.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/demo_agents/demo_SAC.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_auto_examples_demo_agents_demo_SAC.py>`
        to download the full example code

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_demo_agents_demo_SAC.py:


=============================
SAC Soft Actor-Critic
=============================

This script shows how to train a SAC agent on a Pendulum environment.

.. GENERATED FROM PYTHON SOURCE LINES 8-44

.. code-block:: python3


    import time

    import gymnasium as gym
    from rlberry_research.agents.torch.sac import SACAgent
    from rlberry_research.envs import Pendulum
    from rlberry.manager import ExperimentManager


    def env_ctor(env, wrap_spaces=True):
        return env


    # Setup agent parameters
    env_name = "Pendulum"
    fit_budget = int(2e5)
    agent_name = f"{env_name}_{fit_budget}_{int(time.time())}"

    # Setup environment parameters
    env = Pendulum()
    env = gym.wrappers.TimeLimit(env, max_episode_steps=200)
    env = gym.wrappers.RecordEpisodeStatistics(env)
    env_kwargs = dict(env=env)

    # Create agent instance
    xp_manager = ExperimentManager(
        SACAgent,
        (env_ctor, env_kwargs),
        fit_budget=fit_budget,
        n_fit=1,
        enable_tensorboard=True,
        agent_name=agent_name,
    )

    # Start training
    xp_manager.fit()


.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 0.000 seconds)


.. _sphx_glr_download_auto_examples_demo_agents_demo_SAC.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example




    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: demo_SAC.py <demo_SAC.py>`

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: demo_SAC.ipynb <demo_SAC.ipynb>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_