An implementation of Tak and a computer opponent in C https://git.l-3.space/ctak/atom/.gitignore?h=hybrid_rootstrap 2026-09-25T15:18:21Z 2026-09-25T15:18:21Z tslil tslil@posteo.de 2026-09-25T13:46:31Z urn:sha1:61e5b8949b2f5e8973c58f0dcc7c20c4bdade029 2026-09-11T16:00:18Z tslil tslil@posteo.de 2026-09-11T11:56:12Z urn:sha1:6e90f1145b2c5c0f2dcc82d21ec45432274b8cad The goal in this change was to overcome the rock-paper-scissors phenomenon that was happening in capability space by having on a single candidate learn to beat the most recent version of itself. In some sense this lead to rotating around in capability space instead of chasing monotonic improvements. I hope that flipping to a system in which many (N=5) candidates play each other and learn from their own set of diverse games in this pool, combined with --replay-iters, will lead to a given network having to have a much more comprehensive understanding of the space of tactics. I haven't yet had time to train this thorougly, will run those experiments on my desktop computer. 2026-09-02T11:13:01Z tslil tslil@posteo.de 2026-08-30T18:46:07Z urn:sha1:241156da6f35cb888253e6b8814e7b61a76b4fc7 NOTE: 6x6 weights are as-yet untrained On the performance side: * switch from linked-list chaining hash table to direct mapping * cache check_win by hash * persist transposition tables across plies (this was a big deal and difficult to puzzle out) * add align directives to the network floats * prepare_nn_input gained a small LUT to avoid branching (i suppose you might call this 1D embedding) * apply mtune=native for the native builds On the correctness side: * Zobrist has now includes the ply parity * the network now predicts something in [-1, 1] using tanh (approximated by polynomials) * the training object is now MSE because we're learning a value estimate * use .clangd instead of compile_commands.json On the training side: * completely forgo human-derived data set * implement td(lambda), self-play, tournaments 2026-05-05T21:16:39Z tslil tslil@posteo.de 2026-05-05T21:06:02Z urn:sha1:696c3808220ea9d8c604939894a2d509f05cc4c6 we needed to be saving the alpha before the search loop in which we modified it. At this point, though i can't remember, i expect that this is the cause of whatever "instability" the comment was talking about that would have prevented us from using >= in the TT lookup. 2023-01-15T15:03:37Z tslil clingman tslil@posteo.de 2023-01-15T15:03:37Z urn:sha1:81213c273fd874aba95c45bd692e14079ebce434 Gone is the convolutional neural network, for it turns out not only is it more difficult to train, but all of the extra information about board layers didn't make much of a difference at this size. So cnn1986 has been replaced by nn1986, a standard, two-layer, dense nn configured as a binary classifier and (mis)used in that capacity. Note: total number of parameters is unchanged. HARK: this new nn exposes a bug somewhere in ctak. Run ctlm with self-play to see the completely borked board state at the end. 2021-02-05T19:02:36Z tslil clingman tslil@posteo.de 2021-02-05T19:02:36Z urn:sha1:ed070ebc252f6d6d392b51b3a836bd08965b3946 2021-02-05T05:12:18Z tslil clingman tslil@posteo.de 2021-02-03T00:23:54Z urn:sha1:4f20d9fd63b6b3e30130c84c20f7cdbbbf2df76d 2021-01-19T04:14:12Z tslil clingman tslil@posteo.de 2021-01-19T04:14:12Z urn:sha1:c99089f290e9cc8180d856e4150995107bc9f4e3 2021-01-19T01:19:18Z tslil clingman tslil@posteo.de 2021-01-19T01:19:18Z urn:sha1:ddc29d6bd8ff17123986bd5c36556c784476a8c7 2021-01-18T02:06:04Z tslil clingman tslil@posteo.de 2021-01-18T02:06:04Z urn:sha1:af3c5a9094d0c27bb49ec618f2a9a7af5f96f575 This reverts commit 43eec01361eb6174142180c29afef960e041514e.