Peter Stone's Selected Publications

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


Graph-Based Domain Mapping for Transfer Learning in General Games

Gregory Kuhlmann and Peter Stone. Graph-Based Domain Mapping for Transfer Learning in General Games. In Proceedings of The Eighteenth European Conference on Machine Learning, September 2007.

Download

[PDF]377.0kB  [postscript]601.6kB  

Abstract

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.

BibTeX Entry

@Inproceedings(ECML07-rulegraphs,
  author="Gregory Kuhlmann and Peter Stone",
  title="Graph-Based Domain Mapping for Transfer Learning in General Games",
  booktitle="Proceedings of The Eighteenth European Conference on Machine Learning",
  month="September",
  year="2007",
  abstract={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.  },
)

Generated by bib2html.pl (written by Patrick Riley ) on Fri Sep 05, 2014 12:17:35