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 --- .gitignore | 6 ++++++ 1 file changed, 6 insertions(+) (limited to '.gitignore') diff --git a/.gitignore b/.gitignore index 52a279d..b013cd7 100644 --- a/.gitignore +++ b/.gitignore @@ -1,9 +1,15 @@ *.o data/ +include/cand_weights_*.c ct1986* ctlm* pptdb* cttei* geminict* +selfplay* +match* +__pycache__/ +production-*.log buildroot* +test/ .cache -- cgit v1.3.1