.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/demo_agents/video_plot_a2c.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_video_plot_a2c.py>`
        to download the full example code

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

.. _sphx_glr_auto_examples_demo_agents_video_plot_a2c.py:


==============================================
A demo of A2C algorithm in PBall2D environment
==============================================
 Illustration of how to set up an A2C algorithm in rlberry.
 The environment chosen here is PBALL2D environment.

.. video:: ../../video_plot_a2c.mp4
   :width: 600

.. GENERATED FROM PYTHON SOURCE LINES 12-33

.. code-block:: python3


    from rlberry_research.agents.torch import A2CAgent
    from rlberry_research.envs.benchmarks.ball_exploration import PBall2D
    from gymnasium.wrappers import TimeLimit


    env = PBall2D()
    env = TimeLimit(env, max_episode_steps=256)
    n_timesteps = 50_000
    agent = A2CAgent(env, gamma=0.99, learning_rate=0.001)
    agent.fit(budget=n_timesteps)

    env.enable_rendering()

    observation, info = env.reset()
    for tt in range(200):
        action = agent.policy(observation)
        observation, reward, terminated, truncated, info = env.step(action)
        done = terminated or truncated

    video = env.save_video("_video/video_plot_a2c.mp4")


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

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


.. _sphx_glr_download_auto_examples_demo_agents_video_plot_a2c.py:

.. only:: html

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




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

      :download:`Download Python source code: video_plot_a2c.py <video_plot_a2c.py>`

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

      :download:`Download Jupyter notebook: video_plot_a2c.ipynb <video_plot_a2c.ipynb>`


.. only:: html

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

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