Peter Stone's Selected Publications

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


Value Function Transfer for General Game Playing

Bikramjit Banerjee, Gregory Kuhlmann, and Peter Stone. Value Function Transfer for General Game Playing. In ICML workshop on Structural Knowledge Transfer for Machine Learning, June 2006.
ICML 2006 workshop on Structural Knowledge Transfer for Machine Learning

Download

[PDF]172.9kB  [postscript]464.0kB  

Abstract

We present value function transfer techniques for General Game Playing (GGP) by Reinforcement Learning. We focus on 2 player, alternate-move, complete information board games and use the GGP simulator and framework. Our approach is two-pronged: first we extract knowledge about crucial regions in the value-function space of any game in the genre. Then for each target game, we generate a smaller version of this game and extract symmetry information from the board setup. The combined knowledge of value function and symmetry allows us to achieve significant transfer via Reinforcement Learning, to larger board games using only a limited size of state-space by virtue of exploiting symmetry.

BibTeX Entry

@inproceedings(ICML06-bikram,
   author="Bikramjit Banerjee and Gregory Kuhlmann and Peter Stone",
   title="Value Function Transfer for General Game Playing",
  Booktitle="{ICML} workshop on Structural Knowledge Transfer for Machine Learning",
  month="June",year="2006",
        abstract={
	          We present value function transfer techniques for
	          General Game Playing (GGP) by Reinforcement
	          Learning. We focus on 2 player, alternate-move,
	          complete information board games and use the GGP
	          simulator and framework. Our approach is
	          two-pronged: first we extract knowledge about
	          crucial regions in the value-function space of any
	          game in the genre. Then for each target game, we
	          generate a smaller version of this game and extract
	          symmetry information from the board setup. The
	          combined knowledge of value function and symmetry
	          allows us to achieve significant transfer via
	          Reinforcement Learning, to larger board games using
	          only a limited size of state-space by virtue of
	          exploiting symmetry.
        },
        wwwnote={<a href="http://www.cs.utexas.edu/~banerjee/icmlws06/">ICML 2006 workshop on Structural Knowledge Transfer for Machine Learning</a>},
)

Generated by bib2html.pl (written by Patrick Riley ) on Fri Nov 21, 2014 15:59:49