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

Age	Commit message (Collapse)	Author
41 hours	Playing around with huge nn's, poorly trained.sixes	tslil
	Not great at shallow depths
41 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.
41 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.
41 hours	Rename ct_k -> ct, IANAL but ...	tslil

41 hours	Small typo in generated output for weights	tslil clingman

41 hours	Correct line clearing behaviour, EXIT_FAILURE <~ -1	tslil clingman

41 hours	Renamed binaries	tslil clingman

41 hours	TEI interface working!	tslil clingman

41 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.
41 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.
41 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.
41 hours	Purged uninteresting statistics	tslil

41 hours	Syntax errors, small tweak to training data generation	tslil clingman

41 hours	Added license information!	tslil clingman

41 hours	Print progress before recursion rather than after	tslil clingman

41 hours	Small oversight	tslil clingman

41 hours	Small changes to build ct1986	tslil clingman

41 hours	Stable negamax-alpha-beta fail-soft	tslil clingman

41 hours	Actually it seems before i was mis-counting	tslil clingman

41 hours	There is still a bug, it doesn't appear to be checking enough	tslil clingman

41 hours	Stripping debug stuff	tslil clingman

41 hours	Still bugs...	tslil clingman

41 hours	Still some bugs, standing stone becomes flat at depth4 self-play??	tslil clingman

41 hours	Incidental bugfix	tslil clingman

41 hours	Memory leak fix	tslil clingman

41 hours	This is the basic idea, there's ≥ 1 bug (generates illegals...)	tslil clingman

41 hours	Working on action lists to refactor	tslil clingman

41 hours	Still trying	tslil clingman
	\|
41 hours	Hash collisions	tslil clingman

41 hours	Fixed some important bugs	tslil clingman

41 hours	Attempting Zobrist hashing	tslil clingman

41 hours	no speed increase ...	tslil clingman

41 hours	Trying caching to speed things up	tslil clingman

41 hours	Should now play out to the end	tslil clingman

41 hours	Starting work on LCD library	tslil clingman

41 hours	Slight fix to game loop	tslil clingman

41 hours	Renaming	tslil clingman

41 hours	Many fixes, i think this is actually correct	tslil clingman

41 hours	Experimenting	tslil clingman

41 hours	Vertical line is just incremented %2, i'll have to manually buffer	tslil clingman
	charlcd.c:621 case '\n': /* * flush the remainder of the current line and * go to the beginning of the next line */ for (; priv->addr.x < lcd->bwidth; priv->addr.x++) lcd->ops->write_data(lcd, ' '); priv->addr.x = 0; priv->addr.y = (priv->addr.y + 1) % lcd->height; charlcd_gotoxy(lcd); break;
41 hours	Working on better output + build system refinement	tslil clingman

41 hours	Forgot some file arguments	tslil clingman

41 hours	Can't stop half-way through turn	tslil clingman

41 hours	In-lined as much as a i dare	tslil clingman

41 hours	Closing in on lcd!	tslil clingman

41 hours	Slight bug	tslil clingman

41 hours	Currently segfaults. Maybe because serial is in use?	tslil clingman

41 hours	First steps towards character LCD	tslil clingman

41 hours	Saving cursor position was not a good idea	tslil clingman

41 hours	Multiplatform builds!	tslil clingman