ctak/include/pv.h, branch hybrid_rootstrapAn implementation of Tak and a computer opponent in Chttps://git.l-3.space/ctak/atom/include/pv.h?h=hybrid_rootstrap2026-09-10T20:04:40Zcredit Mitchell Riley: we can drop 65 parameters for about the same strength; also train for longer2026-09-10T20:04:40Ztsliltslil@posteo.de2026-09-10T13:12:41Zurn:sha1:220a4b79e4b6d742a9ca7c278a1962b870500fbc
The idea is that the current model is M_theta(board, ply) = "score for player 0", but we can instead create a different model M'_theta(board) = "score for player 0 assuming that it's player 0's move" and for a certain pair of functions sigma, normalise, recover M_theta(board, ply) = sigma(ply) M'_theta(normalise(board, ply)).
This pair of functions is sigma(ply) = +/- 1 (parity), and normalise being a conditional interchange of pieces on the board depending on the parity of the ply. The only things stopping this from being completely straightforward is that nn_train.py evaluates M'_theta itself so we need to pass sigma(ply) to the training loop.
6x6 is still untrained.
~25% speedup in selfplay due to: incremental zobrist hashing, smarter road checking, re-using the input computed for the NN2026-09-09T20:45:17Ztsliltslil@posteo.de2026-09-08T10:55:28Zurn:sha1:1c9e266ae25f7f6067806d139e5971ce8513d2f6TD-leaf and another negamax bug2026-09-04T20:03:59Ztsliltslil@posteo.de2026-09-03T19:17:22Zurn:sha1:1ca3309dad9d412870b2b793f33af7a7ccabd514
TD-lambda and TD-leaf are separated by the observation that minimax with a parameterised leaf heuristic is differentiable* in the parameters. "All" that had to be done was to extract the "principal variation": which one position survived all of the pruning to become the reported value.
This was a bit fiddly and uncovered a subtle bug (again) in negamax.c: we were not being complete in our overriding of the TT entry and by omitting key it was possible that later searches would find incorrect values.
The more interesting question to me was: how do we introduce enough variety while not corrupting the PV chain? I settled on having selfplay have one of the players be epsilon-random but the other greedy (minimax) and simply report only the greedy portion PV chain. This appears to work well enough in practice and doesn't introduce nonsense training data for the net (we don't force its actions to be nonsensical). I also deciced, perhaps in a departure from tradition, that we had good supervised labels for PVs that happened to be winning states, so the training overrides the targets in that case. Finally rolled back some of the ambition in nn_train.py default arguments.
*almost always