sb3-soft Documentation
======================

Reinforcement learning algorithms with soft Q-targets, built for Stable-Baselines3.

`sb3-soft` currently provides:

- `SQL: Discrete Soft Q-Learning <https://proceedings.mlr.press/v70/haarnoja17a.html>`_
- `SDSAC: Stable Discrete Soft Actor-Critic <https://openreview.net/forum?id=EUF2R6VBeU>`_

.. toctree::
   :maxdepth: 2
   :caption: User Guide

   quickstart

.. toctree::
   :maxdepth: 2
   :caption: API Reference

   api/index