From 7f1566fb21dfe8c99bc770885cc2cc4e478e16b4 Mon Sep 17 00:00:00 2001 From: tslil Date: Sat, 12 Sep 2026 19:37:56 +0100 Subject: move data generation into the epoch loop Previously we would spend all of the training epochs on making the network a better predictor of the *initial* TD-leaf values that we computed before the start of the first epoch. There's definitely something stale about this, given that the TD-leaf training targets involved the net evaluation at PVs. I'm not overly confident that this makes sense, but as a kind of compromise between fully on-line TD-leaf and the fully stale version we had before, we now recompute the TD-leaf values in each epoch with the fine-tuned net instead of the epoch 0 net. Perhaps we were just lucky, but this seems to train a strong network under the default setting. More experimentation is required. --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'Makefile') diff --git a/Makefile b/Makefile index 1b87677..d6ca030 100644 --- a/Makefile +++ b/Makefile @@ -37,7 +37,7 @@ cand_b = $(word 2,$(subst -, ,$1)) .PHONY: selfplay-% selfplay-%: rm -f selfplay-% - rm -f src/*.o include/*.o + rm -f src/*.o include/negamax.o include/pv.o include/tt.o $(MAKE) SELFPLAY_OUT=$@ \ DEFINES="-DRECORD_PV -DCAND_A=$(call cand_a,$*) -DCAND_B=$(call cand_b,$*) \ -DCAND_A_WEIGHTS_5='\"cand_$(call cand_a,$*)_weights_5.c\"' \ -- cgit v1.3.1