Fishy RL
========

**Fishy RL** is a distributed reinforcement learning framework for model-based and model-free algorithms. It is designed to be *flexible* and *user-friendly*, allowing researchers and practitioners to easily interchange components and environments.

.. note::
   This documentation is still under construction. Please check back later for more information and examples.

.. toctree::
   :maxdepth: 3
   :caption: Contents:

   API reference <api/fishyrl>