.. 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_ppo.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_ppo.py>`
        to download the full example code

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

.. _sphx_glr_auto_examples_demo_agents_video_plot_ppo.py:


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

.. video:: ../../video_plot_ppo.mp4
   :width: 600

.. GENERATED FROM PYTHON SOURCE LINES 12-31

.. code-block:: python3


    from rlberry_research.agents.torch import PPOAgent
    from rlberry_research.envs.benchmarks.ball_exploration import PBall2D


    env = PBall2D()
    n_steps = 3e3

    agent = PPOAgent(env)
    agent.fit(budget=n_steps)

    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_ppo.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_ppo.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_ppo.py <video_plot_ppo.py>`

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

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


.. only:: html

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

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