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

Age	Commit message (Collapse)	Author
2 days	Forgot some file arguments	tslil clingman

2 days	Can't stop half-way through turn	tslil clingman

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

2 days	Closing in on lcd!	tslil clingman

2 days	Slight bug	tslil clingman

2 days	Currently segfaults. Maybe because serial is in use?	tslil clingman

2 days	First steps towards character LCD	tslil clingman

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

2 days	Multiplatform builds!	tslil clingman

2 days	Shed dependency of linenoise	tslil clingman

2 days	Finally fixed move generation	tslil clingman

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

2 days	Toying with symmetrising data	tslil clingman

2 days	In-lined score reporting	tslil clingman

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

2 days	Finally fixed memory order of weights!	tslil clingman

2 days	Opps, wrong stone	tslil clingman

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

2 days	Starting work on MCU port	tslil clingman

2 days	Better status	tslil clingman

2 days	Went back up to 1986 weights	tslil

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

2 days	Changed function back to macro	tslil

2 days	There was a bug in the minimax!	tslil

2 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.
2 days	So after a small tweak, it actually plays well!	tslil

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

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

2 days	There are still some bugs somewhere in minimax ...	tslil
	In tinue it doesn't seem to choose a move
2 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
2 days	Trying minimax	tslil

2 days	Weights?	tslil

2 days	Wider?	tslil

2 days	Trying various things to teach ti	tslil

2 days	Have to account for CPS	tslil

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

2 days	Closing in!	tslil

2 days	Auto-generating weights	tslil

2 days	Generate the correct format directly	tslil

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

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

2 days	Working version of this script	tslil

2 days	Hopefully removed all layer bugs	tslil

2 days	Trying again with correct data generation	tslil

2 days	Also this was wrong	tslil

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

2 days	Two inputs to model, stacks and flat counts	tslil

2 days	Shuffling is important	tslil

2 days	Magic	tslil