Guiding a Reinforcement Learner with Natural Language Advice: Initial Results in RoboCup Soccer

Gregory Kuhlmann, Peter Stone, Raymond Mooney, and Jude Shavlik
In The AAAI-2004 Workshop on Supervisory Control of Learning and Adaptive Systems, July 2004.

Abstract: 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.

@InCollection(AAAI04ws-pillar,
  author="Gregory Kuhlmann and Peter Stone and Raymond Mooney and Jude Shavlik",
  title="Guiding a Reinforcement Learner with Natural Language Advice:	Initial Results in {R}obo{C}up Soccer",
  booktitle="The {AAAI}-2004 Workshop on Supervisory Control of Learning and Adaptive Systems",
  month="July",
  year="2004"
)