazeal, and Peter Stone, In In Proceedings of 7th ACM/IEEE International Conference on Human-Robot Interaction, Late-Breaking Reports Session (HRI 2012), March 2012.
Learning from Human-Generated Reward 2012
W. Bradley Knox, No other information
Reinforcement Learning from Human Reward: Discounting in Episodic Tasks 2012
W. Bradley Knox and Peter Stone, In In Proceedings of the 21st IEEE International Symposium on Robot and Human Interactive Communication (Ro-Man), September 2012.
Reinforcement Learning with Human and MDP Reward 2012
W. Bradley Knox and Peter Stone, In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2012), June 2012.
The Nature of Belief-Directed Exploratory Choice in Human Decision-Making 2012
W. Bradley Knox , A. Ross Otto , Peter Stone , and Bradley Love, Frontiers in Psychology, Vol. 2 (2012). The paper can be accessed at: http://www.frontiersin.org/Journal/Abstract.aspx?s=196&name=cognitive_science&ART_DOI=10.3389/fpsyg.2011.00398.
Understanding Human Teaching Modalities in Reinforcement Learning Environments: A Preliminary Report 2011
W. Bradley Knox and Peter Stone, In IJCAI 2011 Workshop on Agents Learning Interactively from Human Teachers (ALIHT), July 2011.
Combining Manual Feedback with Subsequent MDP Reward Signals for Reinforcement Learning 2010
W. Bradley Knox and Peter Stone, In Proc. of 9th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2010), May 2010.
Design Principles for Creating Human-Shapable Agents 2009
W. Bradley Knox, Ian Fasel, and Peter Stone, In AAAI Spring 2009 Symposium on Agents that Learn from Human Teachers, March 2009.
Diagnosis and Reconfiguration using Bayesian Networks: An Electrical Power System Case Study 2009
W. Bradley Knox and Ole Mengshoel, In IJCAI 2009 Workshop on Self-* and Autonomous Systems 2009.
Interactively Shaping Agents via Human Reinforcement: The TAMER Framework 2009
W. Bradley Knox and Peter Stone, In The Fifth International Conference on Knowledge Capture, September 2009.
Inter-Classifier Feedback for Human-Robot Interaction in a Domestic Setting 2008
Juhyun Lee, W. Bradley Knox, and Peter Stone, Journal of Physical Agents, Vol. 2, 2 (2008), pp. 41-50. Special Issue on Human Interaction with Domestic Robots.
Know Thine Enemy: A Champion RoboCup Coach Agent 2006
Gregory Kuhlmann, William B. Knox, and Peter Stone, In Proceedings of the Twenty-First National Conference on Artificial Intelligence, pp. 1463-68, July 2006.
Projects
Teaching an Agent Manually via Evaluative Reinforcement (TAMER) 2008 - Present
Areas of Interest
Reinforcement Learning Social Agents Transfer Learning
Demos
Teaching an Agent Manually via Evaluative Reinforcement (TAMER)W. Bradley Knox and Peter Stone2009
Labs
Formerly affiliated with Learning Agents