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

Age	Commit message (Collapse)	Author
43 hours	Shed dependency of linenoise	tslil clingman

43 hours	Finally fixed move generation	tslil clingman

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

43 hours	Toying with symmetrising data	tslil clingman

43 hours	In-lined score reporting	tslil clingman

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

43 hours	Finally fixed memory order of weights!	tslil clingman

43 hours	Opps, wrong stone	tslil clingman

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

43 hours	Starting work on MCU port	tslil clingman

43 hours	Better status	tslil clingman

43 hours	Went back up to 1986 weights	tslil

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

43 hours	Changed function back to macro	tslil

43 hours	There was a bug in the minimax!	tslil

43 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.
43 hours	So after a small tweak, it actually plays well!	tslil

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

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

43 hours	There are still some bugs somewhere in minimax ...	tslil
	In tinue it doesn't seem to choose a move
43 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
43 hours	Trying minimax	tslil

43 hours	Weights?	tslil

43 hours	Wider?	tslil

43 hours	Trying various things to teach ti	tslil

43 hours	Have to account for CPS	tslil

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

43 hours	Closing in!	tslil

43 hours	Auto-generating weights	tslil

43 hours	Generate the correct format directly	tslil

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

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

43 hours	Working version of this script	tslil

43 hours	Hopefully removed all layer bugs	tslil

43 hours	Trying again with correct data generation	tslil

43 hours	Also this was wrong	tslil

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

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

43 hours	Shuffling is important	tslil

43 hours	Magic	tslil

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

43 hours	Closing in on something reasonable for roads	tslil

43 hours	Searching for a good representation	tslil

43 hours	Small tweaks	tslil

43 hours	On the hunt for a better representation	tslil

43 hours	Experimenting with training nn	tslil

43 hours	Separate concerns in pptdb, remove legacy in extract.sh	tslil

43 hours	Gotta go fast	tslil

43 hours	First attempt at training data + exclude draws + list overflows too	tslil
	Take the output and do grep -Fvxf output_file input_file to drop the bad games from consideration