neural networks research group
areas
people
projects
demos
publications
software/data
Training a Robot via Human Feedback: A Case Study (2013)
W. Bradley Knox
and
Peter Stone
and Cynthia Breazeal
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.
View:
PDF
,
HTML
Citation:
In
Social Robotics
, October 2013.
Bibtex:
@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} }
People
W. Bradley Knox
bradknox [at] mit edu
Peter Stone
pstone [at] cs utexas edu
Areas of Interest
Planning
Social Agents
Reinforcement Learning