Add pipeline tag, license and code link

This PR adds the `pipeline_tag` (`reinforcement-learning`) and `license` (`apache-2.0`) metadata, and links the official GitHub repository so users can find the code and CLI used with these checkpoints.

README.md

@@ -1,11 +1,15 @@
 ---
 library_name: pytorch
+pipeline_tag: reinforcement-learning
+license: apache-2.0
 ---
 
 # AnyGoal model checkpoints
 
 paper: [https://arxiv.org/abs/2610.26844](https://arxiv.org/abs/2610.26844)
 
+Code: [https://github.com/galilai-group/AnyGoal](https://github.com/galilai-group/AnyGoal)
+
 Model checkpoints for [AnyGoal](https://hazel-heejeong-nam.github.io/anygoal/), a compositional generalization suite for world-model research. The repository provides checkpoints used by AnyGoal's rollout and planning integrations while preserving each model's native checkpoint format.
 
 ## Quick start
@@ -124,4 +128,4 @@ See the [AnyGoal documentation](https://hazel-heejeong-nam.github.io/anygoal/) f
 
 ## Metadata and attribution
 
-AnyGoal-produced checkpoints are accompanied by same-named JSON sidecars containing provenance and recoverable training metadata. Third-party model architectures and imported checkpoints remain subject to their original attribution and licensing requirements.
+AnyGoal-produced checkpoints are accompanied by same-named JSON sidecars containing provenance and recoverable training metadata. Third-party model architectures and imported checkpoints remain subject to their original attribution and licensing requirements.