Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Behavior Transfer for Value-Function-Based Reinforcement Learning

Matthew E. Taylor and Peter Stone. Behavior Transfer for Value-Function-Based Reinforcement Learning. In The Fourth International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 53–59, ACM Press, New York, NY, July 2005.
AAMAS-2005

Download

[PDF]230.4kB  [postscript]620.1kB  

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 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.

BibTeX Entry

@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>},
}       

Generated by bib2html.pl (written by Patrick Riley ) on Wed Jul 09, 2014 11:54:43