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

Age	Commit message (Collapse)	Author
47 hours	Added tunable search depth and self-play	tslil clingman

47 hours	Toying with symmetrising data	tslil clingman

47 hours	In-lined score reporting	tslil clingman

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

47 hours	Finally fixed memory order of weights!	tslil clingman

47 hours	Opps, wrong stone	tslil clingman

47 hours	Inlined placements, should be faster	tslil clingman

47 hours	Merge branch 'master' of git.sr.ht:~tslil/ctak	tslil clingman

47 hours	Memory oob fix	tslil clingman

47 hours	Fixed extract script, wget tells me not to use -O	tslil clingman

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

47 hours	It works, but it's too slow	tslil clingman

47 hours	Starting work on MCU port	tslil clingman

47 hours	Better status	tslil clingman

47 hours	New weights from a wider training	tslil clingman

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

47 hours	Might as well use all of them...	tslil clingman

47 hours	Went back up to 1986 weights	tslil

47 hours	Quick sketch of non-determinism	tslil

47 hours	Another road bug	tslil

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

47 hours	Changed function back to macro	tslil

47 hours	There was a bug in the minimax!	tslil

47 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.
47 hours	So after a small tweak, it actually plays well!	tslil

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

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

47 hours	There are still some bugs somewhere in minimax ...	tslil
	In tinue it doesn't seem to choose a move
47 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
47 hours	Trying minimax	tslil

47 hours	Crass error	tslil

47 hours	Weights?	tslil

47 hours	Wider?	tslil

47 hours	Trying various things to teach ti	tslil

47 hours	Have to account for CPS	tslil

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

47 hours	Closing in!	tslil

47 hours	Auto-generating weights	tslil

47 hours	Generate the correct format directly	tslil

47 hours	New weights	tslil

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

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

47 hours	Working version of this script	tslil

47 hours	This finally works!	tslil

47 hours	Hopefully removed all layer bugs	tslil

47 hours	Trying again with correct data generation	tslil

47 hours	Also this was wrong	tslil

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

47 hours	This is the general idea, but i'm sure order is incorrect somewhere	tslil