docs homepage

automl · May 30, 2024 · f27bccc · f27bccc
1 parent 9d393e6
commit f27bccc
Show file tree

Hide file tree

Showing 3 changed files with 13 additions and 2 deletions.
diff --git a/docs/basic_usage/env_subsets.rst b/docs/basic_usage/env_subsets.rst
@@ -5,7 +5,7 @@ We analyzed the hyperparameter landscapes of PPO, DQN and SAC on 20 environments
 
 .. image:: path/subsets.png
  :width: 800
- :alt: Alternative text
+ :alt: Environment subsets for PPO, DQN and SAC
 
 We strongly recommend you focus your benchmarking on these exact environments to ensure you cover the space total landscape of RL behaviors well. 
 The data generated for selecting these environments is available on `HuggingFace <https://huggingface.co/datasets/autorl-org/arlbench>`_ for you to use in your experiments.

diff --git a/docs/images/structure.png b/docs/images/structure.png
diff --git a/docs/index.rst b/docs/index.rst
@@ -15,4 +15,15 @@ Home
  contributing
 
 
-Lorem ipsum dolor.
+Welcome to ARLBench, your pathway into efficient AutoRL!
+We offer lightning-fast implementations of PPO, DQN and SAC that are highly configurable as well as a subset of environments which will give you a representative result of your AutoRL method across the RL landscape.
+This documentation, in combination with our examples, should provide you with a starting point to get your AutoRL method up and running in no time.
+
+.. image:: path/structure.png
+ :width: 800
+ :alt: ARLBench overview figure
+
+You will interact with ARLBench through the `AutoRL Environment` class, which is the main entry point for all the functionalities that ARLBench offers.
+It works similarly to a gymnasium environment: you can use 'reset' to start a fresh run and then 'step' to take one configuration step. 
+Between steps, you can change your configuration to allow for flexible schedules.
+Additionally, the AutoRL Environment can also return information about the RL algorithm's internal state so you can build and learn reactive schedules as well.