@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(AAAI07-taylor,
        author="Matthew E.\ Taylor and Shimon Whiteson and  Peter Stone",
        title="Temporal Difference and Policy Search Methods for
         Reinforcement Learning: An Empirical Comparison",
        note = "Nectar Track",
	pages="1675--1678",
        booktitle="Proceedings of the Twenty-Second 
         Conference on Artificial Intelligence",
        month="July",year="2007", 
        abstract="Reinforcement learning (RL) methods have become
         popular in recent years because of their ability to solve
         complex tasks with minimal feedback. Both genetic algorithms
         (GAs) and temporal difference (TD) methods have proven
         effective at solving difficult RL problems, but few rigorous
         comparisons have been conducted. Thus, no general guidelines
         describing the methods' relative strengths and weaknesses are
         available. This paper summarizes a detailed empirical
         comparison between a GA and a TD method in Keepaway, a
         standard RL benchmark domain based on robot soccer. The
         results from this study help isolate the factors critical to
         the performance of each learning method and yield insights
         into their general strengths and weaknesses.",
        wwwnote={<a href="http://www.aaai.org/Conferences/National/2007/aaai07.html">AAAI
         2007</a>}, 
)