@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{ECML09-jong,
    author="Nicholas K. Jong and Peter Stone",
    title="Compositional Models for Reinforcement Learning",
    booktitle="The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases",
    month="September",year="2009",
    abstract={Innovations such as optimistic exploration, function
                 approximation, and hierarchical decomposition have
                 helped scale reinforcement learning to more complex
                 environments, but these three ideas have rarely been
                 studied together.  This paper develops a unified
                 framework that formalizes these algorithmic
                 contributions as operators on learned models of the
                 environment.  Our formalism reveals some synergies
                 among these innovations, and it suggests a
                 straightforward way to compose them.  The resulting
                 algorithm, Fitted R-MAXQ, is the first to combine
                 the function approximation of fitted algorithms, the
                 efficient model-based exploration of R-MAX, and the
                 hierarchical decompostion of MAXQ.},
}