Sciweavers

Share
ACG
2003
Springer

Evaluation in Go by a Neural Network using Soft Segmentation

9 years 14 days ago
Evaluation in Go by a Neural Network using Soft Segmentation
In this article a neural network architecture is presented that is able to build a soft segmentation of a two-dimensional input. This network architecture is applied to position evaluation in the game of Go. It is trained using self-play and temporal difference learning combined with a rich two-dimensional reinforcement signal. Two experiments are performed, one using the raw board position as input, the other one doing some simple preprocessing of the board. The second network is able to achieve playing strength comparable to a 13-kyu Go program.
Markus Enzenberger
Added 06 Jul 2010
Updated 06 Jul 2010
Type Conference
Year 2003
Where ACG
Authors Markus Enzenberger
Comments (0)
books