@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@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 generate
		   policies 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>.},
)