Update OpenEnv guide with new notebook (#4555)

Author: sergiopaniego

docs/source/openenv.md

@@ -5,7 +5,7 @@
 In this guide, we’ll focus on **how to integrate OpenEnv with TRL**, but feel free to explore the links above to dive deeper into OpenEnv itself.
 
 > [!NOTE]
-> You can explore ready-to-use example scripts in the [`examples/scripts/openenv/`](https://github.com/huggingface/trl/blob/main/examples/scripts/openenv/) directory.
+> You can explore ready-to-use example [scripts](example_overview#scripts) and [notebooks](example_overview#notebooks) in the Examples Overview.
 
 > [!NOTE]
 > Explore the [OpenEnv docs](https://meta-pytorch.org/OpenEnv/) for more details.
@@ -349,6 +349,9 @@ Below is the reward curve from training:
 
 Let's level this up a bit by training a model to interact with a more complex environment. We'll use the game word guessing game [wordle](https://www.nytimes.com/games/wordle/index.html) from the [`TextArena`](https://meta-pytorch.org/OpenEnv/environments/textarena/) environment.
 
+> [!NOTE]  
+> You can explore the notebook version of this example [here](https://github.com/huggingface/trl/blob/main/examples/notebooks/openenv_wordle_grpo.ipynb).
+
 ### The TextArena Environment
 
 [TextArena](https://huggingface.co/papers/2504.11442) is an open-source collection of competitive text-based games designed to evaluate reasoning skills in LLMs using textual games like Wordle, Snake, Tic-Tac-Toe, and more. Research has shown that such games improve model performance on reasoning tasks.