Evolution of Neural Networks to Play the Game of Dots-and-Boxes

@article{Weaver1996EvolutionON,
  title={Evolution of Neural Networks to Play the Game of Dots-and-Boxes},
  author={Lex Weaver and Terry Bossomaier},
  journal={CoRR},
  year={1996},
  volume={cs.NE/9809111}
}
Dots-and-Boxes is a child's game which remains analytically unsolved. We implement and evolve ar-tiicial neural networks to play this game, evaluating them against simple heuristic players. Our networks do not evaluate or predict the nal outcome of the game, but rather recommend moves at each stage. Superior generalisation of play by co-evolved populations is found, and a comparison made with networks trained by back-propagation using simple heuristics as an oracle. 

References

Publications referenced by this paper.
Showing 1-3 of 3 references

Minds , brains and programs

  • J. R. Searle
  • Shadows of the Mind
  • 1994

A New Factor in Evolution

  • N. Snoad
  • The American Naturalist

Similar Papers

Loading similar papers…