Spaces:

InosLihka
/

rhythm_env

Sleeping

App Files Files Community

rhythm_env / docs

1.2 MB

Ctrl+K

Ctrl+K

3 contributors

History: 4 commits

InosLihka's picture

fix: reduce kl_coef to prevent training instability

0bdfeaa about 1 month ago

references
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline about 1 month ago
round1
Reorganize docs: segregate Round 1 and Round 2 about 1 month ago
round2
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline about 1 month ago
blog_post.md

7.83 kB
fix: reduce kl_coef to prevent training instability about 1 month ago