diff options
| author | tslil <tslil@posteo.de> | 2026-09-11 12:56:12 +0100 |
|---|---|---|
| committer | tslil <tslil@posteo.de> | 2026-09-11 17:00:18 +0100 |
| commit | 6e90f1145b2c5c0f2dcc82d21ec45432274b8cad (patch) | |
| tree | 18db1c03ea7c3c4724028fc5154d4bca3d7200a5 /include/nn.h | |
| parent | 220a4b79e4b6d742a9ca7c278a1962b870500fbc (diff) | |
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.
Diffstat (limited to 'include/nn.h')
0 files changed, 0 insertions, 0 deletions