Spaces:

InosLihka
/

rhythm_env

Sleeping

App Files Files Community

Ctrl+K

Ctrl+K

3 contributors

History: 19 commits

InosLihka's picture

Claude Opus 4.7 (1M context)

env: meta-RL refactor (continuous profiles, action+belief, adaptation grader)

ecbe0d8 15 days ago

docs
docs: add sim-to-real deployment architecture reference 15 days ago
scripts
env: meta-RL refactor (continuous profiles, action+belief, adaptation grader) 15 days ago
server
env: meta-RL refactor (continuous profiles, action+belief, adaptation grader) 15 days ago
tests
env: meta-RL refactor (continuous profiles, action+belief, adaptation grader) 15 days ago
training
env: meta-RL refactor (continuous profiles, action+belief, adaptation grader) 15 days ago
ui
refactor: rewrite blog around product vision; fix UI for Gradio 6 15 days ago
.dockerignore

92 Bytes
Initial commit: RhythmEnv daily planning RL environment about 1 month ago
.gitignore

68 Bytes
Initial commit: RhythmEnv daily planning RL environment about 1 month ago
Dockerfile

2.79 kB
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline 15 days ago
README.md

13.7 kB
env: meta-RL refactor (continuous profiles, action+belief, adaptation grader) 15 days ago
__init__.py

724 Bytes
env: enrich observation with history, anomalies, and discovery bonus 15 days ago
blog_post.md

7.95 kB
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline 15 days ago
client.py

3.13 kB
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline 15 days ago
eval_baselines_meta.json

70.4 kB
env: meta-RL refactor (continuous profiles, action+belief, adaptation grader) 15 days ago
eval_results.json

14 kB
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline 15 days ago
eval_results_v1.json

14 kB
env: meta-RL refactor (continuous profiles, action+belief, adaptation grader) 15 days ago
inference.py

12.7 kB
env: meta-RL refactor (continuous profiles, action+belief, adaptation grader) 15 days ago
models.py

3.54 kB
env: enrich observation with history, anomalies, and discovery bonus 15 days ago
openenv.yaml

93 Bytes
Initial commit: RhythmEnv daily planning RL environment about 1 month ago
pyproject.toml

909 Bytes
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline 15 days ago
training_log.json

513 kB
Add Run 3 training results: plots, training log, README update 15 days ago
uv.lock

576 kB
Initial commit: RhythmEnv daily planning RL environment about 1 month ago