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

Age	Commit message (Collapse)	Author
4 days	Can't stop half-way through turn	tslil clingman

4 days	In-lined as much as a i dare	tslil clingman

4 days	Slight bug	tslil clingman

4 days	First steps towards character LCD	tslil clingman

4 days	Saving cursor position was not a good idea	tslil clingman

4 days	Multiplatform builds!	tslil clingman

4 days	Shed dependency of linenoise	tslil clingman

4 days	Finally fixed move generation	tslil clingman

4 days	Added tunable search depth and self-play	tslil clingman

4 days	Nicer info, corrected strncmp --> strcmp in places	tslil clingman

4 days	Opps, wrong stone	tslil clingman

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

4 days	Better status	tslil clingman

4 days	Went back up to 1986 weights	tslil

4 days	Dragon is not separate, fixed concession, allowing playing as b/w	tslil

4 days	Changed function back to macro	tslil

4 days	There was a bug in the minimax!	tslil

4 days	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.
4 days	So after a small tweak, it actually plays well!	tslil

4 days	Seems tolerable, but not great. Still wont win or lose ???	tslil

4 days	Trying alpha-beta pruning. There's a bug somewhere ...	tslil

4 days	There are still some bugs somewhere in minimax ...	tslil
	In tinue it doesn't seem to choose a move
4 days	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
4 days	Trying minimax	tslil

4 days	Have to account for CPS	tslil

4 days	Well it works, and it's bad. Many bugs fixed in interim	tslil

4 days	Closing in!	tslil

4 days	one output (of course), Pade approximant of logistic for activation	tslil

4 days	Train on data that is close to the end of the game only	tslil

4 days	Close in principle, but there;s a bug in ct1997 &/ pptdb!	tslil

4 days	Fixed a small bug in PTN parsing, other stuff	tslil

4 days	Tabs for indentation, spaces for alignment	tslil

4 days	Fixed indentation and some bugs, stats programme	tslil

4 days	Set dialect to C99	tslil

4 days	Added help, trimmed print_info	tslil

4 days	tak.h now tracks win state, optimisations, saved a byte on counts	tslil

4 days	Silly mistake	tslil

4 days	Line-mode mostly complete	tslil

4 days	Working on line-mode front-end	tslil

4 days	Fixed road DFS errors	tslil

4 days	Board printing	tslil

4 days	Added linenoise library, uninitialised variable + renaming	tslil

4 days	Transition to single file header	tslil

4 days	OBOEs in try_move + logic errors	tslil
	- Corrected use of static - Implemented next_turn
4 days	Output PTN as well	tslil

4 days	PTN code looks correct, minor tweaks and header guards	tslil

4 days	Started on PTN stuff	tslil

4 days	Changed representation, implemented most basic things for tak.h	tslil

4 days	Init	tslil