• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Real Time Targeted Exploration in Large Domains.
Todd Hester and Peter Stone.
In The Ninth International Conference on Development and Learning
(ICDL), August 2010.
ICDL 2010
[PDF]253.9kB [postscript]554.1kB
A developing agent needs to explore to learn about the world and learn good behaviors. In many real world tasks, this exploration can take far too long, and the agent must make decisions about which states to explore, and which states not to explore. Bayesian methods attempt to address this problem, but take too much computation time to run in reasonably sized domains. In this paper, we present TEXPLORE, the first algorithm to perform targeted exploration in real time in large domains. The algorithm learns multiple possible models of the domain that generalize action effects across states. We experiment with possible ways of adding intrinsic motivation to the agent to drive exploration. TEXPLORE is fully implemented and tested in a novel domain called Fuel World that is designed to reflect the type of targeted exploration needed in the real world. We show that our algorithm significantly outperforms representative examples of both model-free and model-based RL algorithms from the literature and is able to quickly learn to perform well in a large world in real-time.
@InProceedings{ICDL10-hester,
author="Todd Hester and Peter Stone",
title="Real Time Targeted Exploration in Large Domains",
booktitle = "The Ninth International Conference on Development and Learning (ICDL)",
location = "Ann Arbor, Michigan",
month = "August",
year = "2010",
abstract = "A developing agent needs to explore to learn about
the world and learn good behaviors. In many real world tasks,
this exploration can take far too long, and the agent must make
decisions about which states to explore, and which states not
to explore. Bayesian methods attempt to address this problem,
but take too much computation time to run in reasonably sized
domains. In this paper, we present TEXPLORE, the first algorithm
to perform targeted exploration in real time in large domains.
The algorithm learns multiple possible models of the domain
that generalize action effects across states. We experiment with
possible ways of adding intrinsic motivation to the agent to drive
exploration. TEXPLORE is fully implemented and tested in a novel
domain called Fuel World that is designed to reflect the type of
targeted exploration needed in the real world. We show that
our algorithm significantly outperforms representative examples
of both model-free and model-based RL algorithms from the
literature and is able to quickly learn to perform well in a large
world in real-time.",
wwwnote={<a href="http://www.eecs.umich.edu/icdl-2010/">ICDL 2010</a>},
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Apr 17, 2024 18:42:55