An implementation of Tak and a computer opponent in C https://git.l-3.space/ctak/atom?h=main 2026-08-28T18:37:41Z 2026-08-28T18:37:41Z tslil clingman tslil@posteo.de 2023-01-15T20:31:00Z urn:sha1:0223a9bec5535fced1a7698b55fd42155d9b0446 Previously the code base assumed that there was a single, global game state which was the implicit target of all actions taken. Looking ahead at architectural improvements, this has now been (almost entirely) made explicit and functions take tak_state_p where necessary (and also where unnecessary). Two important fixes to actions.c were made: - Previously when generating the possible stack moves, stack height overflows (> 15) were not taken into account and this resulted in the tree search corrupting the board state. Now action search does not list all legal actions, rather the subset of these encodeable by the implementation. - The check for crushing on a stack move was incorrect (too strict), and this resulted in many legitimate moves being igonored. Finally, in other changes, weights have also been improved by training all games instead of some subset for chosen players, and clang-format was run on the codebase. 2026-08-28T18:37:41Z tslil clingman tslil@posteo.de 2023-01-15T15:03:37Z urn:sha1:ee216c008a188a9436fedb85c70ee5d1719733b1 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 So cnn1986 has been replaced by nn1986, a standard, two-layer, dense nn configured as a binary classifier and (mis)used in that capacity.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. 2026-08-28T18:37:41Z tslil clingman tslil@posteo.de 2021-10-05T22:22:23Z urn:sha1:cf175fc346f1b208766b1f55d3673a7b208f322a 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. 2026-08-28T18:37:41Z tslil clingman tslil@posteo.de 2021-03-18T03:10:53Z urn:sha1:c9823c76dd43aa40bef3f67fa0940a78cb40bf05 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-02-12T02:04:42Z urn:sha1:00a04c2929bdc8f8f4bf7d5d8cf413ebfb3cd006 For some reason it would seem that moving flats to a lower value and increasing the proximity between caps and top flats improves acquisition. Still not great, but every bit counts. 2026-08-28T18:37:41Z tslil clingman tslil@posteo.de 2021-02-11T01:07:24Z urn:sha1:890eb8d7f4a8c46eae18283ca5ac9c61fd41ed97 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. 2026-08-28T18:37:41Z tslil clingman tslil@posteo.de 2021-02-03T00:23:54Z urn:sha1:40c6b1dafab4de169bac8a799e7953e85061218e 2026-08-28T18:37:41Z tslil clingman tslil@posteo.de 2021-02-02T02:46:24Z urn:sha1:11956b2e940f5e1839efab187d898092e819a766 If TEI is implemented, then i could make use of Morten's racetrack (https://github.com/MortenLohne/racetrack) and develop a quantitative measure of the bot's performance. This is the current priority. 2026-08-28T18:37:41Z tslil clingman tslil@posteo.de 2021-02-01T04:33:39Z urn:sha1:328c8d1e3094a942d6a2edd933c9cc4ab09daab1 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. 2026-08-28T18:37:41Z tslil clingman tslil@posteo.de 2021-01-29T19:05:06Z urn:sha1:fcface1079b1c44c7ccca3d117c698347c978f20