From 241156da6f35cb888253e6b8814e7b61a76b4fc7 Mon Sep 17 00:00:00 2001 From: tslil Date: Sun, 30 Aug 2026 19:46:07 +0100 Subject: TD(lambda), and a big rework NOTE: 6x6 weights are as-yet untrained On the performance side: * switch from linked-list chaining hash table to direct mapping * cache check_win by hash * persist transposition tables across plies (this was a big deal and difficult to puzzle out) * add align directives to the network floats * prepare_nn_input gained a small LUT to avoid branching (i suppose you might call this 1D embedding) * apply mtune=native for the native builds On the correctness side: * Zobrist has now includes the ply parity * the network now predicts something in [-1, 1] using tanh (approximated by polynomials) * the training object is now MSE because we're learning a value estimate * use .clangd instead of compile_commands.json On the training side: * completely forgo human-derived data set * implement td(lambda), self-play, tournaments --- include/nn_input.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) create mode 100644 include/nn_input.c (limited to 'include/nn_input.c') diff --git a/include/nn_input.c b/include/nn_input.c new file mode 100644 index 0000000..2fbd8da --- /dev/null +++ b/include/nn_input.c @@ -0,0 +1,54 @@ +/* + This file is part of ctak. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, but + WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + General Public License for more details. + + You should have received a copy of the GNU General Public License + along with ctak. If not, see . +*/ + +#include "nn.h" +#include "tak.h" + +/* + * Encode a board position into the network's input vector: + * [0] ply parity (-1 / +1) + * [1] white flats remaining, as a fraction of the total + * [2] black flats remaining, as a fraction of the total + * [3 ..] one scalar per cell for the top stone: + * 0 empty, +-0.25 standing, +-0.5 flat, +-1 capstone, + * + white, - black + * + * `cur_board' must have room for 3 + board_size*board_size floats. + */ + +// The per-cell scalar depends only on the top stone's colour, variant +// and occupancy, so it's a table lookup keyed on those three bits. +static const float cell_scalar[16] = { + 0.0f, -0.5f, 0.0f, -0.25f, 0.0f, -1.0f, 0.0f, 0.0f, // black + 0.0f, +0.5f, 0.0f, +0.25f, 0.0f, +1.0f, 0.0f, 0.0f, // white +}; + +void nn_prepare_input(float *cur_board, tak_state_p state) { + const float inv_max_flats = + (state->board_size == 6) ? (1.0f / 30.0f) : (1.0f / 21.0f); + const unsigned int n_cells = state->board_size * state->board_size; + for (unsigned int loc = 0; loc < n_cells; loc++) { + const uint8_t d = state->celldat[loc]; + cur_board[3 + loc] = cell_scalar[((state->colours[loc] & 1) << 3) | + ((d & STONE_MASK) << 1) | + ((d & NUM_MASK) != 0)]; + } + // Add input of flat counts and ply parity + cur_board[0] = (state->ply & 1) ? 1 : -1; + cur_board[1] = (float)(state->white_count & 127) * inv_max_flats; + cur_board[2] = (float)(state->black_count & 127) * inv_max_flats; +} -- cgit v1.3.1