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

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

1998-09-28

arxiv.org/abs/cs/9809111v1

Alife V: Poster Presentations, May 16-18 1996, pages 43-50

Computer Science

Neural and Evolutionary Computing

8 pages, 5 figures, LaTeX 2.09 (works with LaTeX2e)

Scientific paper

Dots-and-Boxes is a child's game which remains analytically unsolved. We implement and evolve artificial neural networks to play this game, evaluating them against simple heuristic players. Our networks do not evaluate or predict the final 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.

Affiliated with

Also associated with

No associations

Rating

Evolution of Neural Networks to Play the Game of Dots-and-Boxes does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Evolution of Neural Networks to Play the Game of Dots-and-Boxes, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Evolution of Neural Networks to Play the Game of Dots-and-Boxes will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-481977