From 6e90f1145b2c5c0f2dcc82d21ec45432274b8cad Mon Sep 17 00:00:00 2001 From: tslil Date: Fri, 11 Sep 2026 12:56:12 +0100 Subject: 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. --- include/weights_6.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/weights_6.h') diff --git a/include/weights_6.h b/include/weights_6.h index d927748..be64253 100644 --- a/include/weights_6.h +++ b/include/weights_6.h @@ -23,10 +23,10 @@ #define NN_ALIGNED __attribute__((aligned(16))) -extern const float six_embedding[7]; -extern const float six_dense_weights[SIX_DENSE_NUM][SIX_INP_NUM] NN_ALIGNED; -extern const float six_dense_biases[SIX_DENSE_NUM]; -extern const float six_logit_weights[SIX_DENSE_NUM] NN_ALIGNED; -extern const float six_logit_bias; +extern const float SIX_embedding[7]; +extern const float SIX_dense_weights[SIX_DENSE_NUM][SIX_INP_NUM] NN_ALIGNED; +extern const float SIX_dense_biases[SIX_DENSE_NUM]; +extern const float SIX_logit_weights[SIX_DENSE_NUM] NN_ALIGNED; +extern const float SIX_logit_bias; #endif -- cgit v1.3.1