@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{AAAI06-shimon,
	author="Shimon Whiteson and Peter Stone",
	title="Sample-Efficient Evolutionary Function Approximation for Reinforcement Learning",
        booktitle="Proceedings of the Twenty-First National Conference on Artificial Intelligence",
        month="July",year="2006",
	pages="518--23",
	abstract={
                  Reinforcement learning problems are commonly tackled
                  with temporal difference methods, which attempt to
                  estimate the agent's optimal value function.  In
                  most real-world problems, learning this value
                  function requires a function approximator, which
                  maps state-action pairs to values via a concise,
                  parameterized function.  In practice, the success of
                  function approximators depends on the ability of the
                  human designer to select an appropriate
                  representation for the value function.  A recently
                  developed approach called evolutionary function
                  approximation uses evolutionary computation to
                  automate the search for effective representations.
                  While this approach can substantially improve the
                  performance of TD methods, it requires many sample
                  episodes to do so.  We present an enhancement to
                  evolutionary function approximation that makes it
                  much more sample-efficient by exploiting the
                  off-policy nature of certain TD methods.  Empirical
                  results in a server job scheduling domain
                  demonstrate that the enhanced method can learn
                  better policies than evolution or TD methods alone
                  and can do so in many fewer episodes than standard
                  evolutionary function approximation.
	},
        wwwnote={<a href="http://www.aaai.org/Conferences/AAAI/aaai06.php">AAAI 2006</a>},
}