• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Ian Fasel, Michael Quinlan, and Peter Stone. A General Purpose Task Specification Language for Bootstrap Learning. Technical Report AI-08-1, The University of Texas at Austin, Department ofComputer Sciences, AI Laboratory, 2008.
[PDF]160.4kB [postscript]1.9MB
Reinforcement learning (RL) is an effective framework for online learning by autonomous agents. Most RL research focuses on domain-independent learning algorithms, requiring an expert human to define the environment (state and action representation) and task to be performed (e.g. start state and reward function) on a case-by-case basis. In this paper, we describe a general language for a teacher to specify sequential decision making tasks to RL agents. The teacher may communicate properties such as start states, reward functions, termination conditions, successful execution traces, task decompositions, and other advice. The learner may then practice and learn the task on its own using any RL algorithm. We demonstrate our language in a simple GridWorld example and on the RoboCup soccer keepaway benchmark problem. The language forms the basis of a larger ``Bootstrap Learning'' model for machine learning, a paradigm for incremental development of complete systems through integration of multiple machine learning techniques.
@TechReport{faseltr08,
author = "Ian Fasel and Michael Quinlan and Peter Stone",
title = "A General Purpose Task Specification Language for Bootstrap Learning",
institution = "The University of Texas at Austin, Department of
Computer Sciences, AI Laboratory",
number = "AI-08-1",
year = 2008,
abstract = {
Reinforcement learning (RL) is an effective
framework for online learning by autonomous
agents. Most RL research focuses on
domain-independent learning \emph{algorithms},
requiring an expert human to define the
\emph{environment} (state and action representation)
and \emph{task} to be performed (e.g.\ start state
and reward function) on a case-by-case basis. In
this paper, we describe a general language for a
teacher to specify sequential decision making tasks
to RL agents. The teacher may communicate
properties such as start states, reward functions,
termination conditions, successful execution traces,
task decompositions, and other advice. The learner
may then practice and learn the task on its own
using any RL algorithm. We demonstrate our language
in a simple GridWorld example and on the RoboCup
soccer keepaway benchmark problem. The language
forms the basis of a larger ``Bootstrap Learning''
model for machine learning, a paradigm for
incremental development of complete systems through
integration of multiple machine learning techniques.
},
}
Generated by bib2html.pl (written by Patrick Riley ) on Fri Feb 06, 2009 01:41:46