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

Age	Commit message (Collapse)	Author
2 days	switch to explicit game state & important bug fix & clang format	tslil clingman
	Previously the code base assumed that there was a single, global game state which was the implicit target of all actions taken. Looking ahead at architectural improvements, this has now been (almost entirely) made explicit and functions take tak_state_p where necessary (and also where unnecessary). Two important fixes to actions.c were made: - Previously when generating the possible stack moves, stack height overflows (> 15) were not taken into account and this resulted in the tree search corrupting the board state. Now action search does not list all legal actions, rather the subset of these encodeable by the implementation. - The check for crushing on a stack move was incorrect (too strict), and this resulted in many legitimate moves being igonored. Finally, in other changes, weights have also been improved by training all games instead of some subset for chosen players, and clang-format was run on the codebase.
2 days	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 So cnn1986 has been replaced by nn1986, a standard, two-layer, dense nn configured as a binary classifier and (mis)used in that capacity.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.
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