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

Age	Commit message (Collapse)	Author
39 hours	fix longstanding negamax bugHEAD main	tslil
	we needed to be saving the alpha before the search loop in which we modified it. At this point, though i can't remember, i expect that this is the cause of whatever "instability" the comment was talking about that would have prevented us from using >= in the TT lookup.
39 hours	new neural network arch (faster + better) & minor changes + fixes	tslil clingman
	Gone is the convolutional neural network, for it turns out not only is it more difficult to train, but all of the extra information about board layers didn't make much of a difference at this size. So cnn1986 has been replaced by nn1986, a standard, two-layer, dense nn configured as a binary classifier and (mis)used in that capacity. Note: total number of parameters is unchanged. HARK: this new nn exposes a bug somewhere in ctak. Run ctlm with self-play to see the completely borked board state at the end.
39 hours	Renamed binaries	tslil clingman

39 hours	TEI interface working!	tslil clingman

39 hours	First steps towards character LCD	tslil clingman

39 hours	Getting ready for cross compilation	tslil clingman

39 hours	Revert "Starting work on MCU port"	tslil clingman
	This reverts commit 43eec01361eb6174142180c29afef960e041514e.
39 hours	Starting work on MCU port	tslil clingman

39 hours	Fixed indentation and some bugs, stats programme	tslil

39 hours	Ignore training data for now	tslil

39 hours	Init	tslil