UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Graph-Based Domain Mapping for Transfer Learning in General Games (2007)
Gregory Kuhlmann
and
Peter Stone
A general game player is an agent capable of taking as input a description of a game's rules in a formal language and proceeding to play without any subsequent human input. To do well, an agent should learn from experience with past games and transfer the learned knowledge to new problems. We introduce a graph-based method for identifying previously encountered games and prove its robustness formally. We then describe how the same basic approach can be used to identify similar but non-identical games. We apply this technique to automate domain mapping for value function transfer and speed up reinforcement learning on variants of previously played games. Our approach is fully implemented with empirical results in the general game playing system.
View:
PDF
,
PS
,
HTML
Citation:
In
Proceedings of the 18th European Conference on Machine Learning
, September 2007.
Bibtex:
@InProceedings{kuhlmann:ecml07, title={Graph-Based Domain Mapping for Transfer Learning in General Games}, author={Gregory Kuhlmann and Peter Stone}, booktitle={Proceedings of the 18th European Conference on Machine Learning}, month={September}, url="http://www.cs.utexas.edu/users/ai-lab?kuhlmann:ecml07", year={2007} }
People
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