move from single candidate td-leaf with gating to tournament of a population

The goal in this change was to overcome the rock-paper-scissors phenomenon that was happening in capability space by having on a single candidate learn to beat the most recent version of itself. In some sense this lead to rotating around in capability space instead of chasing monotonic improvements.

I hope that flipping to a system in which many (N=5) candidates play each other and learn from their own set of diverse games in this pool, combined with --replay-iters, will lead to a given network having to have a much more comprehensive understanding of the space of tactics. I haven't yet had time to train this thorougly, will run those experiments on my desktop computer.

1 files changed, 6 insertions, 0 deletions

diff --git a/.clangd b/.clangd
index 3b254c0..d6d8b02 100644
--- a/.clangd
+++ b/.clangd
@@ -9,6 +9,12 @@ CompileFlags:
     - -I../include
     - -D_DEFAULT_SOURCE
     - -DRECORD_PV
+    - -DCAND_A=1
+    - -DCAND_B=2
+    - -DCAND_A_WEIGHTS_5="cand_1_weights_5.c"
+    - -DCAND_A_WEIGHTS_6="cand_1_weights_6.c"
+    - -DCAND_B_WEIGHTS_5="cand_2_weights_5.c"
+    - -DCAND_B_WEIGHTS_6="cand_2_weights_6.c"
     - -Wall
     - -Wextra
     - -Wpedantic