@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
@article{AIJ15-Hester,
AUTHOR={Todd Hester and Peter Stone},
TITLE={Intrinsically motivated model learning for developing curious robots},
JOURNAL={Artificial Intelligence},
YEAR={2017},
month={June},
pages={170--86},
volume=247,
URL={http://www.sciencedirect.com/science/article/pii/S0004370215000764},
DOI={10.1016/j.artint.2015.05.002},
ISSN={},
ABSTRACT={
Reinforcement Learning (RL) agents are typically deployed to
learn a specific, concrete task based on a pre-defined
reward function. However, in some cases an agent may be able
to gain experience in the domain prior to being given a
task. In such cases, intrinsic motivation can be used to
enable the agent to learn a useful model of the environment
that is likely to help it learn its eventual tasks more
efficiently. This paradigm fits robots particularly well, as
they need to learn about their own dynamics and affordances
which can be applied to many different tasks. This article
presents the texplore with
Variance-And-Novelty-Intrinsic-Rewards algorithm
(texplore-vanir), an intrinsically motivated model-based RL
algorithm. The algorithm learns models of the transition
dynamics of a domain using random forests. It calculates two
different intrinsic motivations from this model: one to
explore where the model is uncertain, and one to acquire
novel experiences that the model has not yet been trained
on. This article presents experiments demonstrating that the
combination of these two intrinsic rewards enables the
algorithm to learn an accurate model of a domain with no
external rewards and that the learned model can be used
afterward to perform tasks in the domain. While learning the
model, the agent explores the domain in a developing and
curious way, progressively learning more complex skills. In
addition, the experiments show that combining the agent's
intrinsic rewards with external task rewards enables the
agent to learn faster than using external rewards alone. We
also present results demonstrating the applicability of this
approach to learning on robots.
},
wwwnote={from journal website.}
}