Spaces:

InosLihka
/

rhythm_env

Sleeping

App Files Files Community

1.93 MB

Ctrl+K

Ctrl+K

3 contributors

History: 8 commits

InosLihka's picture

Claude Sonnet 4.6

fix: reduce kl_coef to prevent training instability

0bdfeaa 30 days ago

docs
fix: reduce kl_coef to prevent training instability 30 days ago
server
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline about 1 month ago
tests
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline about 1 month ago
training
fix: reduce kl_coef to prevent training instability 30 days ago
ui
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline about 1 month ago
.dockerignore

92 Bytes
Initial commit: RhythmEnv daily planning RL environment about 2 months ago
.gitignore

68 Bytes
Initial commit: RhythmEnv daily planning RL environment about 2 months ago
Dockerfile

2.79 kB
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline about 1 month ago
README.md

9.37 kB
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline about 1 month ago
__init__.py

694 Bytes
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline about 1 month ago
blog_post.md

7.95 kB
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline about 1 month ago
client.py

3.13 kB
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline about 1 month ago
eval_results.json

14 kB
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline about 1 month ago
inference.py

11.6 kB
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline about 1 month ago
models.py

2.22 kB
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline about 1 month ago
openenv.yaml

93 Bytes
Initial commit: RhythmEnv daily planning RL environment about 2 months ago
pyproject.toml

909 Bytes
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline about 1 month ago
uv.lock

576 kB
Initial commit: RhythmEnv daily planning RL environment about 2 months ago