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

Age	Commit message (Collapse)	Author
45 hours	Slight fix to game loop	tslil clingman

45 hours	Renaming	tslil clingman

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

45 hours	Experimenting	tslil clingman

45 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;
45 hours	Working on better output + build system refinement	tslil clingman

45 hours	Forgot some file arguments	tslil clingman

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

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

45 hours	Closing in on lcd!	tslil clingman

45 hours	Slight bug	tslil clingman

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

45 hours	First steps towards character LCD	tslil clingman

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

45 hours	Multiplatform builds!	tslil clingman

45 hours	Shed dependency of linenoise	tslil clingman

45 hours	Finally fixed move generation	tslil clingman

45 hours	Added tunable search depth and self-play	tslil clingman

45 hours	Toying with symmetrising data	tslil clingman

45 hours	In-lined score reporting	tslil clingman

45 hours	Nicer info, corrected strncmp --> strcmp in places	tslil clingman

45 hours	Finally fixed memory order of weights!	tslil clingman

45 hours	Opps, wrong stone	tslil clingman

45 hours	Revert "Starting work on MCU port"	tslil clingman
	This reverts commit 43eec01361eb6174142180c29afef960e041514e.
45 hours	It works, but it's too slow	tslil clingman

45 hours	Starting work on MCU port	tslil clingman

45 hours	Better status	tslil clingman

45 hours	Went back up to 1986 weights	tslil

45 hours	Dragon is not separate, fixed concession, allowing playing as b/w	tslil

45 hours	Changed function back to macro	tslil

45 hours	There was a bug in the minimax!	tslil

45 hours	Better trained weights, an important oversight in minimax (steps <=)	tslil
	I still can't tell whether if ((ply & 1) == 0) this = this - 1.0; is correct.
45 hours	So after a small tweak, it actually plays well!	tslil

45 hours	Seems tolerable, but not great. Still wont win or lose ???	tslil

45 hours	Trying alpha-beta pruning. There's a bug somewhere ...	tslil

45 hours	There are still some bugs somewhere in minimax ...	tslil
	In tinue it doesn't seem to choose a move
45 hours	Fixed minimax (!), fixed bugs in tak.c	tslil
	With minimax of depth 1 the evaluation function seems alright with the current method of training and generating weights
45 hours	Trying minimax	tslil

45 hours	Weights?	tslil

45 hours	Wider?	tslil

45 hours	Trying various things to teach ti	tslil

45 hours	Have to account for CPS	tslil

45 hours	Well it works, and it's bad. Many bugs fixed in interim	tslil

45 hours	Closing in!	tslil

45 hours	Auto-generating weights	tslil

45 hours	Generate the correct format directly	tslil

45 hours	one output (of course), Pade approximant of logistic for activation	tslil

45 hours	Train on data that is close to the end of the game only	tslil

45 hours	Working version of this script	tslil

45 hours	Hopefully removed all layer bugs	tslil