diff options
| author | tslil <tslil@posteo.de> | 2026-08-30 19:46:07 +0100 |
|---|---|---|
| committer | tslil <tslil@posteo.de> | 2026-09-02 12:13:01 +0100 |
| commit | 241156da6f35cb888253e6b8814e7b61a76b4fc7 (patch) | |
| tree | e562029445b1473cc89590793f32c561540d621c /include/xorshift64.c | |
| parent | 696c3808220ea9d8c604939894a2d509f05cc4c6 (diff) | |
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
Diffstat (limited to 'include/xorshift64.c')
| -rw-r--r-- | include/xorshift64.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/include/xorshift64.c b/include/xorshift64.c index 0a68c71..c758a47 100644 --- a/include/xorshift64.c +++ b/include/xorshift64.c @@ -1,5 +1,5 @@ /* - This file is part of ct. + 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 @@ -12,7 +12,7 @@ General Public License for more details. You should have received a copy of the GNU General Public License - along with ct. If not, see <https://www.gnu.org/licenses/>. + along with ctak. If not, see <https://www.gnu.org/licenses/>. */ #include "xorshift64.h" |