Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Bayesian Models of Nonstationary Markov Decision Problems

Nicholas K. Jong and Peter Stone. Bayesian Models of Nonstationary Markov Decision Problems. In IJCAI 2005 workshop on Planning and Learning in A Priori Unknown or Dynamic Domains, August 2005.
Workshop webpage.

Download

[PDF]42.4kB  

Abstract

Standard reinforcement learning algorithms gener- ate polices that optimize expected future rewards in a priori unknown domains, but they assume that the domain does not change over time. Prior work cast the reinforcement learning problem as a Bayesian estimation problem, using experience data to condition a probability distribution over domains. In this paper we propose an elaboration of the typical Bayesian model that accounts for the possibility that some aspect of the domain changes spontaneously during learning. We develop a reinforcement learning algorithm based on this model that we expect to react more intelligently to sudden changes in the behavior of the environment.

BibTeX Entry

@inproceedings(IJCAI05ws,
        author="Nicholas K.\ Jong and Peter Stone",
        title="Bayesian Models of Nonstationary Markov Decision Problems",
        booktitle="{IJCAI} 2005 workshop on Planning and Learning in A Priori Unknown or Dynamic Domains",
        month="August",year="2005",
        abstract={
                   Standard reinforcement learning algorithms gener-
                   ate polices that optimize expected future rewards
                   in a priori unknown domains, but they assume that
                   the domain does not change over time. Prior work
                   cast the reinforcement learning problem as a
                   Bayesian estimation problem, using experience data
                   to condition a probability distribution over
                   domains. In this paper we propose an elaboration of
                   the typical Bayesian model that accounts for the
                   possibility that some aspect of the domain
                   changes spontaneously during learning. We develop
                   a reinforcement learning algorithm based on this
                   model that we expect to react more intelligently to
                   sudden changes in the behavior of the environment.
                 },
        wwwnote={<a href="http://www-rcf.usc.edu/~skoenig/workshop.html">Workshop webpage</a>.},
)

Generated by bib2html.pl (written by Patrick Riley ) on Thu Dec 11, 2014 23:22:58