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

.. only:: html

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

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

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

.. _sphx_glr_info_auto_examples_plot_new_obj.py:


New Objective
=====================
An example to implement a new blackbox objective for any PyXAB algorithm to optimize. First import all the useful packages

.. GENERATED FROM PYTHON SOURCE LINES 7-13

.. code-block:: default


    from PyXAB.synthetic_obj.Objective import Objective
    from PyXAB.algos.HOO import T_HOO
    from PyXAB.partition.BinaryPartition import BinaryPartition









.. GENERATED FROM PYTHON SOURCE LINES 14-17

We have already shown a ``Sine`` function example in the general instructions.
Here, we give another very simple example. Suppose the objective is only a constant, i.e., ``f(x) = 1`` everywhere,
then the class definition would be as simple as.

.. GENERATED FROM PYTHON SOURCE LINES 17-27

.. code-block:: default


    class Constant_1(Objective):
        def __init__(self):
            self.fmax = 1

        def f(self, x):
            return 1










.. GENERATED FROM PYTHON SOURCE LINES 28-30

The inheritance of the ``Objective`` class is unnecessary (but highly recommended for consistency).
E.g., another possible definition could be

.. GENERATED FROM PYTHON SOURCE LINES 30-37

.. code-block:: default


    class Constant_2():

        def evaluate(self, x):
            return 1









.. GENERATED FROM PYTHON SOURCE LINES 38-40

Let us suppose the domain for this objective is ``[0, 10]``, and we use the binary partition for the domain and the HOO
algorithm to optimize the objectives

.. GENERATED FROM PYTHON SOURCE LINES 40-48

.. code-block:: default


    T = 100
    target1 = Constant_1()
    target2 = Constant_2()
    domain = [[0, 10]]
    partition = BinaryPartition
    algo = T_HOO(domain=domain, partition=partition)








.. GENERATED FROM PYTHON SOURCE LINES 49-50

Now as can be seen below, the objectives are ready to be optimized

.. GENERATED FROM PYTHON SOURCE LINES 50-65

.. code-block:: default


    # Optimize Objective Constant_1
    for t in range(1, T+1):

        point = algo.pull(t)
        reward = target1.f(point)
        algo.receive_reward(t, reward)


    # Optimize Objective Constant_2
    for t in range(1, T+1):

        point = algo.pull(t)
        reward = target2.evaluate(point)
        algo.receive_reward(t, reward)








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

   **Total running time of the script:** (0 minutes 0.273 seconds)


.. _sphx_glr_download_info_auto_examples_plot_new_obj.py:

.. only:: html

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




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

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

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

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


.. only:: html

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

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