ctak/include/cnn1986.c, branch mainAn implementation of Tak and a computer opponent in Chttps://git.l-3.space/cgit/ctak/atom?h=main2026-08-28T18:37:41Znew neural network arch (faster + better) & minor changes + fixes2026-08-28T18:37:41Ztslil clingmantslil@posteo.de2023-01-15T15:03:37Zurn: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So cnn1986 has been replaced by nn1986, a standard, two-layer, dense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.
Welcome geminict!2026-08-28T18:37:41Ztslil clingmantslil@posteo.de2021-10-05T22:22:23Zurn: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.
Trying to make things faster2026-08-28T18:37:41Ztsliltslil@posteo.de2021-06-01T19:20:48Zurn:sha1:0deb42134cb7f0ed6ec809c3de1052ab2dfe2235
I tried the following, but they all made things worse:
- moving away from the singly-linked (tail tracking) list for actions
by:
+ using an array zipper for a deque
+ using an array to poorly hold a floating deque
- caching the results of generating move lists in the transposition
table and then
+ copying the resulting list/zip/deque instead of generating it
+ applying the move-to-front without copying, but this made the
search order worse. Presumably in this case shallower nodes were
messing up the search tree with garbage moves?
I think some of this is not supposed to happen, but i have just the
right combination of poor evaluation function and naively ordered and
cheap move generation that i'm in a local minimum here.
Fix copyright notice in files, and small preemptive optimisation2026-08-28T18:37:41Ztslil clingmantslil@posteo.de2021-03-28T04:19:05Zurn:sha1:2dbb9fa9b69e49d49cebb1c17559f6fe67600a4d
Eventually there'll be a more complicated data generation step than
the one we're presently using, so having it in-lined in the loop is
wasteful. Ideally also this would be update per ply and we could avoid
recalculating it entirely for every query -- though it's probably
``fast enough'' for now. Also, caching is WIP.
Rename ct_k -> ct, IANAL but ...2026-08-28T18:37:41Ztsliltslil@posteo.de2021-02-05T21:49:14Zurn:sha1:ce09b6d94ac3dbf426e959b14fd7731001a003d1Just some #weightgoals ;)2026-08-28T18:37:41Ztslil clingmantslil@posteo.de2021-02-01T04:33:39Zurn: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.
Added license information!2026-08-28T18:37:41Ztslil clingmantslil@posteo.de2021-01-29T02:30:30Zurn:sha1:a77062ce3dc9a99ad0662010cc7eeb00dd5036a6There is still a bug, it doesn't appear to be checking enough2026-08-28T18:37:41Ztslil clingmantslil@posteo.de2021-01-26T05:24:03Zurn:sha1:9131e08817ae2f3bd58a8a0ba9f1e692ceb8604cStill trying2026-08-28T18:37:41Ztslil clingmantslil@posteo.de2021-01-24T17:07:18Zurn:sha1:815cde44e5060ad093347bb47fc66d41c9d3a3ed
|
Attempting Zobrist hashing2026-08-28T18:37:41Ztslil clingmantslil@posteo.de2021-01-23T23:20:05Zurn:sha1:18496a371a2204e8c1b448921a87108f4aa7ada3