Co-Evolving Checkers Playing Programs using only Win , Lose , or Draw

  title={Co-Evolving Checkers Playing Programs using only Win , Lose , or Draw},
  author={Kumar Chellapilla and David B. Fogel},
This paper details ef forts made to evolve neural networks for playing checkers. In particular , multilayer perceptrons were used as evaluation functions to compare the worth of alternative boards. The weights of these neural networks were evolved in a coevolutionary manner , which networks competing only against other extant networks in the population. No external "expert system" was used for comparison or evaluation. Feedback to the networks was limited to an overall point score based on the… CONTINUE READING


Publications referenced by this paper.
Showing 1-7 of 7 references

Deep Thoughts on Deep Blue,

  • D. Clark
  • IEEE Exper t,
  • 1997
Highly Influential
4 Excerpts

Tree Searching Algorithms,

  • H. Kaindl
  • T. A. Marsland and J. Schaef fer,
  • 1990
2 Excerpts

Similar Papers

Loading similar papers…