@COMMENT This file was generated by bib2html.pl version 0.90
@COMMENT written by Patrick Riley
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{KCAP09-knox,
author="W.~Bradley Knox and Peter Stone",
title="Interactively Shaping Agents via Human Reinforcement: The {TAMER} Framework",
booktitle="The Fifth International Conference on Knowledge Capture",
month="September",
year="2009",
abstract={As computational learning agents move into domains that incur real
costs (e.g., autonomous driving or financial investment), it will be
necessary to learn good policies without numerous high-cost learning
trials. One promising approach to reducing sample complexity of
learning a task is knowledge transfer from humans to agents. Ideally,
methods of transfer should be accessible to anyone with task
knowledge, regardless of that person's expertise in programming and
AI. This paper focuses on allowing a human trainer to interactively
shape an agent's policy via reinforcement signals. Specifically, the
paper introduces ``Training an Agent Manually via Evaluative
Reinforcement,'' or TAMER, a framework that enables such shaping.
Differing from previous approaches to interactive shaping, a TAMER
agent models the human's reinforcement and exploits its model by
choosing actions expected to be most highly reinforced. Results from
two domains demonstrate that lay users can train TAMER agents
without defining an environmental reward function (as in an MDP)
and indicate that human training within the TAMER framework
can reduce sample complexity over autonomous learning algorithms.
},
wwwnote={The TAMER project page with videos of TAMER in action.
K-CAP 2009},
}