msproj

Go to file

Woody Folsom aca8320600 First working implementation of ANN which is trained using GameResults.

The PassFilter simply outputs BlackWins and WhiteWins (Range 0 - 1 but not presently clamped).
In principle, this type of feedforward ANN can be used to decide whether a PASS will result in blackwins or whitewins at any stage.
The goal is for the network to learn that passing while losing when valid moves exist is bad, but passing while winning is relatively harmless later in the game.

2012-11-17 18:40:31 -05:00

.settings

Initial commit.

2012-08-26 11:48:21 -04:00

bugreports

MonteCarloUCT now plays most of a 9x9 game.

2012-09-01 18:14:12 -04:00

data

First working implementation of ANN which is trained using GameResults.

2012-11-17 18:40:31 -05:00

lib

Beginning to implement neural net training. Fixed bugs in SGF/LaTeX export.

2012-11-15 15:00:40 -05:00

src/net/woodyfolsom/msproj

First working implementation of ANN which is trained using GameResults.

2012-11-17 18:40:31 -05:00

test/net/woodyfolsom/msproj

First working implementation of ANN which is trained using GameResults.

2012-11-17 18:40:31 -05:00

.classpath

Fixed unit tests. Updated classpath.

2012-11-16 04:21:19 -05:00

.gitignore

Initial commit.

2012-08-26 11:48:21 -04:00

.project

Initial commit.

2012-08-26 11:48:21 -04:00

build.xml

Game can now be run using java -jar GoGame.jar.

2012-09-06 09:43:32 -04:00

README.txt

Added simple GUI for 9x9 go. Use HUMAN_GUI player option.

2012-11-13 10:38:34 -05:00

README.txt

Wood texture is from open source Wordpress resource site wpliving.net.