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

Age	Commit message (Collapse)	Author
3 days	Just some #weightgoals ;)	tslil clingman
	It turns out that while i was training on a 0/1 classification problem, i was using 2*eval - 1. Training using this function instead, and on bot-dominated game choices (chosen_player in extract.sh) seems to have given a better evaluation function. At the least, Morten's swindle doesn't work anymore.
3 days	Added license information!	tslil clingman

3 days	Finally fixed memory order of weights!	tslil clingman

3 days	New weights from a wider training	tslil clingman

3 days	Went back up to 1986 weights	tslil

3 days	There was a bug in the minimax!	tslil

3 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.
3 days	Seems tolerable, but not great. Still wont win or lose ???	tslil

3 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
3 days	Trying minimax	tslil

3 days	Weights?	tslil

3 days	Wider?	tslil

3 days	Trying various things to teach ti	tslil

3 days	Auto-generating weights	tslil

3 days	New weights	tslil

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

3 days	This finally works!	tslil