@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{AAMAS05-transfer,
        author="Matthew E.\ Taylor and Peter Stone",
        title="Behavior Transfer for Value-Function-Based Reinforcement Learning",
        booktitle="The Fourth International Joint Conference on Autonomous Agents and  Multiagent Systems",
       month="July",year="2005",
       editor="Frank Dignum and Virginia Dignum and Sven Koenig and Sarit Kraus and Munindar P.~Singh and Michael Wooldridge",
      publisher="{ACM Press}",
      address="New York, NY",
      pages="53--59",
       abstract={
                 Temporal difference (TD) learning
                 methods have become popular
                 reinforcement learning techniques in recent years. TD
                 methods have had some experimental successes and have
                 been shown to exhibit some desirable properties in
                 theory, but have often been found very slow in
                 practice.  A key feature of TD methods is that they
                 represent policies in terms of value functions. In
                 this paper we introduce \emph{behavior transfer}, a
                 novel approach to speeding up TD learning by
                 transferring the learned value function from one task
                 to a second related task. We present experimental
                 results showing that autonomous learners are able to
                 learn one multiagent task and then use behavior
                 transfer to markedly reduce the total training time
                 for a more complex task.
       },
       wwwnote={<a href="http://www.aamas2005.nl/">AAMAS-2005</a>},
}