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 So cnn1986 has been replaced by nn1986, a standard, two-layer, dense nn configured as a binary classifier and (mis)used in that capacity.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	Fix copyright notice in files, and small preemptive optimisation	tslil clingman
	Eventually there'll be a more complicated data generation step than the one we're presently using, so having it in-lined in the loop is wasteful. Ideally also this would be update per ply and we could avoid recalculating it entirely for every query -- though it's probably ``fast enough'' for now. Also, caching is WIP.
2 days	Rename ct_k -> ct, IANAL but ...	tslil

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	Added license information!	tslil clingman

2 days	Finally fixed memory order of weights!	tslil clingman

2 days	New weights from a wider training	tslil clingman

2 days	Went back up to 1986 weights	tslil

2 days	There was a bug in the minimax!	tslil

2 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.
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	Auto-generating weights	tslil

2 days	New weights	tslil

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

2 days	This finally works!	tslil