Add minigrid docs

docs/datasets/minigrid.md

@@ -0,0 +1,20 @@
+---
+firstpage:
+lastpage:
+---
+
+# MiniGrid
+
+Dataset generated from the [MiniGrid-FourRooms environment](https://minigrid.farama.org/environments/minigrid/FourRoomsEnv/). The objective of the agent is to reach a goal position in a gridworld.
+We regenerate the dataset of [D4RL](https://github.com/Farama-Foundation/D4RL/wiki/Tasks#minigrid-fourrooms) for full reproducibility, using a random policy and an expert policy that navigates straight to the goal.
+
+
+```{toctree}
+:hidden:
+minigrid/random.md
+minigrid/expert.md
+```
+
+## References
+
+[1] Fu, Justin, et al. ‘D4RL: Datasets for Deep Data-Driven Reinforcement Learning’. CoRR, vol. abs/2004.07219, 2020, https://arxiv.org/abs/2004.07219.

docs/requirements.txt

@@ -4,5 +4,6 @@ sphinx_github_changelog
 myst-parser
 google-cloud-storage==2.5.0
 gymnasium-robotics>=1.2.1
+minigrid>=2.2.0
 git+https://github.com/sphinx-gallery/sphinx-gallery.git@4006662c8c1984453a247dc6d3df6260e5b00f4b#egg=sphinx_gallery
 git+https://github.com/Farama-Foundation/Celshast#egg=furo

pyproject.toml

@@ -43,7 +43,6 @@ testing = [
     "nbmake",
     "gymnasium-robotics>=1.2.3",
     "imageio>=2.14.1",
-    "minigrid>=2.2.0",
 ]
 
 [project.urls]