ctak, branch hybrid_rootstrapAn implementation of Tak and a computer opponent in Chttps://git.l-3.space/ctak/atom/?h=hybrid_rootstrap2026-10-09T19:29:37Zswitch to orjson for faster loading2026-10-09T19:29:37Ztsliltslil@posteo.de2026-10-08T18:51:04Zurn:sha1:dfd6accd85cc56babb3ee7c6fac53d7d3cad3a07fix plot labels2026-09-25T17:03:07Ztsliltslil@posteo.de2026-09-25T16:43:48Zurn:sha1:adf8dee63cf3a2b2fea7c74daf90f7efbe1e9017factor out nn_train.py into a separate python project to make it more manageable, add plotting and offline strength fit2026-09-25T15:18:21Ztsliltslil@posteo.de2026-09-25T13:46:31Zurn:sha1:61e5b8949b2f5e8973c58f0dcc7c20c4bdade029try combining loops2026-09-20T07:29:22Ztsliltslil@posteo.de2026-09-20T07:28:09Zurn:sha1:6a2197328065fe38ac62d9e76e3e943fd297e73ctransposing the weights gives ~2.5x speedup2026-09-19T19:32:46Ztsliltslil@posteo.de2026-09-19T19:24:08Zurn:sha1:9f5f953a95c8617cd2fdd24f7402af632c1b07c2big refactor2026-09-19T18:23:34Ztsliltslil@posteo.de2026-09-19T08:59:29Zurn:sha1:fe7268110d93e2abe4d4b51ac64e83521a8d6382
* use elo
* optionally train on only diagonal
* train-inference nonlinearity alignment
grid search2026-09-18T20:19:33Ztsliltslil@posteo.de2026-09-18T14:12:13Zurn:sha1:3f918be9b31026ae546f66c565b9494dab6d82a2working towards hybrid rootstrap2026-09-18T14:12:19Ztsliltslil@posteo.de2026-09-17T06:01:29Zurn:sha1:0dba02072e9a89e35885d9078c0c8b58956448cefix tt issue for non-self-play2026-09-16T20:02:53Ztsliltslil@posteo.de2026-09-16T19:10:33Zurn:sha1:1898add0142b70b3fef5af78a6f3d7399a3f2cd5
A little subtle, but in non-self-play games sharing tt entries is incorrect. We must therefore key additionally on the evaulation function itself.
move data generation into the epoch loop2026-09-13T19:15:31Ztsliltslil@posteo.de2026-09-12T18:37:56Zurn:sha1:7f1566fb21dfe8c99bc770885cc2cc4e478e16b4
Previously we would spend all of the training epochs on making the network a better predictor of the *initial* TD-leaf values that we computed before the start of the first epoch. There's definitely something stale about this, given that the TD-leaf training targets involved the net evaluation at PVs. I'm not overly confident that this makes sense, but as a kind of compromise between fully on-line TD-leaf and the fully stale version we had before, we now recompute the TD-leaf values in each epoch with the fine-tuned net instead of the epoch 0 net.
Perhaps we were just lucky, but this seems to train a strong network under the default setting.
More experimentation is required.