We describe our current efforts towards creating a reinforcement learner that learns both from reinforcements provided by its environment and from human-generated advice. Our research involves two complementary components: (a) mapping advice expressed in English to a formal advice language and (b) using advice expressed in a formal notation in a reinforcement learner. We use a subtask of the challenging RoboCup simulated soccer task as our testbed.

PDF, PS, HTML

In The AAAI-2004 Workshop on Supervisory Control of Learning and Adaptive Systems, July 2004.

@InProceedings{AAAI04ws-pillar, title={Guiding a Reinforcement Learner with Natural Language Advice: Initial Results in RoboCup Soccer}, author={Gregory Kuhlmann and Peter Stone and Raymond J. Mooney and Jude W. Shavlik}, booktitle={The AAAI-2004 Workshop on Supervisory Control of Learning and Adaptive Systems}, month={July}, url="http://www.cs.utexas.edu/users/ai-lab/?AAAI04ws-pillar", year={2004} }