ctak - An implementation of Tak and a computer opponent in C

Age	Commit message (Collapse)	Author
42 hours	might as well enable size 6	tslil clingman
	Same network architecture, same training principle. Predictably this is too slow. Also statically allocate state in driver programmes.
42 hours	switch to explicit game state & important bug fix & clang format	tslil clingman
	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.
42 hours	new neural network arch (faster + better) & minor changes + fixes	tslil clingman
	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 So cnn1986 has been replaced by nn1986, a standard, two-layer, dense nn configured as a binary classifier and (mis)used in that capacity.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.
42 hours	Corrected generation of training data for 6s	tslil clingman

42 hours	Don't generate header for training data + tweaks	tslil
	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.
42 hours	Change the training data generation a little	tslil clingman
	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.
42 hours	TEI interface working!	tslil clingman

42 hours	Tried some naive iterative deepening. Work on TEI interface next	tslil clingman
	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.
42 hours	Just some #weightgoals ;)	tslil clingman
	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.
42 hours	Fairly important bug fixes to lcdlib, LCD now echoes input!	tslil clingman
	Input polling without line-buffering is done using ncurses, so the buildroot configuration had to change accordingly to include that library. The Makefile changed to accommodate stand-alone building of ct1986 and to include -lcurses where appropriate. There were also some typos about copying ct1986 and ctaklm to the correct directories.
42 hours	Syntax errors, small tweak to training data generation	tslil clingman

42 hours	Cleaned up build system	tslil clingman

42 hours	Busybox is irritating	tslil clingman

42 hours	Busybox needs LFS to build	tslil clingman

42 hours	Cleaning up busybox	tslil clingman

42 hours	Auto-start the game	tslil clingman

42 hours	Working on better output + build system refinement	tslil clingman

42 hours	Infrastructure more or less set up!	tslil clingman
	It remains to tweak ct1986.c and add a .login file to autorun stuff!