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/tt.h | 62 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) create mode 100644 include/tt.h (limited to 'include/tt.h') diff --git a/include/tt.h b/include/tt.h new file mode 100644 index 0000000..b8e1a2e --- /dev/null +++ b/include/tt.h @@ -0,0 +1,62 @@ +/* + 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 . +*/ + +#ifndef TT_H +#define TT_H + +#include + +#include + +// =================================================================== +// Types +// =================================================================== + +enum TT_FLAG { TT_EXACT, TT_LOWERBOUND, TT_UPPERBOUND }; + +typedef struct tt_node_s { + uint16_t gen; + uint64_t key; + enum TT_FLAG flag; + uint8_t depth; + float value; + action_t action; +} tt_entry_t; + +// =================================================================== +// Variables +// =================================================================== + +// Direct-mapped hash table (no chaining); one slot per key. +#define TT_SIZE ((uint32_t)((1 << 19) - 1)) + +// =================================================================== +// Methods +// =================================================================== + +// Bump the generation counter, invalidating all entries (memsets the +// table on wraparound). Called from negamax_init when the board size +// (and hence the zobrist table) changes; entries are otherwise kept +// across plies on purpose (see negamax.c). +int tt_init(void); + +tt_entry_t *tt_seek(const uint64_t key); + +int tt_insert(const uint64_t key, const enum TT_FLAG flag, const uint8_t depth, + const float value, const action_t action); + +#endif -- cgit v1.3.1