aboutsummaryrefslogtreecommitdiff
path: root/src/cnn_train.py
AgeCommit message (Collapse)Author
2 daysJust some #weightgoals ;)tslil clingman
It turns out that while i was training on a 0/1 classification problem, i was using 2*eval - 1. Training using this function instead, and on bot-dominated game choices (chosen_player in extract.sh) seems to have given a better evaluation function. At the least, Morten's swindle doesn't work anymore.
2 daysSyntax errors, small tweak to training data generationtslil clingman