Commit History
-
docs: add model card YAML metadata
1aa7daf -
feat: add Q-Learning agent trained on teeunit-env Space
- New Q-Learning agent (20 episodes, 938 steps, 39.38 total reward) - JSON and pickle formats for easy loading - Comprehensive README with usage examples - Links to HF Space and GitHub repo Trained on: https://huggingface.co/spaces/ziadbc/teeunit-env868f2dd -
Training complete: 10000 steps
Verified signature9f1799f -
initial commit
Verified signature1fcb2ad