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

Age	Commit message (Collapse)	Author
46 hours	Stripping debug stuff	tslil clingman

46 hours	Still bugs...	tslil clingman

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

46 hours	Incidental bugfix	tslil clingman

46 hours	Memory leak fix	tslil clingman

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

46 hours	Working on action lists to refactor	tslil clingman

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

46 hours	Fixed some important bugs	tslil clingman

46 hours	Attempting Zobrist hashing	tslil clingman

46 hours	no speed increase ...	tslil clingman

46 hours	Trying caching to speed things up	tslil clingman

46 hours	Should now play out to the end	tslil clingman

46 hours	Slight fix to game loop	tslil clingman

46 hours	Renaming	tslil clingman

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

46 hours	Experimenting	tslil clingman

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

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

46 hours	Slight bug	tslil clingman

46 hours	First steps towards character LCD	tslil clingman

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

46 hours	Multiplatform builds!	tslil clingman

46 hours	Shed dependency of linenoise	tslil clingman

46 hours	Finally fixed move generation	tslil clingman

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

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

46 hours	Opps, wrong stone	tslil clingman

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

46 hours	Better status	tslil clingman

46 hours	Went back up to 1986 weights	tslil

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

46 hours	Changed function back to macro	tslil

46 hours	There was a bug in the minimax!	tslil

46 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.
46 hours	So after a small tweak, it actually plays well!	tslil

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

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

46 hours	There are still some bugs somewhere in minimax ...	tslil
	In tinue it doesn't seem to choose a move
46 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
46 hours	Trying minimax	tslil

46 hours	Have to account for CPS	tslil

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

46 hours	Closing in!	tslil

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

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

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

46 hours	Fixed a small bug in PTN parsing, other stuff	tslil