UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Value Function Transfer for General Game Playing (2006)
Bikramjit Banerjee
,
Gregory Kuhlmann
, and
Peter Stone
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.
View:
PDF
,
PS
,
HTML
Citation:
In
ICML workshop on Structural Knowledge Transfer for Machine Learning
, June 2006.
Bibtex:
@inproceedings{ICML06-bikram, title={Value Function Transfer for General Game Playing}, author={Bikramjit Banerjee and Gregory Kuhlmann and Peter Stone}, booktitle={ICML workshop on Structural Knowledge Transfer for Machine Learning}, month={June}, url="http://www.cs.utexas.edu/users/ai-lab?ICML06-bikram", year={2006} }
People
Bikramjit Banerjee
Postdoctoral Alumni
bikramjitbanerjee [at] yahoo com
Gregory Kuhlmann
Ph.D. Alumni
kuhlmann [at] cs utexas edu
Peter Stone
Faculty
pstone [at] cs utexas edu
Areas of Interest
General Game Playing
Other Areas
Reinforcement Learning
Transfer Learning
Labs
Learning Agents