We present a case study of applying a framework for learning from numeric human feedback---TAMER---to a physically embodied robot. In doing so, we also provide the first demonstration of the ability to train multiple behaviors by such feedback without algorithmic modifications and of a robot learning from free-form human-generated feedback without any further guidance or evaluative feedback. We describe transparency challenges specific to a physically embodied robot learning from human feedback and adjustments that address these challenges.

PDF, HTML

In Social Robotics, October 2013.

@inproceedings{ICSR13-knox, title={Training a Robot via Human Feedback: A Case Study}, author={W. Bradley Knox and Peter Stone and Cynthia Breazeal}, booktitle={Social Robotics}, month={October}, url="http://nn.cs.utexas.edu/?knox:icsr13", year={2013} }