diff options
| author | tslil clingman <tslil@posteo.de> | 2021-02-10 20:07:24 -0500 |
|---|---|---|
| committer | tslil <tslil@posteo.de> | 2026-08-28 19:37:41 +0100 |
| commit | 890eb8d7f4a8c46eae18283ca5ac9c61fd41ed97 (patch) | |
| tree | e0239b7d48b83fce4f9107ed553717b14042646a /include/cnn1986_treap_cache.c | |
| parent | ce09b6d94ac3dbf426e959b14fd7731001a003d1 (diff) | |
Change the training data generation a little
Although it pains me to say it, ``label smoothing'' appears to be
actually work. I'm also currently experimenting with training simply
against _all_ games, instead of only bot matches. Once the training
finishes i'll pit cttei against itself with old and new weights,
hopefully there'll be a noticeable improvement.
Diffstat (limited to 'include/cnn1986_treap_cache.c')
0 files changed, 0 insertions, 0 deletions