Learning on Graphs in the Game of Go

@inproceedings{Graepel2001LearningOG,
  title={Learning on Graphs in the Game of Go},
  author={Thore Graepel and Mike Goutri{\'e} and Marco Kr{\"u}ger and Ralf Herbrich},
  booktitle={ICANN},
  year={2001}
}
We consider the game of Go from the point of view of machine learning and as a well-deened domain for learning on graph representations. We discuss the representation of both board positions and candidate moves and introduce the common fate graph (CFG) as an adequate representation of board positions for learning. Single candidate moves are represented as feature vectors with features given by subgraphs relative to the given move in the CFG. Using this representation we train a support vector… CONTINUE READING
Highly Cited
This paper has 31 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.
24 Citations
8 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-8 of 8 references

The program GoTools and its computer-generated Tsume Go database

  • T. Wolf
  • Proceedings of the 1st Game Programming Workshop,
  • 1994
2 Excerpts

Knowledge representation in The Many Faces of Go

  • D. Fotland
  • 1993
1 Excerpt

Theoretical foundations of the potential function method in pattern recognition learning

  • M. Aizerman, E. Braverman, L. Rozonoer
  • Automation and Remote Control,
  • 1964
1 Excerpt

Similar Papers

Loading similar papers…