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

Age	Commit message (Collapse)	Author
2 days	Welcome geminict!	tslil clingman
	This is a special interface to negamax_cnn1986 which is designed to generate output for use in a CGI tak interface to be used over gemini. Also in this commit is a reformating of the various source files to use the traditional tab width of 8 spaces.
2 days	Corrected generation of training data for 6s	tslil clingman

2 days	Don't generate header for training data + tweaks	tslil
	For some reason it would seem that moving flats to a lower value and increasing the proximity between caps and top flats improves acquisition. Still not great, but every bit counts.
2 days	Change the training data generation a little	tslil clingman
	Although it pains me to say it, ``label smoothing'' appears to be actually work. I'm also currently experimenting with training simply against _all_ games, instead of only bot matches. Once the training finishes i'll pit cttei against itself with old and new weights, hopefully there'll be a noticeable improvement.
2 days	TEI interface working!	tslil clingman

2 days	Tried some naive iterative deepening. Work on TEI interface next	tslil clingman
	If TEI is implemented, then i could make use of Morten's racetrack (https://github.com/MortenLohne/racetrack) and develop a quantitative measure of the bot's performance. This is the current priority.
2 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.
2 days	Syntax errors, small tweak to training data generation	tslil clingman

2 days	Added license information!	tslil clingman

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

2 days	Toying with symmetrising data	tslil clingman

2 days	Went back up to 1986 weights	tslil

2 days	Changed function back to macro	tslil

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

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	Generate the correct format directly	tslil

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

2 days	Hopefully removed all layer bugs	tslil

2 days	Trying again with correct data generation	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	Fixed a small bug in PTN parsing, other stuff	tslil

2 days	Closing in on something reasonable for roads	tslil

2 days	Searching for a good representation	tslil

2 days	Small tweaks	tslil

2 days	On the hunt for a better representation	tslil

2 days	Experimenting with training nn	tslil

2 days	Separate concerns in pptdb, remove legacy in extract.sh	tslil

2 days	Gotta go fast	tslil

2 days	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
2 days	Tabs for indentation, spaces for alignment	tslil

2 days	Fixed indentation and some bugs, stats programme	tslil