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

Age	Commit message (Collapse)	Author
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 So cnn1986 has been replaced by nn1986, a standard, two-layer, dense nn configured as a binary classifier and (mis)used in that capacity.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	Trying to make things faster	tslil
	I tried the following, but they all made things worse: - moving away from the singly-linked (tail tracking) list for actions by: + using an array zipper for a deque + using an array to poorly hold a floating deque - caching the results of generating move lists in the transposition table and then + copying the resulting list/zip/deque instead of generating it + applying the move-to-front without copying, but this made the search order worse. Presumably in this case shallower nodes were messing up the search tree with garbage moves? I think some of this is not supposed to happen, but i have just the right combination of poor evaluation function and naively ordered and cheap move generation that i'm in a local minimum here.
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	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	Try to squeeze out a little more performance	tslil clingman
	``Common wisdom'' dictates that placements are often better than stack moves, so we bias the generated move list in this fashion. Seems to be a little faster.
2 days	Added license information!	tslil clingman

2 days	Print progress before recursion rather than after	tslil clingman

2 days	It would appear that any function call whatsoever is slower :/	tslil clingman
	For now we'll stay with directly recomputing it at each non-terminal node
2 days	I don't have the presence of mind to debug this right now	tslil clingman

2 days	Small changes to build ct1986	tslil clingman

2 days	Storing best moves!	tslil clingman

2 days	This matches alpha-beta!	tslil clingman

2 days	Stable negamax-alpha-beta fail-soft	tslil clingman

2 days	Once again, adding TT changes the outcome	tslil clingman

2 days	Actually it seems before i was mis-counting	tslil clingman

2 days	There is still a bug, it doesn't appear to be checking enough	tslil clingman

2 days	Stripping debug stuff	tslil clingman

2 days	Still bugs...	tslil clingman

2 days	Still some bugs, standing stone becomes flat at depth4 self-play??	tslil clingman

2 days	There are still some bugs in the undo almost surely...	tslil clingman

2 days	Lots of bugfixes, mostly uint vs int. Still weirdness in game	tslil clingman

2 days	This is the basic idea, there's ≥ 1 bug (generates illegals...)	tslil clingman

2 days	Working on action lists to refactor	tslil clingman

2 days	Still trying	tslil clingman
	\|
2 days	Hash collisions	tslil clingman

2 days	Fixed some important bugs	tslil clingman

2 days	Attempting Zobrist hashing	tslil clingman