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

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

.. _sphx_glr_auto_examples_demo_agents_video_plot_rs_kernel_ucbvi.py:


=============================================================
A demo of RSKernelUCBVIAgent algorithm in Acrobot environment
=============================================================
 Illustration of how to set up a RSKernelUCBVI algorithm in rlberry.
 The environment chosen here is Acrobot environment.

.. video:: ../../video_plot_rs_kernel_ucbvi.mp4
   :width: 600

.. GENERATED FROM PYTHON SOURCE LINES 12-49

.. code-block:: python3


    from rlberry_research.envs import Acrobot
    from rlberry_research.agents import RSKernelUCBVIAgent
    from rlberry.wrappers import RescaleRewardWrapper

    env = Acrobot()
    # rescake rewards to [0, 1]
    env = RescaleRewardWrapper(env, (0.0, 1.0))

    agent = RSKernelUCBVIAgent(
        env,
        gamma=0.99,
        horizon=300,
        bonus_scale_factor=0.01,
        min_dist=0.2,
        bandwidth=0.05,
        beta=1.0,
        kernel_type="gaussian",
    )
    agent.fit(budget=500)

    env.enable_rendering()
    observation, info = env.reset()

    time_before_done = 0
    ended = False
    for tt in range(2 * agent.horizon):
        action = agent.policy(observation)
        observation, reward, terminated, truncated, info = env.step(action)
        done = terminated or truncated
        if not done and not ended:
            time_before_done += 1
        if done:
            ended = True

    print("steps to achieve the goal for the first time = ", time_before_done)
    video = env.save_video("_video/video_plot_rs_kernel_ucbvi.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_rs_kernel_ucbvi.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_rs_kernel_ucbvi.py <video_plot_rs_kernel_ucbvi.py>`

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

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


.. only:: html

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

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