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

Age	Commit message (Collapse)	Author
48 hours	Finally fixed memory order of weights!	tslil clingman

48 hours	Opps, wrong stone	tslil clingman

48 hours	Inlined placements, should be faster	tslil clingman

48 hours	Memory oob fix	tslil clingman

48 hours	Revert "Starting work on MCU port"	tslil clingman
	This reverts commit 43eec01361eb6174142180c29afef960e041514e.
48 hours	Leftover from another branch	tslil clingman

48 hours	Starting work on MCU port	tslil clingman

48 hours	Beginning to work on probabilistic depth now that MCU is out	tslil clingman

48 hours	Quick sketch of non-determinism	tslil

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

48 hours	Changed function back to macro	tslil

48 hours	There was a bug in the minimax!	tslil

48 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.
48 hours	So after a small tweak, it actually plays well!	tslil

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

48 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
48 hours	Trying minimax	tslil