Delete compiled cache + re-inject Unsloth attrs for Kaggle/Colab compat

Bypass Unsloth GRPO compilation - fix SymFloat crash on Colab/Kaggle

Inject unsloth_logit_chunk_multiplier into GRPOConfig

Inject all expected Unsloth GRPO args

Inject unsloth_num_chunks into GRPOConfig

Remove unsupported kwargs from GRPOConfig

Disable PatchFastRL to fix Colab OSError

Fix openenv dependency name in notebook

Fix notebook dependencies and CUDA attribute

Add Colab GRPO training notebook

Add pyarrow to notebook dependencies to fix colab mismatch

Fix openenv missing from notebook

Update latest changes

Update training notebook and verifiers

Hackathon Final Submission: PettingZoo multi-agent arch, GRPO training, docs