Create cleanrl.md

docs/hub/cleanrl.md

@@ -0,0 +1,24 @@
+# Using CleanRL at Hugging Face
+
+[CleanRL](https://github.com/vwxyzjn/cleanrl) is a Deep Reinforcement Learning library that provides high-quality single-file implementation with research-friendly features.
+
+## Exploring Stable-Baselines3 in the Hub
+
+You can find CleanRL models by filtering at the left of the [models page](https://huggingface.co/models?library=cleanrl).
+
+All models on the Hub come up with useful features:
+1. An automatically generated model card with a description, a training configuration, and more.
+2. Metadata tags that help for discoverability.
+3. A video widget where you can watch your agent performing.
+
+## Using existing models
+WIP
+
+## Sharing your models
+WIP
+
+
+## Additional resources
+- CleanRL [documentation](https://docs.cleanrl.dev/)
+
+