Spaces:

Darshankumarr03
/

mini-rl-openenv

Sleeping

App Files Files Community

mini-rl-openenv / training

51.5 kB

Ctrl+K

Ctrl+K

1 contributor

History: 15 commits

Darshan03's picture

feat: strictly bound task scores to (0, 1) range for RL training stability

470ff2f 7 months ago

baseline_openai.py

6.53 kB
fix: update all consumer files for OpenEnv model migration 8 months ago
config.py

650 Bytes
Unify ENV_URL and ensure full .env loading across all modules 8 months ago
dataset.py

4.52 kB
feat: migrate to native OpenEnv spec + TRL environment_factory 8 months ago
dry_run.py

3.03 kB
feat: migrate to native OpenEnv spec + TRL environment_factory 8 months ago
inference.py

7.3 kB
fix: update all consumer files for OpenEnv model migration 8 months ago
requirements.txt

98 Bytes
Add Docker deployment for HF Spaces 8 months ago
rewards.py

8.02 kB
revert: restore original rewards and env logic, keep grader normalization in inference only 7 months ago
rollout.py

4.54 kB
fix: update all consumer files for OpenEnv model migration 8 months ago
support_tool_env.py

9 kB
feat: migrate to native OpenEnv spec + TRL environment_factory 8 months ago
train.py

2.58 kB
feat: migrate to native OpenEnv spec + TRL environment_factory 8 months ago
verify_graders.py

5.26 kB
feat: strictly bound task scores to (0, 1) range for RL training stability 7 months ago