An implementation of Tak and a computer opponent in C https://git.l-3.space/ctak/atom/Makefile?h=hybrid_rootstrap 2026-09-18T14:12:19Z 2026-09-18T14:12:19Z tslil tslil@posteo.de 2026-09-17T06:01:29Z urn:sha1:0dba02072e9a89e35885d9078c0c8b58956448ce 2026-09-13T19:15:31Z tslil tslil@posteo.de 2026-09-12T18:37:56Z urn: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. 2026-09-12T14:47:15Z tslil tslil@posteo.de 2026-09-11T17:36:10Z urn:sha1:a361728f39812e25599323c52510c0eb3131bd90 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. 2026-09-05T15:02:41Z tslil tslil@posteo.de 2026-09-05T08:54:11Z urn:sha1:f6ea541ce762b190c7d68f221a24b555ebf0c80b After quite a bit of experimentation it would appear that a far better way to train on self-play data in this setup is to randomise not the moves but the opening. The new selfplay and match binaries have lost the epsilon parameter and now play a random opening of some length before switching to pure, deterministic engine inference. This also resulted in a cleanup of nn_train.py. As an added bonus, in this configuration it makes sense to harvest training data from both sides in self-play and consequently the two sides are given distinct game ids (this was almost surely an oversight in the original version of TD(lambda) that i had). I also noticed that rand32 was not using the top 32bits of xorshitf*. *Under default settings nn_train.py produces a 5x5 weight set that doesn't lose a single game to any other cttei that i cared to look at, when measured using `racetrack` (which has a diverse balanced opening book). 2026-09-04T20:03:59Z tslil tslil@posteo.de 2026-09-03T19:17:22Z urn:sha1:1ca3309dad9d412870b2b793f33af7a7ccabd514 TD-lambda and TD-leaf are separated by the observation that minimax with a parameterised leaf heuristic is differentiable* in the parameters. "All" that had to be done was to extract the "principal variation": which one position survived all of the pruning to become the reported value. This was a bit fiddly and uncovered a subtle bug (again) in negamax.c: we were not being complete in our overriding of the TT entry and by omitting key it was possible that later searches would find incorrect values. The more interesting question to me was: how do we introduce enough variety while not corrupting the PV chain? I settled on having selfplay have one of the players be epsilon-random but the other greedy (minimax) and simply report only the greedy portion PV chain. This appears to work well enough in practice and doesn't introduce nonsense training data for the net (we don't force its actions to be nonsensical). I also deciced, perhaps in a departure from tradition, that we had good supervised labels for PVs that happened to be winning states, so the training overrides the targets in that case. Finally rolled back some of the ambition in nn_train.py default arguments. *almost always 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 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. 2021-10-22T19:33:06Z tslil clingman tslil@posteo.de 2021-10-22T19:33:06Z urn:sha1:8908c6e19b8508bd6eab0107f6930dfc52905934 That i can tell at a glance, the largest relevant change this introduces is flush-to-zero for floats. Some testing is required to ensure that the CNN isn't too sensitive to this. Preferable to that option is to simply train it without relying on subnormal floats in the first place. 2021-10-05T22:23:32Z tslil clingman tslil@posteo.de 2021-10-05T22:22:23Z urn:sha1:c9fa20b590de94a9ddb408e277065a117b16570b This is a special interface to negamax_cnn1986 which is designed to generate output for use in a CGI tak interface to be used over gemini. Also in this commit is a reformating of the various source files to use the traditional tab width of 8 spaces.