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

Age	Commit message (Collapse)	Author
41 hours	In-lined as much as a i dare	tslil clingman

41 hours	Closing in on lcd!	tslil clingman

41 hours	Slight bug	tslil clingman

41 hours	Currently segfaults. Maybe because serial is in use?	tslil clingman

41 hours	First steps towards character LCD	tslil clingman

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

41 hours	Multiplatform builds!	tslil clingman

41 hours	Shed dependency of linenoise	tslil clingman

41 hours	Finally fixed move generation	tslil clingman

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

41 hours	Toying with symmetrising data	tslil clingman

41 hours	In-lined score reporting	tslil clingman

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

41 hours	Finally fixed memory order of weights!	tslil clingman

41 hours	Opps, wrong stone	tslil clingman

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

41 hours	Starting work on MCU port	tslil clingman

41 hours	Better status	tslil clingman

41 hours	Went back up to 1986 weights	tslil

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

41 hours	Changed function back to macro	tslil

41 hours	There was a bug in the minimax!	tslil

41 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.
41 hours	So after a small tweak, it actually plays well!	tslil

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

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

41 hours	There are still some bugs somewhere in minimax ...	tslil
	In tinue it doesn't seem to choose a move
41 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
41 hours	Trying minimax	tslil

41 hours	Weights?	tslil

41 hours	Wider?	tslil

41 hours	Trying various things to teach ti	tslil

41 hours	Have to account for CPS	tslil

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

41 hours	Closing in!	tslil

41 hours	Auto-generating weights	tslil

41 hours	Generate the correct format directly	tslil

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

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

41 hours	Working version of this script	tslil

41 hours	Hopefully removed all layer bugs	tslil

41 hours	Trying again with correct data generation	tslil

41 hours	Also this was wrong	tslil

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

41 hours	Two inputs to model, stacks and flat counts	tslil

41 hours	Shuffling is important	tslil

41 hours	Magic	tslil

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

41 hours	Closing in on something reasonable for roads	tslil